Token | that |
Token ID | 326 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
lehem | +2.736 |
RON | +2.583 |
rans | +2.547 |
rons | +2.489 |
enance | +2.460 |
Neg logit contributions | |
jriwal | -2.405 |
kefeller | -2.213 |
impulse | -2.103 |
turmoil | -1.960 |
reaction | -1.913 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
lehem | +0.491 |
RON | +0.461 |
rans | +0.452 |
rons | +0.441 |
enance | +0.438 |
Neg logit contributions | |
jriwal | -0.430 |
kefeller | -0.394 |
impulse | -0.381 |
turmoil | -0.359 |
reaction | -0.352 |
Token | usual |
Token ID | 6678 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
lehem | +0.435 |
RON | +0.411 |
rans | +0.403 |
rons | +0.395 |
enance | +0.392 |
Neg logit contributions | |
jriwal | -0.321 |
kefeller | -0.291 |
impulse | -0.280 |
turmoil | -0.262 |
reaction | -0.256 |
Token | � |
Token ID | 564 |
Feature activation | +5.09e+00 |
Pos logit contributions | |
lehem | +2.014 |
RON | +1.910 |
rans | +1.870 |
rons | +1.845 |
enance | +1.821 |
Neg logit contributions | |
jriwal | -1.603 |
kefeller | -1.471 |
impulse | -1.388 |
turmoil | -1.306 |
reaction | -1.261 |
Token | � |
Token ID | 246 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
lehem | +3.086 |
RON | +2.887 |
rans | +2.827 |
rons | +2.662 |
enance | +2.654 |
Neg logit contributions | |
jriwal | -6.150 |
kefeller | -5.844 |
impulse | -5.612 |
turmoil | -5.420 |
reaction | -5.299 |
Token | Elect |
Token ID | 19453 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
jriwal | +2.918 |
kefeller | +2.687 |
impulse | +2.666 |
turmoil | +2.536 |
reaction | +2.510 |
Neg logit contributions | |
lehem | -2.478 |
RON | -2.284 |
rans | -2.201 |
rons | -2.164 |
enance | -2.153 |
Token | rom |
Token ID | 398 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
lehem | +10.653 |
RON | +10.292 |
rons | +9.973 |
rans | +9.854 |
enance | +9.348 |
Neg logit contributions | |
jriwal | -10.804 |
kefeller | -10.555 |
impulse | -9.769 |
turmoil | -9.242 |
senal | -9.124 |
Token | agnetic |
Token ID | 25145 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
jriwal | +2.718 |
kefeller | +2.507 |
impulse | +2.472 |
turmoil | +2.340 |
reaction | +2.296 |
Neg logit contributions | |
lehem | -2.596 |
RON | -2.422 |
rans | -2.341 |
rons | -2.297 |
enance | -2.294 |
Token | field |
Token ID | 2214 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
jriwal | +1.307 |
kefeller | +1.187 |
impulse | +1.154 |
turmoil | +1.083 |
reaction | +1.058 |
Neg logit contributions | |
lehem | -1.727 |
RON | -1.629 |
rans | -1.594 |
rons | -1.562 |
enance | -1.550 |
Token | � |
Token ID | 447 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
lehem | +2.411 |
RON | +2.271 |
rans | +2.237 |
rons | +2.197 |
enance | +2.172 |
Neg logit contributions | |
jriwal | -2.127 |
kefeller | -1.963 |
impulse | -1.860 |
turmoil | -1.752 |
reaction | -1.696 |
Token | � |
Token ID | 247 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
jriwal | +2.033 |
kefeller | +1.899 |
impulse | +1.875 |
turmoil | +1.797 |
reaction | +1.774 |
Neg logit contributions | |
lehem | -1.199 |
RON | -1.085 |
rans | -1.048 |
rons | -1.018 |
enance | -0.998 |
Token | somewhere |
Token ID | 7382 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
lehem | +0.762 |
RON | +0.718 |
rans | +0.704 |
rons | +0.690 |
enance | +0.682 |
Neg logit contributions | |
jriwal | -0.605 |
kefeller | -0.556 |
impulse | -0.535 |
turmoil | -0.506 |
reaction | -0.490 |
Token | : |
Token ID | 25 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
lehem | +3.847 |
RON | +3.602 |
rans | +3.566 |
rons | +3.437 |
enance | +3.398 |
Neg logit contributions | |
jriwal | -3.229 |
kefeller | -3.039 |
impulse | -2.864 |
turmoil | -2.716 |
reaction | -2.624 |
Token |
|
Token ID | 198 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
lehem | +1.055 |
RON | +0.985 |
rans | +0.962 |
rons | +0.936 |
enance | +0.927 |
Neg logit contributions | |
jriwal | -1.071 |
kefeller | -0.989 |
impulse | -0.959 |
turmoil | -0.913 |
reaction | -0.891 |
Token |
|
Token ID | 198 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
lehem | +0.310 |
RON | +0.293 |
rans | +0.285 |
rons | +0.278 |
enance | +0.276 |
Neg logit contributions | |
jriwal | -0.328 |
kefeller | -0.302 |
impulse | -0.293 |
turmoil | -0.278 |
reaction | -0.271 |
Token | REF |
Token ID | 31688 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
lehem | +0.436 |
RON | +0.407 |
rans | +0.397 |
rons | +0.384 |
enance | +0.380 |
Neg logit contributions | |
jriwal | -0.505 |
kefeller | -0.470 |
impulse | -0.458 |
turmoil | -0.436 |
reaction | -0.427 |
Token | LECT |
Token ID | 16779 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
jriwal | +3.288 |
kefeller | +3.037 |
impulse | +3.016 |
turmoil | +2.855 |
reaction | +2.817 |
Neg logit contributions | |
lehem | -2.620 |
RON | -2.405 |
rans | -2.341 |
rons | -2.294 |
enance | -2.281 |
Token | _ |
Token ID | 62 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
RON | +10.382 |
lehem | +10.236 |
rons | +9.468 |
rans | +9.443 |
enance | +9.151 |
Neg logit contributions | |
jriwal | -10.707 |
kefeller | -10.098 |
impulse | -9.279 |
turmoil | -9.070 |
inki | -8.868 |
Token | CLASS |
Token ID | 31631 |
Feature activation | +7.23e+00 |
Pos logit contributions | |
lehem | +1.642 |
RON | +1.545 |
rans | +1.496 |
rons | +1.456 |
enance | +1.438 |
Neg logit contributions | |
jriwal | -1.785 |
kefeller | -1.647 |
impulse | -1.603 |
turmoil | -1.528 |
reaction | -1.490 |
Token | _ |
Token ID | 62 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
lehem | +6.190 |
RON | +5.956 |
rans | +5.728 |
rons | +5.619 |
enance | +5.400 |
Neg logit contributions | |
jriwal | -6.817 |
kefeller | -6.369 |
impulse | -5.965 |
turmoil | -5.745 |
senal | -5.611 |
Token | ST |
Token ID | 2257 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
lehem | +1.519 |
RON | +1.430 |
rans | +1.385 |
rons | +1.347 |
enance | +1.331 |
Neg logit contributions | |
jriwal | -1.658 |
kefeller | -1.533 |
impulse | -1.492 |
turmoil | -1.420 |
reaction | -1.388 |
Token | ART |
Token ID | 7227 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
lehem | +2.241 |
RON | +2.112 |
rans | +2.053 |
rons | +1.990 |
enance | +1.957 |
Neg logit contributions | |
jriwal | -2.710 |
kefeller | -2.513 |
impulse | -2.437 |
turmoil | -2.328 |
reaction | -2.282 |
Token | . |
Token ID | 13 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
jriwal | +0.783 |
kefeller | +0.711 |
impulse | +0.693 |
turmoil | +0.650 |
reaction | +0.636 |
Neg logit contributions | |
lehem | -1.008 |
RON | -0.951 |
rans | -0.930 |
rons | -0.911 |
enance | -0.904 |
Token | � |
Token ID | 447 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
lehem | +0.314 |
RON | +0.294 |
rans | +0.287 |
rons | +0.280 |
enance | +0.278 |
Neg logit contributions | |
jriwal | -0.314 |
kefeller | -0.290 |
impulse | -0.282 |
turmoil | -0.267 |
reaction | -0.261 |
Token | � |
Token ID | 251 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
jriwal | +2.094 |
kefeller | +1.952 |
impulse | +1.923 |
turmoil | +1.843 |
reaction | +1.815 |
Neg logit contributions | |
lehem | -1.408 |
RON | -1.289 |
rans | -1.250 |
rons | -1.222 |
enance | -1.196 |
Token |
|
Token ID | 198 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
lehem | +3.578 |
RON | +3.382 |
rans | +3.279 |
rons | +3.186 |
enance | +3.171 |
Neg logit contributions | |
jriwal | -3.940 |
kefeller | -3.693 |
impulse | -3.532 |
turmoil | -3.339 |
reaction | -3.248 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
lehem | +0.015 |
RON | +0.014 |
rans | +0.014 |
rons | +0.013 |
enance | +0.013 |
Neg logit contributions | |
jriwal | -0.015 |
kefeller | -0.014 |
impulse | -0.014 |
turmoil | -0.013 |
reaction | -0.013 |
Token | Elect |
Token ID | 19453 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
lehem | +0.118 |
RON | +0.111 |
rans | +0.107 |
rons | +0.105 |
enance | +0.104 |
Neg logit contributions | |
jriwal | -0.133 |
kefeller | -0.123 |
impulse | -0.120 |
turmoil | -0.114 |
reaction | -0.112 |
Token | a |
Token ID | 64 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
lehem | +9.610 |
RON | +9.432 |
rons | +9.023 |
rans | +8.948 |
enance | +8.437 |
Neg logit contributions | |
jriwal | -11.224 |
kefeller | -10.888 |
impulse | -10.308 |
senal | -9.681 |
turmoil | -9.633 |
Token | Draper |
Token ID | 48575 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
lehem | +1.425 |
RON | +1.335 |
rans | +1.303 |
rons | +1.274 |
enance | +1.261 |
Neg logit contributions | |
jriwal | -1.346 |
kefeller | -1.237 |
impulse | -1.204 |
turmoil | -1.134 |
reaction | -1.109 |
Token | : |
Token ID | 25 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
lehem | +0.389 |
RON | +0.366 |
rans | +0.358 |
rons | +0.350 |
enance | +0.347 |
Neg logit contributions | |
jriwal | -0.336 |
kefeller | -0.308 |
impulse | -0.299 |
turmoil | -0.281 |
reaction | -0.275 |
Token | 303 |
Token ID | 30727 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
lehem | +0.478 |
RON | +0.450 |
rans | +0.440 |
rons | +0.429 |
enance | +0.424 |
Neg logit contributions | |
jriwal | -0.466 |
kefeller | -0.430 |
impulse | -0.417 |
turmoil | -0.392 |
reaction | -0.383 |
Token | - |
Token ID | 12 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
jriwal | +1.087 |
kefeller | +0.976 |
impulse | +0.945 |
turmoil | +0.878 |
reaction | +0.852 |
Neg logit contributions | |
lehem | -1.672 |
RON | -1.592 |
rans | -1.560 |
rons | -1.531 |
enance | -1.517 |
Token | е |
Token ID | 16843 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
lehem | +3.291 |
RON | +3.021 |
rans | +2.917 |
rons | +2.817 |
enance | +2.764 |
Neg logit contributions | |
jriwal | -6.326 |
kefeller | -5.946 |
impulse | -5.710 |
turmoil | -5.503 |
reaction | -5.397 |
Token | е |
Token ID | 16843 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
jriwal | +0.705 |
kefeller | +0.650 |
impulse | +0.641 |
turmoil | +0.610 |
reaction | +0.601 |
Neg logit contributions | |
lehem | -0.599 |
RON | -0.557 |
rans | -0.541 |
rons | -0.528 |
enance | -0.525 |
Token | � |
Token ID | 12466 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
jriwal | +0.652 |
kefeller | +0.601 |
impulse | +0.592 |
turmoil | +0.562 |
reaction | +0.553 |
Neg logit contributions | |
lehem | -0.582 |
RON | -0.542 |
rans | -0.527 |
rons | -0.514 |
enance | -0.511 |
Token | � |
Token ID | 109 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
lehem | +0.389 |
RON | +0.362 |
rans | +0.353 |
rons | +0.343 |
enance | +0.339 |
Neg logit contributions | |
jriwal | -0.468 |
kefeller | -0.436 |
impulse | -0.424 |
turmoil | -0.404 |
reaction | -0.396 |
Token | о� |
Token ID | 25443 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
lehem | +2.993 |
RON | +2.697 |
rans | +2.628 |
rons | +2.493 |
enance | +2.402 |
Neg logit contributions | |
jriwal | -7.063 |
kefeller | -6.662 |
impulse | -6.497 |
turmoil | -6.250 |
reaction | -6.159 |
Token | � |
Token ID | 119 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
jriwal | +4.571 |
kefeller | +4.237 |
impulse | +4.222 |
turmoil | +4.066 |
reaction | +3.997 |
Neg logit contributions | |
lehem | -2.820 |
RON | -2.581 |
rans | -2.481 |
rons | -2.427 |
enance | -2.394 |
Token | ь |
Token ID | 45367 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
lehem | +6.037 |
RON | +5.362 |
rans | +5.233 |
rons | +4.894 |
enance | +4.853 |
Neg logit contributions | |
jriwal | -14.259 |
kefeller | -13.499 |
impulse | -13.077 |
turmoil | -12.476 |
reaction | -12.277 |
Token | � |
Token ID | 141 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
lehem | +0.734 |
RON | +0.668 |
rans | +0.647 |
rons | +0.622 |
enance | +0.614 |
Neg logit contributions | |
jriwal | -1.249 |
kefeller | -1.173 |
impulse | -1.145 |
turmoil | -1.096 |
reaction | -1.079 |
Token | � |
Token ID | 230 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
lehem | +1.953 |
RON | +1.799 |
rans | +1.742 |
rons | +1.686 |
enance | +1.670 |
Neg logit contributions | |
jriwal | -3.082 |
kefeller | -2.887 |
impulse | -2.809 |
turmoil | -2.687 |
reaction | -2.652 |
Token | и |
Token ID | 18849 |
Feature activation | -6.70e+00 |
Pos logit contributions | |
lehem | +0.263 |
RON | +0.238 |
rans | +0.230 |
rons | +0.222 |
enance | +0.219 |
Neg logit contributions | |
jriwal | -0.494 |
kefeller | -0.464 |
impulse | -0.456 |
turmoil | -0.438 |
reaction | -0.432 |
Token | н |
Token ID | 22177 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
jriwal | +7.253 |
impulse | +6.742 |
kefeller | +6.683 |
turmoil | +6.502 |
reaction | +6.433 |
Neg logit contributions | |
lehem | -4.761 |
RON | -4.327 |
enance | -4.100 |
rans | -4.096 |
rons | -4.017 |
Token | - |
Token ID | 12 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
jriwal | +1.988 |
kefeller | +1.805 |
impulse | +1.766 |
turmoil | +1.655 |
reaction | +1.625 |
Neg logit contributions | |
lehem | -2.697 |
RON | -2.548 |
rans | -2.487 |
rons | -2.453 |
enance | -2.428 |
Token | born |
Token ID | 6286 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
lehem | +5.976 |
rans | +5.693 |
RON | +5.575 |
rons | +5.245 |
enance | +5.174 |
Neg logit contributions | |
jriwal | -6.286 |
kefeller | -5.702 |
impulse | -5.583 |
turmoil | -5.252 |
reaction | -5.074 |
Token | Turk |
Token ID | 8484 |
Feature activation | -7.91e-01 |
Pos logit contributions | |
lehem | +3.633 |
RON | +3.416 |
rans | +3.379 |
enance | +3.284 |
rons | +3.249 |
Neg logit contributions | |
jriwal | -2.995 |
kefeller | -2.732 |
impulse | -2.563 |
turmoil | -2.410 |
senal | -2.360 |
Token | named |
Token ID | 3706 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
jriwal | +0.681 |
kefeller | +0.623 |
impulse | +0.606 |
turmoil | +0.572 |
reaction | +0.559 |
Neg logit contributions | |
lehem | -0.779 |
RON | -0.731 |
rans | -0.717 |
rons | -0.699 |
enance | -0.693 |
Token | Ali |
Token ID | 12104 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
lehem | +1.427 |
RON | +1.334 |
rans | +1.301 |
rons | +1.269 |
enance | +1.263 |
Neg logit contributions | |
jriwal | -1.409 |
kefeller | -1.294 |
impulse | -1.259 |
turmoil | -1.191 |
reaction | -1.161 |
Token | Kent |
Token ID | 8758 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
jriwal | +0.206 |
kefeller | +0.189 |
impulse | +0.185 |
turmoil | +0.175 |
reaction | +0.171 |
Neg logit contributions | |
lehem | -0.215 |
RON | -0.201 |
rans | -0.196 |
rons | -0.192 |
enance | -0.190 |
Token | . |
Token ID | 13 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
lehem | +10.091 |
rans | +9.650 |
RON | +9.270 |
rons | +9.184 |
enance | +9.042 |
Neg logit contributions | |
jriwal | -9.725 |
kefeller | -9.080 |
impulse | -9.042 |
turmoil | -8.419 |
senal | -8.246 |
Token | The |
Token ID | 383 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
lehem | +0.456 |
RON | +0.426 |
rans | +0.415 |
rons | +0.406 |
enance | +0.402 |
Neg logit contributions | |
jriwal | -0.477 |
kefeller | -0.440 |
impulse | -0.431 |
turmoil | -0.410 |
reaction | -0.403 |
Token | two |
Token ID | 734 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
lehem | +0.181 |
RON | +0.171 |
rans | +0.168 |
rons | +0.164 |
enance | +0.163 |
Neg logit contributions | |
jriwal | -0.143 |
kefeller | -0.130 |
impulse | -0.126 |
turmoil | -0.118 |
reaction | -0.115 |
Token | had |
Token ID | 550 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
lehem | +0.718 |
RON | +0.675 |
rans | +0.661 |
rons | +0.646 |
enance | +0.640 |
Neg logit contributions | |
jriwal | -0.638 |
kefeller | -0.584 |
impulse | -0.568 |
turmoil | -0.536 |
reaction | -0.524 |
Token | taken |
Token ID | 2077 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
lehem | +2.197 |
RON | +2.089 |
rans | +2.057 |
rons | +2.019 |
enance | +2.000 |
Neg logit contributions | |
jriwal | -1.756 |
kefeller | -1.596 |
impulse | -1.522 |
turmoil | -1.432 |
reaction | -1.392 |
Token | , |
Token ID | 11 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
jriwal | +2.342 |
kefeller | +2.126 |
impulse | +2.080 |
turmoil | +1.960 |
reaction | +1.923 |
Neg logit contributions | |
lehem | -3.002 |
RON | -2.825 |
rans | -2.755 |
rons | -2.708 |
enance | -2.688 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
lehem | +0.227 |
RON | +0.214 |
rans | +0.211 |
rons | +0.205 |
enance | +0.203 |
Neg logit contributions | |
jriwal | -0.187 |
kefeller | -0.170 |
impulse | -0.164 |
turmoil | -0.154 |
reaction | -0.150 |
Token | her |
Token ID | 607 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
jriwal | +2.008 |
kefeller | +1.825 |
impulse | +1.793 |
turmoil | +1.691 |
reaction | +1.658 |
Neg logit contributions | |
lehem | -2.541 |
RON | -2.391 |
rans | -2.324 |
rons | -2.283 |
enance | -2.270 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
lehem | +0.893 |
RON | +0.852 |
rans | +0.836 |
rons | +0.819 |
enance | +0.813 |
Neg logit contributions | |
jriwal | -0.581 |
kefeller | -0.525 |
impulse | -0.496 |
turmoil | -0.462 |
reaction | -0.445 |
Token | is |
Token ID | 318 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
jriwal | +0.726 |
kefeller | +0.658 |
impulse | +0.641 |
turmoil | +0.602 |
reaction | +0.589 |
Neg logit contributions | |
lehem | -0.954 |
RON | -0.899 |
rans | -0.879 |
rons | -0.862 |
enance | -0.855 |
Token | Cant |
Token ID | 16821 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
jriwal | +1.569 |
kefeller | +1.435 |
impulse | +1.402 |
turmoil | +1.322 |
reaction | +1.296 |
Neg logit contributions | |
lehem | -1.797 |
RON | -1.688 |
rans | -1.646 |
rons | -1.612 |
enance | -1.599 |
Token | ones |
Token ID | 1952 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
rans | +5.402 |
lehem | +5.366 |
RON | +4.889 |
rons | +4.870 |
enance | +4.343 |
Neg logit contributions | |
jriwal | -14.261 |
kefeller | -13.464 |
impulse | -12.908 |
senal | -12.779 |
indictment | -12.506 |
Token | e |
Token ID | 68 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
jriwal | +1.039 |
kefeller | +0.981 |
impulse | +0.968 |
turmoil | +0.935 |
reaction | +0.924 |
Neg logit contributions | |
lehem | -0.390 |
RON | -0.344 |
rans | -0.325 |
rons | -0.312 |
enance | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
jriwal | +0.945 |
kefeller | +0.862 |
impulse | +0.839 |
turmoil | +0.788 |
reaction | +0.770 |
Neg logit contributions | |
lehem | -1.151 |
RON | -1.084 |
rans | -1.061 |
rons | -1.038 |
enance | -1.030 |
Token | And |
Token ID | 843 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
lehem | +0.423 |
RON | +0.397 |
rans | +0.387 |
rons | +0.378 |
enance | +0.375 |
Neg logit contributions | |
jriwal | -0.408 |
kefeller | -0.375 |
impulse | -0.366 |
turmoil | -0.346 |
reaction | -0.340 |
Token | she |
Token ID | 673 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
lehem | +0.630 |
RON | +0.593 |
rans | +0.583 |
rons | +0.570 |
enance | +0.563 |
Neg logit contributions | |
jriwal | -0.551 |
kefeller | -0.505 |
impulse | -0.486 |
turmoil | -0.457 |
reaction | -0.446 |
Token | AP |
Token ID | 3486 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
jriwal | +2.075 |
kefeller | +1.910 |
impulse | +1.871 |
turmoil | +1.772 |
reaction | +1.739 |
Neg logit contributions | |
lehem | -2.072 |
RON | -1.934 |
rans | -1.890 |
rons | -1.842 |
enance | -1.830 |
Token | G |
Token ID | 38 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
jriwal | +1.736 |
kefeller | +1.595 |
impulse | +1.551 |
turmoil | +1.470 |
reaction | +1.440 |
Neg logit contributions | |
lehem | -1.774 |
RON | -1.666 |
rans | -1.620 |
rons | -1.588 |
enance | -1.568 |
Token | - |
Token ID | 12 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
jriwal | +1.260 |
kefeller | +1.146 |
impulse | +1.119 |
turmoil | +1.049 |
reaction | +1.027 |
Neg logit contributions | |
lehem | -1.629 |
RON | -1.532 |
rans | -1.500 |
rons | -1.467 |
enance | -1.461 |
Token | 83 |
Token ID | 5999 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
lehem | +3.455 |
RON | +3.321 |
rans | +3.146 |
rons | +3.084 |
enance | +3.000 |
Neg logit contributions | |
jriwal | -4.882 |
kefeller | -4.594 |
impulse | -4.430 |
turmoil | -4.258 |
reaction | -4.158 |
Token | Active |
Token ID | 14199 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
lehem | +3.602 |
RON | +3.496 |
rans | +3.349 |
rons | +3.332 |
enance | +3.200 |
Neg logit contributions | |
jriwal | -3.322 |
kefeller | -3.043 |
impulse | -2.844 |
turmoil | -2.739 |
reaction | -2.637 |
Token | Elect |
Token ID | 5903 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
lehem | +1.299 |
RON | +1.246 |
rans | +1.200 |
rons | +1.188 |
enance | +1.163 |
Neg logit contributions | |
jriwal | -1.198 |
kefeller | -1.098 |
impulse | -1.045 |
turmoil | -1.000 |
reaction | -0.965 |
Token | ron |
Token ID | 1313 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
lehem | +7.585 |
rons | +7.556 |
RON | +7.514 |
rans | +7.048 |
enance | +6.601 |
Neg logit contributions | |
jriwal | -11.985 |
kefeller | -11.939 |
impulse | -11.197 |
turmoil | -10.855 |
indictment | -10.761 |
Token | ically |
Token ID | 1146 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
jriwal | +1.908 |
kefeller | +1.750 |
impulse | +1.715 |
turmoil | +1.618 |
reaction | +1.590 |
Neg logit contributions | |
lehem | -2.052 |
RON | -1.919 |
rans | -1.876 |
rons | -1.830 |
enance | -1.820 |
Token | Sc |
Token ID | 1446 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
jriwal | +1.248 |
kefeller | +1.148 |
impulse | +1.122 |
turmoil | +1.062 |
reaction | +1.042 |
Neg logit contributions | |
lehem | -1.277 |
RON | -1.194 |
rans | -1.165 |
rons | -1.139 |
enance | -1.130 |
Token | anned |
Token ID | 3577 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
jriwal | +0.524 |
kefeller | +0.486 |
impulse | +0.476 |
turmoil | +0.453 |
reaction | +0.446 |
Neg logit contributions | |
lehem | -0.423 |
RON | -0.392 |
rans | -0.380 |
rons | -0.370 |
enance | -0.367 |
Token | Array |
Token ID | 15690 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
lehem | +0.500 |
RON | +0.476 |
rans | +0.464 |
rons | +0.457 |
enance | +0.449 |
Neg logit contributions | |
jriwal | -0.477 |
kefeller | -0.438 |
impulse | -0.418 |
turmoil | -0.399 |
reaction | -0.386 |
Token | � |
Token ID | 12466 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
lehem | +0.518 |
RON | +0.481 |
rans | +0.468 |
rons | +0.456 |
enance | +0.450 |
Neg logit contributions | |
jriwal | -0.636 |
kefeller | -0.592 |
impulse | -0.576 |
turmoil | -0.548 |
reaction | -0.539 |
Token | � |
Token ID | 116 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
lehem | +0.306 |
RON | +0.285 |
rans | +0.278 |
rons | +0.271 |
enance | +0.268 |
Neg logit contributions | |
jriwal | -0.352 |
kefeller | -0.326 |
impulse | -0.318 |
turmoil | -0.302 |
reaction | -0.297 |
Token | � |
Token ID | 12466 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
jriwal | +2.458 |
kefeller | +2.278 |
impulse | +2.246 |
turmoil | +2.143 |
reaction | +2.109 |
Neg logit contributions | |
lehem | -1.964 |
RON | -1.811 |
rans | -1.759 |
rons | -1.714 |
enance | -1.700 |
Token | � |
Token ID | 109 |
Feature activation | +5.10e+00 |
Pos logit contributions | |
lehem | +0.280 |
RON | +0.260 |
rans | +0.253 |
rons | +0.246 |
enance | +0.243 |
Neg logit contributions | |
jriwal | -0.357 |
kefeller | -0.332 |
impulse | -0.324 |
turmoil | -0.309 |
reaction | -0.303 |
Token | о� |
Token ID | 25443 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
lehem | +2.977 |
RON | +2.708 |
rans | +2.632 |
rons | +2.527 |
enance | +2.451 |
Neg logit contributions | |
jriwal | -6.393 |
kefeller | -6.012 |
impulse | -5.847 |
turmoil | -5.609 |
reaction | -5.534 |
Token | � |
Token ID | 119 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
jriwal | +4.500 |
impulse | +4.160 |
kefeller | +4.147 |
turmoil | +3.994 |
reaction | +3.923 |
Neg logit contributions | |
lehem | -3.306 |
RON | -3.031 |
rans | -2.937 |
rons | -2.876 |
enance | -2.842 |
Token | е |
Token ID | 16843 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
lehem | +6.349 |
RON | +5.977 |
rans | +5.789 |
rons | +5.511 |
enance | +5.275 |
Neg logit contributions | |
jriwal | -13.437 |
kefeller | -12.695 |
impulse | -12.171 |
turmoil | -11.517 |
senal | -11.426 |
Token | е |
Token ID | 16843 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
jriwal | +1.111 |
kefeller | +1.036 |
impulse | +1.021 |
turmoil | +0.978 |
reaction | +0.964 |
Neg logit contributions | |
lehem | -0.729 |
RON | -0.668 |
rans | -0.647 |
rons | -0.628 |
enance | -0.624 |
Token | ), |
Token ID | 828 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
jriwal | +0.962 |
kefeller | +0.893 |
impulse | +0.879 |
turmoil | +0.840 |
reaction | +0.827 |
Neg logit contributions | |
lehem | -0.715 |
RON | -0.659 |
rans | -0.640 |
rons | -0.622 |
enance | -0.618 |
Token | � |
Token ID | 12466 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
lehem | +1.947 |
RON | +1.812 |
rans | +1.774 |
rons | +1.718 |
enance | +1.693 |
Neg logit contributions | |
jriwal | -2.289 |
kefeller | -2.130 |
impulse | -2.049 |
turmoil | -1.952 |
reaction | -1.907 |
Token | � |
Token ID | 121 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
lehem | +0.362 |
RON | +0.337 |
rans | +0.329 |
rons | +0.319 |
enance | +0.315 |
Neg logit contributions | |
jriwal | -0.435 |
kefeller | -0.405 |
impulse | -0.394 |
turmoil | -0.375 |
reaction | -0.368 |
Token | oub |
Token ID | 12944 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
jriwal | +1.361 |
kefeller | +1.241 |
impulse | +1.209 |
turmoil | +1.138 |
reaction | +1.114 |
Neg logit contributions | |
lehem | -1.621 |
RON | -1.525 |
rans | -1.488 |
rons | -1.459 |
enance | -1.446 |
Token |
|
Token ID | 198 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
lehem | +0.626 |
RON | +0.593 |
rans | +0.578 |
rons | +0.563 |
enance | +0.560 |
Neg logit contributions | |
jriwal | -0.685 |
kefeller | -0.632 |
impulse | -0.611 |
turmoil | -0.578 |
senal | -0.568 |
Token |
|
Token ID | 198 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
jriwal | +0.360 |
kefeller | +0.331 |
impulse | +0.323 |
turmoil | +0.306 |
reaction | +0.300 |
Neg logit contributions | |
lehem | -0.361 |
RON | -0.338 |
rans | -0.330 |
rons | -0.322 |
enance | -0.320 |
Token | 2005 |
Token ID | 14315 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
jriwal | +0.240 |
kefeller | +0.226 |
impulse | +0.221 |
turmoil | +0.212 |
reaction | +0.209 |
Neg logit contributions | |
lehem | -0.142 |
RON | -0.131 |
rans | -0.126 |
rons | -0.121 |
enance | -0.120 |
Token | Jason |
Token ID | 8982 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
lehem | +1.500 |
RON | +1.415 |
rans | +1.376 |
rons | +1.353 |
enance | +1.337 |
Neg logit contributions | |
jriwal | -1.307 |
kefeller | -1.191 |
impulse | -1.155 |
turmoil | -1.083 |
reaction | -1.057 |
Token | Bat |
Token ID | 6577 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
lehem | +0.473 |
RON | +0.444 |
rans | +0.436 |
rons | +0.425 |
enance | +0.419 |
Neg logit contributions | |
jriwal | -0.493 |
kefeller | -0.451 |
impulse | -0.438 |
turmoil | -0.414 |
reaction | -0.405 |
Token | eman |
Token ID | 8463 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
lehem | +9.883 |
rans | +9.468 |
rons | +9.412 |
RON | +9.184 |
enance | +9.155 |
Neg logit contributions | |
jriwal | -9.358 |
kefeller | -8.672 |
impulse | -8.478 |
senal | -7.737 |
turmoil | -7.732 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
lehem | +0.363 |
RON | +0.339 |
rans | +0.332 |
rons | +0.323 |
enance | +0.321 |
Neg logit contributions | |
jriwal | -0.367 |
kefeller | -0.338 |
impulse | -0.329 |
turmoil | -0.311 |
reaction | -0.305 |
Token |
|
Token ID | 198 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
jriwal | +0.296 |
kefeller | +0.272 |
impulse | +0.265 |
turmoil | +0.251 |
reaction | +0.246 |
Neg logit contributions | |
lehem | -0.291 |
RON | -0.274 |
rans | -0.267 |
rons | -0.260 |
enance | -0.258 |
Token | 2005 |
Token ID | 14315 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
jriwal | +0.218 |
kefeller | +0.204 |
impulse | +0.200 |
turmoil | +0.192 |
reaction | +0.189 |
Neg logit contributions | |
lehem | -0.133 |
RON | -0.121 |
rans | -0.117 |
rons | -0.113 |
enance | -0.112 |
Token | Zach |
Token ID | 18825 |
Feature activation | +7.94e+00 |
Pos logit contributions | |
lehem | +1.291 |
RON | +1.216 |
rans | +1.181 |
rons | +1.161 |
enance | +1.147 |
Neg logit contributions | |
jriwal | -1.151 |
kefeller | -1.049 |
impulse | -1.018 |
turmoil | -0.955 |
reaction | -0.931 |
Token | at |
Token ID | 379 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
lehem | +1.634 |
RON | +1.528 |
rans | +1.505 |
rons | +1.473 |
enance | +1.450 |
Neg logit contributions | |
jriwal | -1.439 |
kefeller | -1.318 |
impulse | -1.277 |
turmoil | -1.211 |
reaction | -1.174 |
Token | your |
Token ID | 534 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
lehem | +1.263 |
RON | +1.186 |
rans | +1.160 |
rons | +1.135 |
enance | +1.122 |
Neg logit contributions | |
jriwal | -1.129 |
kefeller | -1.030 |
impulse | -1.001 |
turmoil | -0.948 |
reaction | -0.924 |
Token | first |
Token ID | 717 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
jriwal | +0.318 |
kefeller | +0.287 |
impulse | +0.276 |
turmoil | +0.259 |
reaction | +0.252 |
Neg logit contributions | |
lehem | -0.466 |
RON | -0.442 |
rans | -0.432 |
rons | -0.425 |
enance | -0.421 |
Token | stop |
Token ID | 2245 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
jriwal | +3.179 |
impulse | +2.968 |
kefeller | +2.952 |
reaction | +2.751 |
turmoil | +2.748 |
Neg logit contributions | |
lehem | -3.306 |
RON | -3.084 |
rans | -3.005 |
rons | -2.938 |
enance | -2.921 |
Token | , |
Token ID | 11 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
lehem | +0.317 |
RON | +0.298 |
rans | +0.292 |
rons | +0.286 |
enance | +0.283 |
Neg logit contributions | |
jriwal | -0.257 |
kefeller | -0.234 |
impulse | -0.227 |
turmoil | -0.214 |
reaction | -0.209 |
Token | Kent |
Token ID | 8758 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
jriwal | +0.723 |
kefeller | +0.663 |
impulse | +0.646 |
turmoil | +0.609 |
reaction | +0.597 |
Neg logit contributions | |
lehem | -0.836 |
RON | -0.786 |
rans | -0.768 |
rons | -0.751 |
enance | -0.746 |
Token | uck |
Token ID | 1347 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
lehem | +9.911 |
rans | +9.233 |
RON | +9.109 |
rons | +8.999 |
enance | +8.655 |
Neg logit contributions | |
jriwal | -9.686 |
kefeller | -8.779 |
impulse | -8.473 |
turmoil | -8.065 |
reaction | -7.730 |
Token | Kn |
Token ID | 6102 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
lehem | +1.137 |
RON | +1.051 |
rans | +1.027 |
rons | +0.993 |
enance | +0.987 |
Neg logit contributions | |
jriwal | -1.534 |
kefeller | -1.432 |
impulse | -1.394 |
turmoil | -1.330 |
reaction | -1.305 |
Token | ob |
Token ID | 672 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
jriwal | +1.816 |
kefeller | +1.671 |
impulse | +1.628 |
turmoil | +1.540 |
reaction | +1.511 |
Neg logit contributions | |
lehem | -1.888 |
RON | -1.768 |
rans | -1.722 |
rons | -1.683 |
enance | -1.672 |
Token | in |
Token ID | 287 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
jriwal | +0.816 |
kefeller | +0.747 |
impulse | +0.728 |
turmoil | +0.687 |
reaction | +0.673 |
Neg logit contributions | |
lehem | -0.932 |
RON | -0.876 |
rans | -0.855 |
rons | -0.837 |
enance | -0.830 |
Token | rural |
Token ID | 10016 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
jriwal | +3.607 |
kefeller | +3.346 |
impulse | +3.285 |
turmoil | +3.118 |
reaction | +3.073 |
Neg logit contributions | |
lehem | -3.841 |
RON | -3.620 |
rans | -3.525 |
rons | -3.430 |
enance | -3.418 |
Token | copying |
Token ID | 23345 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
jriwal | +0.451 |
kefeller | +0.409 |
impulse | +0.389 |
turmoil | +0.363 |
reaction | +0.351 |
Neg logit contributions | |
lehem | -0.669 |
RON | -0.633 |
rans | -0.624 |
rons | -0.605 |
enance | -0.604 |
Token | , |
Token ID | 11 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
jriwal | +1.711 |
kefeller | +1.548 |
impulse | +1.533 |
turmoil | +1.440 |
reaction | +1.414 |
Neg logit contributions | |
lehem | -2.125 |
RON | -2.003 |
rans | -1.954 |
rons | -1.921 |
enance | -1.897 |
Token | or |
Token ID | 393 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
jriwal | +0.508 |
kefeller | +0.464 |
impulse | +0.446 |
turmoil | +0.420 |
reaction | +0.410 |
Neg logit contributions | |
lehem | -0.644 |
RON | -0.607 |
rans | -0.596 |
rons | -0.579 |
enance | -0.576 |
Token | redistribution |
Token ID | 41425 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
jriwal | +1.982 |
kefeller | +1.786 |
impulse | +1.743 |
turmoil | +1.628 |
reaction | +1.588 |
Neg logit contributions | |
lehem | -2.901 |
RON | -2.742 |
rans | -2.680 |
rons | -2.639 |
enance | -2.616 |
Token | ( |
Token ID | 357 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
jriwal | +1.747 |
kefeller | +1.578 |
impulse | +1.560 |
turmoil | +1.465 |
reaction | +1.440 |
Neg logit contributions | |
lehem | -2.159 |
RON | -2.030 |
rans | -1.976 |
rons | -1.945 |
enance | -1.921 |
Token | elect |
Token ID | 9509 |
Feature activation | +1.09e+01 |
Pos logit contributions | |
lehem | +1.445 |
RON | +1.342 |
rans | +1.303 |
rons | +1.253 |
enance | +1.242 |
Neg logit contributions | |
jriwal | -2.063 |
kefeller | -1.929 |
impulse | -1.882 |
turmoil | -1.799 |
reaction | -1.765 |
Token | ronic |
Token ID | 4565 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
lehem | +5.886 |
RON | +5.727 |
rans | +5.305 |
rons | +5.159 |
enance | +4.795 |
Neg logit contributions | |
jriwal | -13.320 |
kefeller | -13.042 |
impulse | -12.421 |
turmoil | -11.981 |
senal | -11.869 |
Token | or |
Token ID | 393 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
jriwal | +0.870 |
kefeller | +0.797 |
impulse | +0.778 |
turmoil | +0.734 |
reaction | +0.720 |
Neg logit contributions | |
lehem | -0.964 |
RON | -0.905 |
rans | -0.884 |
rons | -0.865 |
enance | -0.858 |
Token | otherwise |
Token ID | 4306 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
jriwal | +2.122 |
kefeller | +1.946 |
impulse | +1.905 |
turmoil | +1.796 |
reaction | +1.763 |
Neg logit contributions | |
lehem | -2.320 |
RON | -2.175 |
rans | -2.122 |
rons | -2.080 |
enance | -2.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
jriwal | +0.407 |
kefeller | +0.376 |
impulse | +0.367 |
turmoil | +0.348 |
reaction | +0.341 |
Neg logit contributions | |
lehem | -0.383 |
RON | -0.358 |
rans | -0.349 |
rons | -0.340 |
enance | -0.338 |
Token | including |
Token ID | 1390 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
jriwal | +0.229 |
kefeller | +0.208 |
impulse | +0.201 |
turmoil | +0.189 |
reaction | +0.184 |
Neg logit contributions | |
lehem | -0.297 |
RON | -0.280 |
rans | -0.275 |
rons | -0.268 |
enance | -0.267 |
Token | с |
Token ID | 21727 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
lehem | +0.606 |
RON | +0.561 |
rans | +0.542 |
rons | +0.524 |
enance | +0.519 |
Neg logit contributions | |
jriwal | -0.920 |
kefeller | -0.860 |
impulse | -0.840 |
turmoil | -0.804 |
reaction | -0.789 |
Token | о |
Token ID | 15166 |
Feature activation | -3.46e+00 |
Pos logit contributions | |
jriwal | +1.347 |
kefeller | +1.264 |
impulse | +1.244 |
turmoil | +1.197 |
reaction | +1.181 |
Neg logit contributions | |
lehem | -0.744 |
RON | -0.675 |
rans | -0.652 |
rons | -0.631 |
enance | -0.625 |
Token | � |
Token ID | 12466 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
jriwal | +3.942 |
kefeller | +3.662 |
impulse | +3.660 |
turmoil | +3.510 |
reaction | +3.478 |
Neg logit contributions | |
lehem | -2.358 |
RON | -2.150 |
rans | -2.052 |
enance | -2.011 |
rons | -2.004 |
Token | � |
Token ID | 118 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
jriwal | +0.313 |
kefeller | +0.291 |
impulse | +0.284 |
turmoil | +0.270 |
reaction | +0.265 |
Neg logit contributions | |
lehem | -0.265 |
RON | -0.246 |
rans | -0.240 |
rons | -0.234 |
enance | -0.231 |
Token | о� |
Token ID | 25443 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
jriwal | +1.651 |
kefeller | +1.557 |
impulse | +1.538 |
turmoil | +1.480 |
reaction | +1.465 |
Neg logit contributions | |
lehem | -0.718 |
RON | -0.636 |
rans | -0.609 |
rons | -0.584 |
enance | -0.576 |
Token | � |
Token ID | 119 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
jriwal | +4.753 |
impulse | +4.399 |
kefeller | +4.364 |
turmoil | +4.187 |
reaction | +4.123 |
Neg logit contributions | |
lehem | -3.777 |
RON | -3.485 |
rans | -3.358 |
rons | -3.290 |
enance | -3.259 |
Token | и |
Token ID | 18849 |
Feature activation | -7.44e+00 |
Pos logit contributions | |
lehem | +6.253 |
RON | +5.989 |
rans | +5.692 |
rons | +5.474 |
enance | +5.309 |
Neg logit contributions | |
jriwal | -12.942 |
kefeller | -12.150 |
impulse | -11.558 |
turmoil | -10.972 |
senal | -10.878 |
Token | � |
Token ID | 141 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
jriwal | +7.764 |
impulse | +7.336 |
kefeller | +7.225 |
turmoil | +7.013 |
reaction | +6.983 |
Neg logit contributions | |
lehem | -5.351 |
RON | -4.839 |
rans | -4.664 |
enance | -4.606 |
rons | -4.556 |
Token | � |
Token ID | 229 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
lehem | +1.366 |
RON | +1.245 |
rans | +1.202 |
rons | +1.161 |
enance | +1.145 |
Neg logit contributions | |
jriwal | -2.446 |
kefeller | -2.295 |
impulse | -2.238 |
turmoil | -2.150 |
reaction | -2.118 |
Token | е |
Token ID | 16843 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
lehem | +1.247 |
RON | +1.142 |
rans | +1.107 |
rons | +1.071 |
enance | +1.053 |
Neg logit contributions | |
jriwal | -2.236 |
kefeller | -2.093 |
impulse | -2.037 |
turmoil | -1.960 |
reaction | -1.927 |
Token | с |
Token ID | 21727 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
jriwal | +1.443 |
kefeller | +1.322 |
impulse | +1.312 |
turmoil | +1.245 |
reaction | +1.227 |
Neg logit contributions | |
lehem | -1.375 |
RON | -1.279 |
rans | -1.244 |
rons | -1.212 |
enance | -1.209 |
Token | pass |
Token ID | 1208 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
lehem | +3.206 |
RON | +3.025 |
rans | +2.969 |
rons | +2.907 |
enance | +2.879 |
Neg logit contributions | |
jriwal | -2.900 |
kefeller | -2.667 |
impulse | -2.581 |
turmoil | -2.443 |
reaction | -2.373 |
Token | statues |
Token ID | 25827 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
jriwal | +0.316 |
kefeller | +0.287 |
impulse | +0.279 |
turmoil | +0.262 |
reaction | +0.255 |
Neg logit contributions | |
lehem | -0.410 |
RON | -0.387 |
rans | -0.379 |
rons | -0.371 |
enance | -0.369 |
Token | of |
Token ID | 286 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
lehem | +0.077 |
RON | +0.072 |
rans | +0.070 |
rons | +0.069 |
enance | +0.068 |
Neg logit contributions | |
jriwal | -0.069 |
kefeller | -0.063 |
impulse | -0.061 |
turmoil | -0.058 |
reaction | -0.057 |
Token | champions |
Token ID | 7827 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
lehem | +1.456 |
RON | +1.376 |
rans | +1.344 |
rons | +1.316 |
enance | +1.309 |
Neg logit contributions | |
jriwal | -1.202 |
kefeller | -1.097 |
impulse | -1.061 |
turmoil | -0.996 |
reaction | -0.973 |
Token | – |
Token ID | 784 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
lehem | +3.982 |
RON | +3.749 |
rans | +3.688 |
rons | +3.619 |
enance | +3.604 |
Neg logit contributions | |
jriwal | -3.251 |
kefeller | -3.015 |
impulse | -2.872 |
turmoil | -2.665 |
reaction | -2.590 |
Token | Betty |
Token ID | 29504 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
lehem | +1.728 |
RON | +1.630 |
rans | +1.592 |
rons | +1.559 |
enance | +1.545 |
Neg logit contributions | |
jriwal | -1.428 |
kefeller | -1.303 |
impulse | -1.260 |
turmoil | -1.180 |
reaction | -1.152 |
Token | C |
Token ID | 327 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
lehem | +9.970 |
RON | +9.212 |
rans | +9.106 |
rons | +9.065 |
enance | +8.826 |
Neg logit contributions | |
jriwal | -9.356 |
kefeller | -8.396 |
impulse | -8.160 |
senal | -7.679 |
turmoil | -7.581 |
Token | uth |
Token ID | 1071 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
lehem | +0.941 |
RON | +0.876 |
rans | +0.857 |
rons | +0.839 |
enance | +0.834 |
Neg logit contributions | |
jriwal | -0.932 |
kefeller | -0.858 |
impulse | -0.837 |
turmoil | -0.792 |
reaction | -0.771 |
Token | bert |
Token ID | 4835 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
lehem | +3.516 |
RON | +3.329 |
rans | +3.302 |
rons | +3.226 |
enance | +3.193 |
Neg logit contributions | |
jriwal | -2.502 |
kefeller | -2.244 |
impulse | -2.181 |
turmoil | -2.044 |
reaction | -1.985 |
Token | , |
Token ID | 11 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
lehem | +4.692 |
RON | +4.389 |
rans | +4.323 |
rons | +4.238 |
enance | +4.215 |
Neg logit contributions | |
jriwal | -4.228 |
kefeller | -3.859 |
impulse | -3.763 |
turmoil | -3.500 |
reaction | -3.403 |
Token | Don |
Token ID | 2094 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
jriwal | +0.584 |
kefeller | +0.535 |
impulse | +0.522 |
turmoil | +0.493 |
reaction | +0.483 |
Neg logit contributions | |
lehem | -0.637 |
RON | -0.598 |
rans | -0.584 |
rons | -0.571 |
enance | -0.566 |
Token | ? |
Token ID | 30 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
lehem | +1.832 |
RON | +1.720 |
rans | +1.697 |
rons | +1.645 |
enance | +1.634 |
Neg logit contributions | |
jriwal | -2.080 |
kefeller | -1.938 |
impulse | -1.877 |
turmoil | -1.763 |
reaction | -1.727 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
lehem | +0.115 |
RON | +0.108 |
rans | +0.105 |
rons | +0.103 |
enance | +0.102 |
Neg logit contributions | |
jriwal | -0.117 |
kefeller | -0.108 |
impulse | -0.105 |
turmoil | -0.100 |
reaction | -0.098 |
Token |
|
Token ID | 198 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
lehem | +0.047 |
RON | +0.044 |
rans | +0.043 |
rons | +0.042 |
enance | +0.041 |
Neg logit contributions | |
jriwal | -0.048 |
kefeller | -0.044 |
impulse | -0.043 |
turmoil | -0.041 |
reaction | -0.040 |
Token | A |
Token ID | 32 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
lehem | +0.129 |
RON | +0.119 |
rans | +0.116 |
rons | +0.113 |
enance | +0.111 |
Neg logit contributions | |
jriwal | -0.180 |
kefeller | -0.168 |
impulse | -0.165 |
turmoil | -0.158 |
reaction | -0.155 |
Token | : |
Token ID | 25 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
lehem | +1.221 |
RON | +1.159 |
rans | +1.129 |
rons | +1.091 |
enance | +1.087 |
Neg logit contributions | |
jriwal | -1.303 |
kefeller | -1.206 |
impulse | -1.168 |
turmoil | -1.103 |
senal | -1.083 |
Token | Fort |
Token ID | 21926 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
lehem | +0.791 |
RON | +0.742 |
rans | +0.720 |
rons | +0.699 |
enance | +0.692 |
Neg logit contributions | |
jriwal | -0.929 |
kefeller | -0.862 |
impulse | -0.840 |
turmoil | -0.797 |
reaction | -0.783 |
Token | y |
Token ID | 88 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
lehem | +8.539 |
rans | +8.457 |
RON | +8.045 |
rons | +7.797 |
enance | +7.746 |
Neg logit contributions | |
jriwal | -10.094 |
kefeller | -9.229 |
impulse | -8.826 |
turmoil | -8.469 |
senal | -8.410 |
Token | years |
Token ID | 812 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
lehem | +3.205 |
RON | +3.053 |
rans | +3.000 |
rons | +2.923 |
enance | +2.844 |
Neg logit contributions | |
jriwal | -2.692 |
kefeller | -2.469 |
impulse | -2.347 |
turmoil | -2.192 |
reaction | -2.122 |
Token | ago |
Token ID | 2084 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
lehem | +1.889 |
RON | +1.754 |
rans | +1.716 |
rons | +1.673 |
enance | +1.655 |
Neg logit contributions | |
jriwal | -1.967 |
kefeller | -1.838 |
impulse | -1.761 |
turmoil | -1.666 |
reaction | -1.633 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
lehem | +2.587 |
RON | +2.458 |
rans | +2.400 |
rons | +2.335 |
enance | +2.319 |
Neg logit contributions | |
jriwal | -2.396 |
kefeller | -2.211 |
impulse | -2.101 |
turmoil | -1.968 |
reaction | -1.920 |
Token | 40 |
Token ID | 2319 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
lehem | +0.045 |
RON | +0.043 |
rans | +0.042 |
rons | +0.041 |
enance | +0.041 |
Neg logit contributions | |
jriwal | -0.036 |
kefeller | -0.033 |
impulse | -0.032 |
turmoil | -0.030 |
reaction | -0.029 |
Token | 1995 |
Token ID | 21908 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
jriwal | +0.047 |
kefeller | +0.044 |
impulse | +0.043 |
turmoil | +0.041 |
reaction | +0.040 |
Neg logit contributions | |
lehem | -0.032 |
RON | -0.030 |
rans | -0.029 |
rons | -0.028 |
enance | -0.028 |
Token | Boots |
Token ID | 28807 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
lehem | +3.016 |
RON | +2.865 |
rans | +2.774 |
rons | +2.713 |
enance | +2.670 |
Neg logit contributions | |
jriwal | -3.154 |
kefeller | -2.859 |
impulse | -2.790 |
turmoil | -2.612 |
reaction | -2.566 |
Token | Pharmaceutical |
Token ID | 37175 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
lehem | +1.723 |
RON | +1.635 |
rans | +1.612 |
rons | +1.581 |
enance | +1.545 |
Neg logit contributions | |
jriwal | -1.474 |
kefeller | -1.339 |
impulse | -1.299 |
turmoil | -1.196 |
reaction | -1.152 |
Token | s |
Token ID | 82 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
jriwal | +4.850 |
kefeller | +4.553 |
impulse | +4.490 |
turmoil | +4.320 |
reaction | +4.283 |
Neg logit contributions | |
lehem | -2.854 |
RON | -2.533 |
rans | -2.469 |
enance | -2.352 |
rons | -2.351 |
Token | pressures |
Token ID | 18895 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
jriwal | +2.446 |
kefeller | +2.239 |
impulse | +2.193 |
turmoil | +2.074 |
reaction | +2.030 |
Neg logit contributions | |
lehem | -2.976 |
RON | -2.780 |
rans | -2.719 |
rons | -2.651 |
enance | -2.638 |
Token | Betty |
Token ID | 29504 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
jriwal | +3.431 |
kefeller | +3.137 |
impulse | +3.084 |
turmoil | +2.900 |
reaction | +2.849 |
Neg logit contributions | |
lehem | -4.557 |
RON | -4.275 |
rans | -4.164 |
rons | -4.096 |
enance | -4.050 |
Token | Dong |
Token ID | 28831 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
lehem | +9.558 |
RON | +8.790 |
rans | +8.768 |
rons | +8.689 |
enance | +8.290 |
Neg logit contributions | |
jriwal | -9.721 |
kefeller | -8.640 |
impulse | -8.336 |
senal | -7.855 |
turmoil | -7.823 |
Token | to |
Token ID | 284 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
lehem | +0.803 |
RON | +0.761 |
rans | +0.750 |
rons | +0.734 |
enance | +0.723 |
Neg logit contributions | |
jriwal | -0.619 |
kefeller | -0.559 |
impulse | -0.544 |
turmoil | -0.510 |
reaction | -0.493 |
Token | withdraw |
Token ID | 8399 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
lehem | +0.732 |
RON | +0.694 |
rans | +0.680 |
rons | +0.666 |
enance | +0.659 |
Neg logit contributions | |
jriwal | -0.635 |
kefeller | -0.579 |
impulse | -0.558 |
turmoil | -0.526 |
reaction | -0.514 |
Token | a |
Token ID | 257 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
lehem | +2.727 |
RON | +2.614 |
rans | +2.562 |
enance | +2.530 |
rons | +2.510 |
Neg logit contributions | |
jriwal | -1.864 |
kefeller | -1.678 |
impulse | -1.582 |
turmoil | -1.469 |
inki | -1.418 |
Token | paper |
Token ID | 3348 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
lehem | +0.704 |
RON | +0.672 |
rans | +0.659 |
rons | +0.645 |
enance | +0.641 |
Neg logit contributions | |
jriwal | -0.446 |
kefeller | -0.398 |
impulse | -0.381 |
turmoil | -0.353 |
reaction | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
lehem | +3.528 |
RON | +3.434 |
rans | +3.355 |
enance | +3.251 |
rons | +3.237 |
Neg logit contributions | |
jriwal | -3.648 |
kefeller | -3.312 |
senal | -3.196 |
impulse | -3.180 |
tiss | -3.066 |
Token | A |
Token ID | 317 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
lehem | +0.776 |
RON | +0.725 |
rans | +0.704 |
rons | +0.686 |
enance | +0.678 |
Neg logit contributions | |
jriwal | -0.904 |
kefeller | -0.835 |
impulse | -0.812 |
turmoil | -0.771 |
reaction | -0.756 |
Token | US |
Token ID | 2937 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
lehem | +1.290 |
RON | +1.230 |
rans | +1.189 |
rons | +1.157 |
enance | +1.146 |
Neg logit contributions | |
jriwal | -1.270 |
kefeller | -1.166 |
impulse | -1.135 |
turmoil | -1.071 |
reaction | -1.048 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
lehem | +0.530 |
RON | +0.493 |
rans | +0.480 |
rons | +0.467 |
enance | +0.463 |
Neg logit contributions | |
jriwal | -0.626 |
kefeller | -0.581 |
impulse | -0.567 |
turmoil | -0.538 |
reaction | -0.529 |
Token | Jonathan |
Token ID | 11232 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
lehem | +1.119 |
RON | +1.058 |
rans | +1.025 |
rons | +1.004 |
enance | +0.994 |
Neg logit contributions | |
jriwal | -1.066 |
kefeller | -0.973 |
impulse | -0.942 |
turmoil | -0.886 |
reaction | -0.862 |
Token | Cant |
Token ID | 16821 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
jriwal | +2.278 |
kefeller | +2.083 |
impulse | +2.035 |
turmoil | +1.921 |
reaction | +1.881 |
Neg logit contributions | |
lehem | -2.416 |
RON | -2.265 |
rans | -2.216 |
rons | -2.166 |
enance | -2.145 |
Token | well |
Token ID | 4053 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
lehem | +8.384 |
rans | +7.863 |
rons | +7.689 |
enance | +7.582 |
uate | +7.524 |
Neg logit contributions | |
jriwal | -10.758 |
kefeller | -9.812 |
impulse | -9.540 |
senal | -9.297 |
turmoil | -8.994 |
Token | ( |
Token ID | 357 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
lehem | +2.186 |
RON | +2.037 |
rans | +1.983 |
rons | +1.938 |
enance | +1.918 |
Neg logit contributions | |
jriwal | -2.499 |
kefeller | -2.309 |
impulse | -2.261 |
turmoil | -2.146 |
reaction | -2.097 |
Token | Team |
Token ID | 15592 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
lehem | +1.228 |
RON | +1.161 |
rans | +1.117 |
rons | +1.084 |
enance | +1.068 |
Neg logit contributions | |
jriwal | -1.618 |
kefeller | -1.498 |
impulse | -1.463 |
turmoil | -1.392 |
reaction | -1.362 |
Token | Sax |
Token ID | 29242 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
lehem | +2.819 |
RON | +2.669 |
rans | +2.602 |
rons | +2.539 |
enance | +2.503 |
Neg logit contributions | |
jriwal | -2.767 |
kefeller | -2.536 |
impulse | -2.448 |
turmoil | -2.307 |
reaction | -2.240 |
Token | o |
Token ID | 78 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
lehem | +2.527 |
RON | +2.385 |
rans | +2.378 |
enance | +2.215 |
rons | +2.203 |
Neg logit contributions | |
jriwal | -5.064 |
kefeller | -4.704 |
impulse | -4.487 |
turmoil | -4.314 |
reaction | -4.237 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
lehem | +0.243 |
RON | +0.229 |
rans | +0.224 |
rons | +0.220 |
enance | +0.218 |
Neg logit contributions | |
jriwal | -0.183 |
kefeller | -0.166 |
impulse | -0.161 |
turmoil | -0.151 |
reaction | -0.147 |
Token | s |
Token ID | 82 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
lehem | +2.084 |
RON | +1.945 |
rans | +1.890 |
rons | +1.858 |
enance | +1.830 |
Neg logit contributions | |
jriwal | -2.562 |
kefeller | -2.385 |
impulse | -2.294 |
turmoil | -2.194 |
reaction | -2.142 |
Token | would |
Token ID | 561 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
jriwal | +0.777 |
kefeller | +0.712 |
impulse | +0.704 |
turmoil | +0.664 |
reaction | +0.654 |
Neg logit contributions | |
lehem | -0.842 |
RON | -0.788 |
rans | -0.766 |
rons | -0.748 |
enance | -0.738 |
Token | gen |
Token ID | 2429 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
jriwal | +0.238 |
kefeller | +0.216 |
impulse | +0.214 |
turmoil | +0.201 |
reaction | +0.197 |
Neg logit contributions | |
lehem | -0.283 |
RON | -0.265 |
rans | -0.258 |
rons | -0.253 |
enance | -0.251 |
Token | uf |
Token ID | 3046 |
Feature activation | +5.16e+00 |
Pos logit contributions | |
lehem | +2.938 |
rans | +2.755 |
RON | +2.742 |
rons | +2.635 |
enance | +2.605 |
Neg logit contributions | |
jriwal | -3.491 |
kefeller | -3.246 |
impulse | -3.126 |
turmoil | -3.007 |
reaction | -2.908 |
Token | lect |
Token ID | 801 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
lehem | +3.800 |
RON | +3.662 |
rans | +3.617 |
rons | +3.507 |
enance | +3.449 |
Neg logit contributions | |
jriwal | -5.505 |
kefeller | -5.110 |
impulse | -4.991 |
turmoil | -4.797 |
senal | -4.775 |
Token | before |
Token ID | 878 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
lehem | +9.858 |
enance | +9.487 |
RON | +9.399 |
rons | +9.274 |
rans | +9.216 |
Neg logit contributions | |
jriwal | -8.657 |
kefeller | -7.960 |
senal | -7.314 |
impulse | -7.009 |
inki | -6.906 |
Token | the |
Token ID | 262 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
jriwal | +0.126 |
kefeller | +0.115 |
impulse | +0.112 |
turmoil | +0.104 |
reaction | +0.102 |
Neg logit contributions | |
lehem | -0.172 |
RON | -0.162 |
rans | -0.159 |
rons | -0.155 |
enance | -0.154 |
Token | nut |
Token ID | 6701 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
lehem | +0.235 |
RON | +0.222 |
rans | +0.218 |
rons | +0.214 |
enance | +0.212 |
Neg logit contributions | |
jriwal | -0.161 |
kefeller | -0.145 |
impulse | -0.140 |
turmoil | -0.131 |
reaction | -0.128 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
lehem | +2.513 |
RON | +2.378 |
rans | +2.328 |
rons | +2.301 |
enance | +2.253 |
Neg logit contributions | |
jriwal | -2.152 |
kefeller | -1.964 |
impulse | -1.884 |
turmoil | -1.779 |
reaction | -1.727 |
Token | she |
Token ID | 673 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
jriwal | +0.149 |
kefeller | +0.136 |
impulse | +0.132 |
turmoil | +0.124 |
reaction | +0.121 |
Neg logit contributions | |
lehem | -0.174 |
RON | -0.163 |
rans | -0.160 |
rons | -0.156 |
enance | -0.155 |
Token | child |
Token ID | 1200 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
lehem | +0.199 |
RON | +0.189 |
rans | +0.186 |
rons | +0.182 |
enance | +0.181 |
Neg logit contributions | |
jriwal | -0.123 |
kefeller | -0.111 |
impulse | -0.106 |
turmoil | -0.098 |
reaction | -0.095 |
Token | is |
Token ID | 318 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
lehem | +5.225 |
rans | +4.951 |
RON | +4.932 |
rons | +4.754 |
enance | +4.685 |
Neg logit contributions | |
jriwal | -5.821 |
kefeller | -5.429 |
impulse | -5.012 |
senal | -4.866 |
turmoil | -4.753 |
Token | transgender |
Token ID | 10637 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
jriwal | +1.427 |
kefeller | +1.293 |
impulse | +1.257 |
turmoil | +1.177 |
reaction | +1.150 |
Neg logit contributions | |
lehem | -1.945 |
RON | -1.836 |
rans | -1.797 |
rons | -1.762 |
enance | -1.748 |
Token | , |
Token ID | 11 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
jriwal | +1.424 |
kefeller | +1.295 |
impulse | +1.274 |
turmoil | +1.203 |
reaction | +1.178 |
Neg logit contributions | |
lehem | -1.716 |
RON | -1.617 |
rans | -1.572 |
rons | -1.540 |
enance | -1.533 |
Token | society |
Token ID | 3592 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
jriwal | +0.247 |
kefeller | +0.226 |
impulse | +0.219 |
turmoil | +0.207 |
reaction | +0.202 |
Neg logit contributions | |
lehem | -0.291 |
RON | -0.274 |
rans | -0.268 |
rons | -0.262 |
enance | -0.260 |
Token | inst |
Token ID | 916 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
lehem | +1.418 |
RON | +1.337 |
rans | +1.314 |
rons | +1.285 |
enance | +1.275 |
Neg logit contributions | |
jriwal | -1.242 |
kefeller | -1.139 |
impulse | -1.093 |
turmoil | -1.031 |
reaction | -1.004 |
Token | ills |
Token ID | 2171 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
lehem | +8.913 |
rans | +8.776 |
rons | +8.420 |
RON | +8.382 |
enance | +8.358 |
Neg logit contributions | |
jriwal | -9.506 |
kefeller | -8.927 |
impulse | -8.657 |
turmoil | -8.015 |
senal | -7.989 |
Token | in |
Token ID | 287 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
jriwal | +0.136 |
kefeller | +0.123 |
impulse | +0.120 |
turmoil | +0.112 |
reaction | +0.110 |
Neg logit contributions | |
lehem | -0.191 |
RON | -0.180 |
rans | -0.177 |
rons | -0.173 |
enance | -0.172 |
Token | them |
Token ID | 606 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
jriwal | +2.548 |
kefeller | +2.343 |
impulse | +2.324 |
turmoil | +2.194 |
reaction | +2.167 |
Neg logit contributions | |
lehem | -2.728 |
RON | -2.544 |
rans | -2.454 |
rons | -2.411 |
enance | -2.388 |
Token | rules |
Token ID | 3173 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
lehem | +2.834 |
RON | +2.687 |
rans | +2.656 |
rons | +2.591 |
enance | +2.576 |
Neg logit contributions | |
jriwal | -2.231 |
kefeller | -2.035 |
impulse | -1.900 |
turmoil | -1.781 |
senal | -1.758 |
Token | about |
Token ID | 546 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
jriwal | +1.532 |
kefeller | +1.385 |
impulse | +1.349 |
turmoil | +1.263 |
reaction | +1.234 |
Neg logit contributions | |
lehem | -2.131 |
RON | -2.012 |
rans | -1.968 |
rons | -1.930 |
enance | -1.915 |
Token | Baldwin |
Token ID | 26402 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
lehem | +2.542 |
RON | +2.273 |
rans | +2.133 |
enance | +2.020 |
rons | +1.983 |
Neg logit contributions | |
jriwal | -9.152 |
kefeller | -8.551 |
impulse | -8.476 |
senal | -8.333 |
tiss | -8.202 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
lehem | +4.887 |
RON | +4.816 |
rans | +4.688 |
rons | +4.542 |
enance | +4.523 |
Neg logit contributions | |
jriwal | -7.001 |
kefeller | -6.527 |
senal | -6.316 |
impulse | -6.157 |
tiss | -6.141 |
Token |
|
Token ID | 198 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
jriwal | +0.124 |
kefeller | +0.114 |
impulse | +0.111 |
turmoil | +0.105 |
reaction | +0.103 |
Neg logit contributions | |
lehem | -0.121 |
RON | -0.114 |
rans | -0.111 |
rons | -0.109 |
enance | -0.108 |
Token | 2013 |
Token ID | 6390 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
jriwal | +0.028 |
kefeller | +0.026 |
impulse | +0.026 |
turmoil | +0.024 |
reaction | +0.024 |
Neg logit contributions | |
lehem | -0.026 |
RON | -0.025 |
rans | -0.024 |
rons | -0.024 |
enance | -0.023 |
Token | Jason |
Token ID | 8982 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
jriwal | +0.597 |
kefeller | +0.545 |
impulse | +0.531 |
turmoil | +0.501 |
reaction | +0.490 |
Neg logit contributions | |
lehem | -0.677 |
RON | -0.636 |
rans | -0.621 |
rons | -0.608 |
enance | -0.603 |
Token | Bat |
Token ID | 6577 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
lehem | +0.311 |
RON | +0.293 |
rans | +0.287 |
rons | +0.281 |
enance | +0.279 |
Neg logit contributions | |
jriwal | -0.247 |
kefeller | -0.225 |
impulse | -0.219 |
turmoil | -0.205 |
reaction | -0.200 |
Token | eman |
Token ID | 8463 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
lehem | +8.949 |
rans | +8.764 |
rons | +8.685 |
RON | +8.636 |
enance | +8.564 |
Neg logit contributions | |
jriwal | -9.086 |
senal | -8.878 |
impulse | -8.486 |
kefeller | -8.437 |
tiss | -8.340 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
lehem | +0.393 |
RON | +0.368 |
rans | +0.360 |
rons | +0.351 |
enance | +0.349 |
Neg logit contributions | |
jriwal | -0.377 |
kefeller | -0.347 |
impulse | -0.338 |
turmoil | -0.319 |
reaction | -0.312 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
jriwal | +0.217 |
kefeller | +0.200 |
impulse | +0.195 |
turmoil | +0.184 |
reaction | +0.180 |
Neg logit contributions | |
lehem | -0.213 |
RON | -0.200 |
rans | -0.195 |
rons | -0.191 |
enance | -0.189 |
Token | 2013 |
Token ID | 6390 |
Feature activation | -7.67e-01 |
Pos logit contributions | |
jriwal | +0.118 |
kefeller | +0.109 |
impulse | +0.106 |
turmoil | +0.100 |
reaction | +0.098 |
Neg logit contributions | |
lehem | -0.109 |
RON | -0.103 |
rans | -0.100 |
rons | -0.097 |
enance | -0.097 |
Token | Louis |
Token ID | 5593 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
jriwal | +0.648 |
kefeller | +0.591 |
impulse | +0.576 |
turmoil | +0.542 |
reaction | +0.530 |
Neg logit contributions | |
lehem | -0.768 |
RON | -0.723 |
rans | -0.706 |
rons | -0.691 |
enance | -0.686 |
Token | what |
Token ID | 644 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
jriwal | +0.699 |
kefeller | +0.636 |
impulse | +0.618 |
turmoil | +0.581 |
reaction | +0.567 |
Neg logit contributions | |
lehem | -0.889 |
RON | -0.838 |
rans | -0.820 |
rons | -0.803 |
enance | -0.798 |
Token | he |
Token ID | 339 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
jriwal | +1.555 |
kefeller | +1.426 |
impulse | +1.393 |
turmoil | +1.314 |
reaction | +1.288 |
Neg logit contributions | |
lehem | -1.750 |
RON | -1.642 |
rans | -1.601 |
rons | -1.569 |
enance | -1.555 |
Token | calls |
Token ID | 3848 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lehem | +2.379 |
RON | +2.243 |
rans | +2.223 |
rons | +2.158 |
enance | +2.138 |
Neg logit contributions | |
jriwal | -2.214 |
kefeller | -2.038 |
impulse | -1.951 |
turmoil | -1.847 |
reaction | -1.800 |
Token | � |
Token ID | 564 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
jriwal | +1.364 |
kefeller | +1.242 |
impulse | +1.210 |
turmoil | +1.136 |
reaction | +1.112 |
Neg logit contributions | |
lehem | -1.735 |
RON | -1.634 |
rans | -1.599 |
rons | -1.568 |
enance | -1.553 |
Token | � |
Token ID | 250 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
lehem | +2.511 |
RON | +2.316 |
rans | +2.238 |
enance | +2.114 |
rons | +2.094 |
Neg logit contributions | |
jriwal | -5.075 |
kefeller | -4.786 |
impulse | -4.654 |
turmoil | -4.483 |
reaction | -4.415 |
Token | elect |
Token ID | 9509 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
lehem | +1.720 |
RON | +1.617 |
rans | +1.577 |
rons | +1.524 |
enance | +1.515 |
Neg logit contributions | |
jriwal | -1.945 |
kefeller | -1.800 |
impulse | -1.757 |
turmoil | -1.669 |
reaction | -1.637 |
Token | oral |
Token ID | 6864 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
lehem | +8.754 |
RON | +8.557 |
rans | +8.177 |
rons | +8.081 |
enance | +7.791 |
Neg logit contributions | |
jriwal | -9.733 |
kefeller | -9.346 |
impulse | -8.818 |
senal | -8.321 |
turmoil | -8.313 |
Token | itis |
Token ID | 11815 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
jriwal | +1.160 |
kefeller | +1.036 |
impulse | +1.006 |
turmoil | +0.933 |
reaction | +0.908 |
Neg logit contributions | |
lehem | -1.963 |
RON | -1.858 |
rans | -1.824 |
rons | -1.792 |
enance | -1.779 |
Token | . |
Token ID | 13 |
Feature activation | -9.78e-02 |
Pos logit contributions | |
jriwal | +0.824 |
kefeller | +0.756 |
impulse | +0.737 |
turmoil | +0.696 |
reaction | +0.681 |
Neg logit contributions | |
lehem | -0.887 |
RON | -0.831 |
rans | -0.812 |
rons | -0.794 |
enance | -0.788 |
Token | � |
Token ID | 447 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
jriwal | +0.091 |
kefeller | +0.084 |
impulse | +0.082 |
turmoil | +0.078 |
reaction | +0.076 |
Neg logit contributions | |
lehem | -0.089 |
RON | -0.083 |
rans | -0.081 |
rons | -0.079 |
enance | -0.079 |
Token | � |
Token ID | 251 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
jriwal | +1.815 |
kefeller | +1.685 |
impulse | +1.658 |
turmoil | +1.587 |
reaction | +1.560 |
Neg logit contributions | |
lehem | -1.377 |
RON | -1.270 |
rans | -1.231 |
rons | -1.208 |
enance | -1.185 |
Token | matter |
Token ID | 2300 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
lehem | +1.483 |
RON | +1.427 |
rans | +1.407 |
rons | +1.381 |
enance | +1.378 |
Neg logit contributions | |
jriwal | -0.571 |
kefeller | -0.491 |
impulse | -0.442 |
turmoil | -0.389 |
senal | -0.379 |
Token | . |
Token ID | 13 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
lehem | +1.351 |
RON | +1.273 |
rans | +1.249 |
rons | +1.220 |
enance | +1.218 |
Neg logit contributions | |
jriwal | -1.165 |
kefeller | -1.070 |
impulse | -1.034 |
turmoil | -0.968 |
reaction | -0.946 |
Token | � |
Token ID | 447 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
lehem | +0.185 |
RON | +0.174 |
rans | +0.169 |
rons | +0.166 |
enance | +0.164 |
Neg logit contributions | |
jriwal | -0.182 |
kefeller | -0.167 |
impulse | -0.163 |
turmoil | -0.155 |
reaction | -0.152 |
Token | � |
Token ID | 251 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
jriwal | +1.723 |
kefeller | +1.610 |
impulse | +1.584 |
turmoil | +1.521 |
reaction | +1.497 |
Neg logit contributions | |
lehem | -1.126 |
RON | -1.031 |
rans | -0.999 |
rons | -0.975 |
enance | -0.954 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
lehem | +3.676 |
RON | +3.462 |
rans | +3.349 |
rons | +3.271 |
enance | +3.254 |
Neg logit contributions | |
jriwal | -4.090 |
kefeller | -3.764 |
impulse | -3.680 |
turmoil | -3.458 |
reaction | -3.383 |
Token | R |
Token ID | 49 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
jriwal | +1.881 |
kefeller | +1.740 |
impulse | +1.701 |
turmoil | +1.618 |
reaction | +1.591 |
Neg logit contributions | |
lehem | -1.659 |
RON | -1.538 |
rans | -1.502 |
rons | -1.467 |
enance | -1.454 |
Token | amon |
Token ID | 16487 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
jriwal | +11.859 |
kefeller | +10.964 |
impulse | +10.706 |
reaction | +10.204 |
turmoil | +10.146 |
Neg logit contributions | |
lehem | -9.335 |
RON | -8.606 |
rans | -8.169 |
rons | -7.974 |
enance | -7.767 |
Token | Hare |
Token ID | 42285 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
lehem | +1.543 |
RON | +1.446 |
rans | +1.414 |
rons | +1.383 |
enance | +1.365 |
Neg logit contributions | |
jriwal | -1.507 |
kefeller | -1.372 |
impulse | -1.344 |
turmoil | -1.270 |
reaction | -1.244 |
Token | wood |
Token ID | 3822 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
jriwal | +2.360 |
kefeller | +2.160 |
impulse | +2.110 |
turmoil | +1.996 |
reaction | +1.963 |
Neg logit contributions | |
lehem | -2.535 |
RON | -2.379 |
rans | -2.313 |
rons | -2.265 |
enance | -2.255 |
Token | met |
Token ID | 1138 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
lehem | +0.692 |
RON | +0.651 |
rans | +0.637 |
rons | +0.623 |
enance | +0.616 |
Neg logit contributions | |
jriwal | -0.615 |
kefeller | -0.564 |
impulse | -0.547 |
turmoil | -0.515 |
reaction | -0.503 |
Token | with |
Token ID | 351 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
lehem | +4.521 |
RON | +4.289 |
rans | +4.173 |
rons | +4.109 |
enance | +4.053 |
Neg logit contributions | |
jriwal | -3.695 |
kefeller | -3.363 |
impulse | -3.204 |
turmoil | -2.994 |
reaction | -2.900 |
Token | down |
Token ID | 866 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
jriwal | +2.288 |
kefeller | +2.040 |
impulse | +2.023 |
turmoil | +1.882 |
reaction | +1.851 |
Neg logit contributions | |
lehem | -3.530 |
RON | -3.323 |
rans | -3.242 |
rons | -3.188 |
enance | -3.164 |
Token | with |
Token ID | 351 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
lehem | +0.559 |
RON | +0.529 |
rans | +0.519 |
rons | +0.511 |
enance | +0.506 |
Neg logit contributions | |
jriwal | -0.358 |
kefeller | -0.324 |
impulse | -0.310 |
turmoil | -0.289 |
reaction | -0.279 |
Token | Gohan |
Token ID | 45281 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
lehem | +0.269 |
RON | +0.254 |
rans | +0.249 |
rons | +0.243 |
enance | +0.241 |
Neg logit contributions | |
jriwal | -0.233 |
kefeller | -0.214 |
impulse | -0.206 |
turmoil | -0.194 |
reaction | -0.190 |
Token | ? |
Token ID | 30 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
jriwal | +2.318 |
kefeller | +2.116 |
impulse | +2.084 |
turmoil | +1.976 |
reaction | +1.946 |
Neg logit contributions | |
lehem | -2.658 |
RON | -2.482 |
rans | -2.416 |
rons | -2.365 |
enance | -2.347 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
jriwal | +0.136 |
kefeller | +0.126 |
impulse | +0.123 |
turmoil | +0.117 |
reaction | +0.114 |
Neg logit contributions | |
lehem | -0.126 |
RON | -0.118 |
rans | -0.115 |
rons | -0.112 |
enance | -0.111 |
Token | R |
Token ID | 49 |
Feature activation | -1.21e+01 |
Pos logit contributions | |
jriwal | +2.096 |
kefeller | +1.938 |
impulse | +1.896 |
turmoil | +1.803 |
reaction | +1.773 |
Neg logit contributions | |
lehem | -1.854 |
RON | -1.714 |
rans | -1.676 |
rons | -1.639 |
enance | -1.624 |
Token | ents |
Token ID | 658 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
jriwal | +11.891 |
kefeller | +10.979 |
impulse | +10.723 |
reaction | +10.227 |
turmoil | +10.163 |
Neg logit contributions | |
lehem | -9.272 |
RON | -8.526 |
rans | -8.102 |
rons | -7.907 |
enance | -7.691 |
Token | still |
Token ID | 991 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
lehem | +1.067 |
RON | +1.007 |
rans | +0.991 |
rons | +0.969 |
enance | +0.959 |
Neg logit contributions | |
jriwal | -0.890 |
kefeller | -0.815 |
impulse | -0.788 |
turmoil | -0.738 |
reaction | -0.722 |
Token | have |
Token ID | 423 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
jriwal | +0.500 |
kefeller | +0.454 |
impulse | +0.437 |
turmoil | +0.408 |
reaction | +0.398 |
Neg logit contributions | |
lehem | -0.698 |
RON | -0.660 |
rans | -0.648 |
rons | -0.635 |
enance | -0.630 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
jriwal | +0.052 |
kefeller | +0.048 |
impulse | +0.046 |
turmoil | +0.042 |
reaction | +0.041 |
Neg logit contributions | |
lehem | -0.070 |
RON | -0.067 |
rans | -0.066 |
rons | -0.065 |
enance | -0.064 |
Token | potential |
Token ID | 2785 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
jriwal | +1.065 |
kefeller | +0.950 |
impulse | +0.926 |
turmoil | +0.859 |
reaction | +0.836 |
Neg logit contributions | |
lehem | -1.785 |
RON | -1.692 |
rans | -1.658 |
rons | -1.628 |
enance | -1.618 |
Token | dirty |
Token ID | 11841 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
lehem | +0.489 |
RON | +0.464 |
rans | +0.455 |
rons | +0.448 |
enance | +0.445 |
Neg logit contributions | |
jriwal | -0.333 |
kefeller | -0.302 |
impulse | -0.286 |
turmoil | -0.268 |
reaction | -0.259 |
Token | . |
Token ID | 13 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
jriwal | +2.287 |
kefeller | +2.071 |
impulse | +2.037 |
turmoil | +1.904 |
reaction | +1.879 |
Neg logit contributions | |
lehem | -2.949 |
RON | -2.782 |
rans | -2.716 |
rons | -2.660 |
enance | -2.646 |
Token | � |
Token ID | 447 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lehem | +0.525 |
RON | +0.490 |
rans | +0.477 |
rons | +0.465 |
enance | +0.461 |
Neg logit contributions | |
jriwal | -0.564 |
kefeller | -0.521 |
impulse | -0.508 |
turmoil | -0.481 |
reaction | -0.472 |
Token | � |
Token ID | 251 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
jriwal | +1.937 |
kefeller | +1.813 |
impulse | +1.784 |
turmoil | +1.712 |
reaction | +1.686 |
Neg logit contributions | |
lehem | -1.166 |
RON | -1.063 |
rans | -1.027 |
rons | -0.997 |
enance | -0.982 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
lehem | +3.732 |
RON | +3.505 |
rans | +3.412 |
rons | +3.311 |
enance | +3.288 |
Neg logit contributions | |
jriwal | -4.176 |
kefeller | -3.883 |
impulse | -3.711 |
turmoil | -3.525 |
reaction | -3.427 |
Token | R |
Token ID | 49 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
jriwal | +2.115 |
kefeller | +1.955 |
impulse | +1.913 |
turmoil | +1.819 |
reaction | +1.789 |
Neg logit contributions | |
lehem | -1.869 |
RON | -1.729 |
rans | -1.690 |
rons | -1.653 |
enance | -1.638 |
Token | USE |
Token ID | 19108 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
jriwal | +11.621 |
kefeller | +10.747 |
impulse | +10.497 |
reaction | +9.996 |
turmoil | +9.942 |
Neg logit contributions | |
lehem | -9.199 |
RON | -8.487 |
rans | -8.066 |
rons | -7.870 |
enance | -7.669 |
Token | LL |
Token ID | 3069 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
lehem | +0.136 |
RON | +0.128 |
rans | +0.125 |
rons | +0.121 |
enance | +0.120 |
Neg logit contributions | |
jriwal | -0.126 |
kefeller | -0.116 |
impulse | -0.112 |
turmoil | -0.106 |
reaction | -0.103 |
Token | : |
Token ID | 25 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
lehem | +0.032 |
RON | +0.029 |
rans | +0.028 |
rons | +0.028 |
enance | +0.027 |
Neg logit contributions | |
jriwal | -0.046 |
kefeller | -0.042 |
impulse | -0.042 |
turmoil | -0.040 |
reaction | -0.039 |
Token | What |
Token ID | 1867 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
jriwal | +0.575 |
kefeller | +0.530 |
impulse | +0.518 |
turmoil | +0.491 |
reaction | +0.482 |
Neg logit contributions | |
lehem | -0.555 |
RON | -0.519 |
rans | -0.506 |
rons | -0.494 |
enance | -0.489 |
Token | I |
Token ID | 314 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
jriwal | +2.973 |
kefeller | +2.716 |
impulse | +2.696 |
turmoil | +2.557 |
reaction | +2.517 |
Neg logit contributions | |
lehem | -3.198 |
RON | -2.994 |
rans | -2.912 |
rons | -2.843 |
enance | -2.829 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
lehem | +5.493 |
RON | +5.056 |
rans | +5.029 |
enance | +4.869 |
rons | +4.847 |
Neg logit contributions | |
jriwal | -6.185 |
kefeller | -5.883 |
impulse | -5.586 |
turmoil | -5.260 |
reaction | -5.167 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
jriwal | +0.020 |
kefeller | +0.018 |
impulse | +0.018 |
turmoil | +0.017 |
reaction | +0.017 |
Neg logit contributions | |
lehem | -0.020 |
RON | -0.019 |
rans | -0.018 |
rons | -0.018 |
enance | -0.018 |
Token | First |
Token ID | 5962 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
lehem | +0.078 |
RON | +0.072 |
rans | +0.070 |
rons | +0.068 |
enance | +0.067 |
Neg logit contributions | |
jriwal | -0.114 |
kefeller | -0.107 |
impulse | -0.105 |
turmoil | -0.100 |
reaction | -0.099 |
Token | posted |
Token ID | 4481 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
jriwal | +2.361 |
kefeller | +2.151 |
impulse | +2.085 |
turmoil | +1.964 |
reaction | +1.916 |
Neg logit contributions | |
lehem | -2.857 |
RON | -2.692 |
rans | -2.638 |
rons | -2.573 |
enance | -2.555 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
jriwal | +1.358 |
kefeller | +1.269 |
impulse | +1.233 |
turmoil | +1.176 |
reaction | +1.151 |
Neg logit contributions | |
lehem | -1.036 |
RON | -0.961 |
rans | -0.937 |
rons | -0.913 |
enance | -0.896 |
Token | R |
Token ID | 49 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
jriwal | +2.322 |
kefeller | +2.147 |
impulse | +2.100 |
turmoil | +1.997 |
reaction | +1.964 |
Neg logit contributions | |
lehem | -2.054 |
RON | -1.898 |
rans | -1.856 |
rons | -1.817 |
enance | -1.800 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
jriwal | +11.610 |
kefeller | +10.735 |
impulse | +10.501 |
reaction | +10.005 |
turmoil | +9.950 |
Neg logit contributions | |
lehem | -9.168 |
RON | -8.437 |
rans | -8.014 |
rons | -7.826 |
enance | -7.620 |
Token | k |
Token ID | 74 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
jriwal | +0.137 |
kefeller | +0.127 |
impulse | +0.124 |
turmoil | +0.119 |
reaction | +0.117 |
Neg logit contributions | |
lehem | -0.106 |
RON | -0.098 |
rans | -0.095 |
rons | -0.093 |
enance | -0.092 |
Token | ot |
Token ID | 313 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
jriwal | +0.790 |
kefeller | +0.731 |
impulse | +0.712 |
turmoil | +0.676 |
reaction | +0.661 |
Neg logit contributions | |
lehem | -0.767 |
RON | -0.717 |
rans | -0.703 |
rons | -0.685 |
enance | -0.675 |
Token | : |
Token ID | 25 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
lehem | +2.526 |
RON | +2.387 |
rans | +2.349 |
rons | +2.283 |
enance | +2.239 |
Neg logit contributions | |
jriwal | -2.287 |
kefeller | -2.142 |
impulse | -2.029 |
turmoil | -1.920 |
reaction | -1.866 |
Token | In |
Token ID | 554 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
jriwal | +0.781 |
kefeller | +0.719 |
impulse | +0.702 |
turmoil | +0.665 |
reaction | +0.653 |
Neg logit contributions | |
lehem | -0.782 |
RON | -0.732 |
rans | -0.714 |
rons | -0.698 |
enance | -0.691 |
Token | the |
Token ID | 262 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
jriwal | +2.312 |
kefeller | +2.092 |
impulse | +2.063 |
turmoil | +1.919 |
reaction | +1.884 |
Neg logit contributions | |
lehem | -3.291 |
RON | -3.091 |
rans | -3.032 |
rons | -2.969 |
enance | -2.953 |
Token | End |
Token ID | 5268 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
jriwal | +0.064 |
kefeller | +0.058 |
impulse | +0.056 |
turmoil | +0.053 |
reaction | +0.051 |
Neg logit contributions | |
lehem | -0.082 |
RON | -0.078 |
rans | -0.076 |
rons | -0.075 |
enance | -0.074 |
Token | Around |
Token ID | 16824 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
lehem | +3.456 |
RON | +3.209 |
rans | +3.171 |
rons | +3.090 |
enance | +3.005 |
Neg logit contributions | |
jriwal | -3.685 |
kefeller | -3.419 |
impulse | -3.324 |
turmoil | -3.123 |
reaction | -3.031 |
Token | . |
Token ID | 13 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
lehem | +3.002 |
RON | +2.828 |
rans | +2.750 |
rons | +2.724 |
enance | +2.668 |
Neg logit contributions | |
jriwal | -2.299 |
kefeller | -2.111 |
impulse | -2.016 |
turmoil | -1.889 |
reaction | -1.822 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
lehem | +0.394 |
RON | +0.368 |
rans | +0.358 |
rons | +0.348 |
enance | +0.345 |
Neg logit contributions | |
jriwal | -0.457 |
kefeller | -0.423 |
impulse | -0.414 |
turmoil | -0.393 |
reaction | -0.386 |
Token | R |
Token ID | 49 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
jriwal | +2.605 |
kefeller | +2.408 |
impulse | +2.355 |
turmoil | +2.240 |
reaction | +2.204 |
Neg logit contributions | |
lehem | -2.310 |
RON | -2.131 |
rans | -2.087 |
rons | -2.044 |
enance | -2.025 |
Token | ape |
Token ID | 1758 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
jriwal | +11.619 |
kefeller | +10.744 |
impulse | +10.504 |
reaction | +10.004 |
turmoil | +9.957 |
Neg logit contributions | |
lehem | -9.137 |
RON | -8.427 |
rans | -8.011 |
rons | -7.819 |
enance | -7.611 |
Token | by |
Token ID | 416 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
lehem | +0.443 |
RON | +0.420 |
rans | +0.412 |
rons | +0.402 |
enance | +0.397 |
Neg logit contributions | |
jriwal | -0.354 |
kefeller | -0.321 |
impulse | -0.308 |
turmoil | -0.289 |
reaction | -0.280 |
Token | fraud |
Token ID | 7394 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
jriwal | +2.081 |
kefeller | +1.892 |
impulse | +1.859 |
turmoil | +1.742 |
reaction | +1.709 |
Neg logit contributions | |
lehem | -2.662 |
RON | -2.497 |
rans | -2.441 |
rons | -2.395 |
enance | -2.376 |
Token | : |
Token ID | 25 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
jriwal | +3.228 |
kefeller | +2.928 |
impulse | +2.877 |
turmoil | +2.700 |
reaction | +2.656 |
Neg logit contributions | |
lehem | -4.034 |
RON | -3.805 |
rans | -3.713 |
rons | -3.634 |
enance | -3.623 |
Token | What |
Token ID | 1867 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
jriwal | +0.681 |
kefeller | +0.625 |
impulse | +0.606 |
turmoil | +0.572 |
reaction | +0.559 |
Neg logit contributions | |
lehem | -0.738 |
RON | -0.693 |
rans | -0.678 |
rons | -0.661 |
enance | -0.656 |
Token | more |
Token ID | 517 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
lehem | +0.206 |
RON | +0.194 |
rans | +0.189 |
rons | +0.185 |
enance | +0.184 |
Neg logit contributions | |
jriwal | -0.175 |
kefeller | -0.159 |
impulse | -0.155 |
turmoil | -0.147 |
reaction | -0.143 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
jriwal | +4.328 |
impulse | +3.950 |
turmoil | +3.830 |
kefeller | +3.811 |
reaction | +3.737 |
Neg logit contributions | |
lehem | -4.510 |
RON | -4.070 |
enance | -3.890 |
rans | -3.875 |
rons | -3.749 |
Token | About |
Token ID | 8585 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
jriwal | +2.384 |
kefeller | +2.204 |
impulse | +2.156 |
turmoil | +2.050 |
reaction | +2.017 |
Neg logit contributions | |
lehem | -2.111 |
RON | -1.949 |
rans | -1.907 |
rons | -1.867 |
enance | -1.849 |
Token |
|
Token ID | 198 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
lehem | +0.148 |
RON | +0.138 |
rans | +0.135 |
rons | +0.132 |
enance | +0.131 |
Neg logit contributions | |
jriwal | -0.149 |
kefeller | -0.137 |
impulse | -0.133 |
turmoil | -0.126 |
reaction | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
jriwal | +2.029 |
kefeller | +1.859 |
impulse | +1.832 |
turmoil | +1.737 |
reaction | +1.714 |
Neg logit contributions | |
lehem | -2.280 |
RON | -2.110 |
rans | -2.066 |
rons | -2.030 |
enance | -2.004 |
Token | R |
Token ID | 49 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
jriwal | +2.100 |
kefeller | +1.937 |
impulse | +1.900 |
turmoil | +1.805 |
reaction | +1.778 |
Neg logit contributions | |
lehem | -1.873 |
RON | -1.725 |
rans | -1.693 |
rons | -1.656 |
enance | -1.642 |
Token | acing |
Token ID | 4092 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
jriwal | +10.857 |
kefeller | +10.081 |
impulse | +9.859 |
reaction | +9.378 |
turmoil | +9.343 |
Neg logit contributions | |
lehem | -8.893 |
RON | -8.158 |
rans | -7.797 |
rons | -7.593 |
enance | -7.393 |
Token | Apex |
Token ID | 49440 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
lehem | +1.772 |
RON | +1.666 |
rans | +1.634 |
rons | +1.596 |
enance | +1.586 |
Neg logit contributions | |
jriwal | -1.509 |
kefeller | -1.385 |
impulse | -1.325 |
turmoil | -1.241 |
reaction | -1.215 |
Token | is |
Token ID | 318 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
jriwal | +0.588 |
kefeller | +0.537 |
impulse | +0.523 |
turmoil | +0.492 |
reaction | +0.482 |
Neg logit contributions | |
lehem | -0.694 |
RON | -0.653 |
rans | -0.638 |
rons | -0.625 |
enance | -0.620 |
Token | a |
Token ID | 257 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
jriwal | +3.499 |
kefeller | +3.146 |
impulse | +3.083 |
turmoil | +2.887 |
reaction | +2.833 |
Neg logit contributions | |
lehem | -4.927 |
RON | -4.639 |
rans | -4.542 |
rons | -4.450 |
enance | -4.419 |
Token | fast |
Token ID | 3049 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
jriwal | +0.555 |
kefeller | +0.500 |
impulse | +0.481 |
turmoil | +0.447 |
reaction | +0.432 |
Neg logit contributions | |
lehem | -0.846 |
RON | -0.805 |
rans | -0.787 |
rons | -0.773 |
enance | -0.766 |
Token | 16 |
Token ID | 1433 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
lehem | +0.441 |
RON | +0.411 |
rans | +0.399 |
rons | +0.388 |
enance | +0.385 |
Neg logit contributions | |
jriwal | -0.518 |
kefeller | -0.480 |
impulse | -0.469 |
turmoil | -0.446 |
reaction | -0.438 |
Token | , |
Token ID | 11 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
lehem | +1.666 |
RON | +1.566 |
rans | +1.531 |
rons | +1.490 |
enance | +1.485 |
Neg logit contributions | |
jriwal | -1.486 |
kefeller | -1.393 |
impulse | -1.338 |
turmoil | -1.249 |
reaction | -1.218 |
Token | violence |
Token ID | 3685 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
jriwal | +0.239 |
kefeller | +0.221 |
impulse | +0.214 |
turmoil | +0.202 |
reaction | +0.198 |
Neg logit contributions | |
lehem | -0.262 |
RON | -0.246 |
rans | -0.240 |
rons | -0.234 |
enance | -0.233 |
Token | erupted |
Token ID | 23681 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
jriwal | +2.040 |
kefeller | +1.810 |
impulse | +1.779 |
turmoil | +1.662 |
reaction | +1.625 |
Neg logit contributions | |
lehem | -3.231 |
RON | -3.064 |
rans | -2.989 |
rons | -2.938 |
enance | -2.911 |
Token | in |
Token ID | 287 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
lehem | +0.934 |
RON | +0.878 |
rans | +0.865 |
rons | +0.847 |
enance | +0.840 |
Neg logit contributions | |
jriwal | -0.721 |
kefeller | -0.665 |
impulse | -0.639 |
turmoil | -0.596 |
reaction | -0.580 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
jriwal | +3.358 |
kefeller | +3.024 |
impulse | +2.993 |
turmoil | +2.833 |
reaction | +2.793 |
Neg logit contributions | |
lehem | -4.057 |
RON | -3.809 |
rans | -3.692 |
rons | -3.633 |
enance | -3.605 |
Token | t |
Token ID | 83 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
jriwal | +10.903 |
kefeller | +9.656 |
impulse | +9.599 |
reaction | +9.295 |
turmoil | +9.277 |
Neg logit contributions | |
lehem | -8.704 |
RON | -8.110 |
enance | -7.686 |
rons | -7.649 |
rans | -7.471 |
Token | ak |
Token ID | 461 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
lehem | +3.009 |
rans | +2.896 |
RON | +2.833 |
rons | +2.723 |
enance | +2.699 |
Neg logit contributions | |
jriwal | -3.521 |
kefeller | -3.328 |
impulse | -3.261 |
senal | -3.204 |
turmoil | -3.128 |
Token | city |
Token ID | 1748 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
jriwal | +0.987 |
kefeller | +0.902 |
impulse | +0.875 |
turmoil | +0.820 |
reaction | +0.800 |
Neg logit contributions | |
lehem | -1.259 |
RON | -1.187 |
rans | -1.164 |
rons | -1.138 |
enance | -1.129 |
Token | which |
Token ID | 543 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
lehem | +2.660 |
RON | +2.500 |
rans | +2.488 |
rons | +2.416 |
enance | +2.410 |
Neg logit contributions | |
jriwal | -2.175 |
kefeller | -2.042 |
impulse | -1.941 |
turmoil | -1.801 |
allergy | -1.738 |
Token | continued |
Token ID | 3767 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
lehem | +1.168 |
RON | +1.097 |
rans | +1.085 |
rons | +1.057 |
enance | +1.052 |
Neg logit contributions | |
jriwal | -0.879 |
kefeller | -0.814 |
impulse | -0.777 |
turmoil | -0.723 |
reaction | -0.704 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
jriwal | +0.507 |
kefeller | +0.466 |
impulse | +0.456 |
turmoil | +0.432 |
reaction | +0.423 |
Neg logit contributions | |
lehem | -0.519 |
RON | -0.486 |
rans | -0.474 |
rons | -0.463 |
enance | -0.459 |
Token | Senior |
Token ID | 31224 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
jriwal | +0.400 |
kefeller | +0.370 |
impulse | +0.362 |
turmoil | +0.344 |
reaction | +0.337 |
Neg logit contributions | |
lehem | -0.364 |
RON | -0.339 |
rans | -0.330 |
rons | -0.322 |
enance | -0.319 |
Token | advocate |
Token ID | 12811 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
jriwal | +1.133 |
kefeller | +1.020 |
impulse | +0.995 |
turmoil | +0.930 |
reaction | +0.908 |
Neg logit contributions | |
lehem | -1.625 |
RON | -1.534 |
rans | -1.503 |
rons | -1.473 |
enance | -1.464 |
Token | Muk |
Token ID | 31509 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
jriwal | +0.468 |
kefeller | +0.435 |
impulse | +0.420 |
turmoil | +0.397 |
reaction | +0.388 |
Neg logit contributions | |
lehem | -0.483 |
RON | -0.453 |
rans | -0.443 |
rons | -0.434 |
enance | -0.429 |
Token | ul |
Token ID | 377 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
jriwal | +4.795 |
kefeller | +4.300 |
impulse | +4.208 |
turmoil | +4.001 |
reaction | +3.958 |
Neg logit contributions | |
lehem | -4.446 |
RON | -4.180 |
rans | -4.018 |
enance | -3.952 |
rons | -3.898 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
jriwal | +2.349 |
kefeller | +2.145 |
impulse | +2.092 |
turmoil | +1.975 |
reaction | +1.937 |
Neg logit contributions | |
lehem | -2.722 |
RON | -2.565 |
rans | -2.499 |
rons | -2.447 |
enance | -2.436 |
Token | at |
Token ID | 265 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
jriwal | +10.127 |
impulse | +9.002 |
kefeller | +8.840 |
reaction | +8.777 |
inki | +8.661 |
Neg logit contributions | |
lehem | -8.992 |
RON | -8.431 |
──────── | -7.819 |
enance | -7.669 |
rons | -7.629 |
Token | gi |
Token ID | 12397 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
lehem | +3.146 |
RON | +2.970 |
rans | +2.964 |
rons | +2.883 |
enance | +2.757 |
Neg logit contributions | |
jriwal | -2.064 |
kefeller | -1.872 |
impulse | -1.780 |
turmoil | -1.670 |
reaction | -1.590 |
Token | appearing |
Token ID | 12655 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
jriwal | +3.905 |
kefeller | +3.490 |
impulse | +3.456 |
turmoil | +3.265 |
reaction | +3.225 |
Neg logit contributions | |
lehem | -4.635 |
RON | -4.336 |
rans | -4.231 |
rons | -4.154 |
enance | -4.121 |
Token | for |
Token ID | 329 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
lehem | +3.137 |
RON | +2.975 |
rans | +2.909 |
enance | +2.869 |
rons | +2.854 |
Neg logit contributions | |
jriwal | -2.051 |
kefeller | -1.932 |
impulse | -1.800 |
turmoil | -1.638 |
senal | -1.616 |
Token | Gh |
Token ID | 11972 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
jriwal | +1.367 |
kefeller | +1.246 |
impulse | +1.214 |
turmoil | +1.143 |
reaction | +1.119 |
Neg logit contributions | |
lehem | -1.656 |
RON | -1.558 |
rans | -1.523 |
rons | -1.491 |
enance | -1.480 |
Token | Sen |
Token ID | 2311 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
lehem | +0.578 |
RON | +0.545 |
rans | +0.538 |
rons | +0.522 |
enance | +0.522 |
Neg logit contributions | |
jriwal | -0.476 |
kefeller | -0.436 |
impulse | -0.412 |
turmoil | -0.385 |
reaction | -0.375 |
Token | . |
Token ID | 13 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
jriwal | +1.494 |
kefeller | +1.361 |
impulse | +1.324 |
turmoil | +1.244 |
reaction | +1.216 |
Neg logit contributions | |
lehem | -1.874 |
RON | -1.767 |
rans | -1.728 |
rons | -1.692 |
enance | -1.679 |
Token | Jeff |
Token ID | 19139 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
lehem | +0.935 |
RON | +0.891 |
rans | +0.863 |
enance | +0.843 |
rons | +0.843 |
Neg logit contributions | |
jriwal | -0.888 |
kefeller | -0.815 |
impulse | -0.783 |
turmoil | -0.730 |
senal | -0.719 |
Token | Flake |
Token ID | 39727 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
lehem | +0.346 |
RON | +0.323 |
rans | +0.313 |
rons | +0.306 |
enance | +0.303 |
Neg logit contributions | |
jriwal | -0.404 |
kefeller | -0.375 |
impulse | -0.368 |
turmoil | -0.349 |
reaction | -0.342 |
Token | ( |
Token ID | 7 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
jriwal | +2.790 |
kefeller | +2.549 |
impulse | +2.508 |
turmoil | +2.376 |
reaction | +2.335 |
Neg logit contributions | |
lehem | -2.968 |
RON | -2.769 |
rans | -2.712 |
rons | -2.644 |
enance | -2.628 |
Token | R |
Token ID | 49 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
jriwal | +0.059 |
kefeller | +0.055 |
impulse | +0.054 |
turmoil | +0.051 |
reaction | +0.050 |
Neg logit contributions | |
lehem | -0.045 |
RON | -0.041 |
rans | -0.040 |
rons | -0.039 |
enance | -0.039 |
Token | - |
Token ID | 12 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
jriwal | +6.220 |
kefeller | +5.729 |
impulse | +5.617 |
reaction | +5.265 |
turmoil | +5.160 |
Neg logit contributions | |
lehem | -12.648 |
RON | -11.768 |
rans | -11.459 |
enance | -11.382 |
rons | -11.324 |
Token | Ari |
Token ID | 26529 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
lehem | +3.810 |
RON | +3.637 |
rans | +3.485 |
enance | +3.374 |
rons | +3.357 |
Neg logit contributions | |
jriwal | -4.868 |
kefeller | -4.474 |
impulse | -4.338 |
turmoil | -4.117 |
reaction | -4.014 |
Token | z |
Token ID | 89 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
jriwal | +1.434 |
kefeller | +1.314 |
impulse | +1.273 |
turmoil | +1.199 |
reaction | +1.170 |
Neg logit contributions | |
lehem | -1.581 |
RON | -1.490 |
rans | -1.456 |
rons | -1.428 |
enance | -1.408 |
Token | .) |
Token ID | 2014 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
jriwal | +2.334 |
kefeller | +2.158 |
impulse | +2.115 |
turmoil | +2.005 |
reaction | +1.982 |
Neg logit contributions | |
lehem | -2.155 |
RON | -2.010 |
rans | -1.949 |
rons | -1.910 |
enance | -1.890 |
Token | after |
Token ID | 706 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
lehem | +0.549 |
RON | +0.521 |
rans | +0.510 |
rons | +0.501 |
enance | +0.498 |
Neg logit contributions | |
jriwal | -0.367 |
kefeller | -0.332 |
impulse | -0.318 |
turmoil | -0.295 |
reaction | -0.286 |
Token | ( |
Token ID | 357 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
lehem | +0.080 |
RON | +0.075 |
rans | +0.073 |
rons | +0.071 |
enance | +0.071 |
Neg logit contributions | |
jriwal | -0.079 |
kefeller | -0.072 |
impulse | -0.070 |
turmoil | -0.067 |
reaction | -0.065 |
Token | SD |
Token ID | 10305 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
lehem | +0.214 |
RON | +0.200 |
rans | +0.194 |
rons | +0.190 |
enance | +0.188 |
Neg logit contributions | |
jriwal | -0.242 |
kefeller | -0.224 |
impulse | -0.219 |
turmoil | -0.209 |
reaction | -0.205 |
Token | ) |
Token ID | 8 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
lehem | +0.911 |
RON | +0.853 |
rans | +0.831 |
rons | +0.811 |
enance | +0.804 |
Neg logit contributions | |
jriwal | -0.957 |
kefeller | -0.883 |
impulse | -0.861 |
turmoil | -0.818 |
reaction | -0.801 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
jriwal | +0.302 |
kefeller | +0.277 |
impulse | +0.270 |
turmoil | +0.255 |
reaction | +0.249 |
Neg logit contributions | |
lehem | -0.331 |
RON | -0.311 |
rans | -0.304 |
rons | -0.297 |
enance | -0.294 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
jriwal | +1.418 |
kefeller | +1.302 |
impulse | +1.277 |
turmoil | +1.209 |
reaction | +1.189 |
Neg logit contributions | |
lehem | -1.513 |
RON | -1.408 |
rans | -1.376 |
rons | -1.348 |
enance | -1.332 |
Token | R |
Token ID | 49 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
jriwal | +1.441 |
kefeller | +1.333 |
impulse | +1.304 |
turmoil | +1.239 |
reaction | +1.218 |
Neg logit contributions | |
lehem | -1.273 |
RON | -1.184 |
rans | -1.153 |
rons | -1.125 |
enance | -1.114 |
Token | SS |
Token ID | 5432 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
jriwal | +9.894 |
kefeller | +9.065 |
impulse | +9.002 |
reaction | +8.432 |
turmoil | +8.363 |
Neg logit contributions | |
lehem | -9.247 |
RON | -8.698 |
rans | -8.180 |
rons | -8.122 |
enance | -7.897 |
Token | ( |
Token ID | 357 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
jriwal | +0.812 |
kefeller | +0.754 |
impulse | +0.732 |
turmoil | +0.703 |
reaction | +0.683 |
Neg logit contributions | |
lehem | -0.643 |
RON | -0.605 |
rans | -0.583 |
rons | -0.572 |
enance | -0.564 |
Token | HD |
Token ID | 10227 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
lehem | +0.043 |
RON | +0.040 |
rans | +0.039 |
rons | +0.038 |
enance | +0.038 |
Neg logit contributions | |
jriwal | -0.040 |
kefeller | -0.037 |
impulse | -0.036 |
turmoil | -0.034 |
reaction | -0.034 |
Token | ) |
Token ID | 8 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
lehem | +1.264 |
RON | +1.184 |
rans | +1.155 |
rons | +1.125 |
enance | +1.112 |
Neg logit contributions | |
jriwal | -1.347 |
kefeller | -1.243 |
impulse | -1.212 |
turmoil | -1.151 |
reaction | -1.128 |
Token | | |
Token ID | 930 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
jriwal | +0.227 |
kefeller | +0.207 |
impulse | +0.202 |
turmoil | +0.190 |
reaction | +0.186 |
Neg logit contributions | |
lehem | -0.258 |
RON | -0.243 |
rans | -0.237 |
rons | -0.232 |
enance | -0.230 |
Token | by |
Token ID | 416 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
jriwal | +0.943 |
kefeller | +0.864 |
impulse | +0.841 |
turmoil | +0.794 |
reaction | +0.776 |
Neg logit contributions | |
lehem | -1.076 |
RON | -1.011 |
rans | -0.989 |
rons | -0.966 |
enance | -0.958 |
Token | blocking |
Token ID | 12013 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
jriwal | +0.632 |
kefeller | +0.571 |
impulse | +0.560 |
turmoil | +0.526 |
reaction | +0.515 |
Neg logit contributions | |
lehem | -0.803 |
RON | -0.757 |
rans | -0.739 |
rons | -0.725 |
enance | -0.719 |
Token | national |
Token ID | 2260 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
jriwal | +2.244 |
kefeller | +2.035 |
impulse | +2.003 |
turmoil | +1.881 |
reaction | +1.852 |
Neg logit contributions | |
lehem | -2.616 |
RON | -2.466 |
rans | -2.388 |
rons | -2.354 |
enance | -2.323 |
Token | highway |
Token ID | 12763 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
jriwal | +0.882 |
kefeller | +0.798 |
impulse | +0.772 |
turmoil | +0.722 |
reaction | +0.704 |
Neg logit contributions | |
lehem | -1.266 |
RON | -1.196 |
rans | -1.173 |
rons | -1.149 |
enance | -1.141 |
Token | connecting |
Token ID | 14320 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
jriwal | +0.734 |
kefeller | +0.672 |
impulse | +0.653 |
turmoil | +0.615 |
reaction | +0.602 |
Neg logit contributions | |
lehem | -0.868 |
RON | -0.817 |
rans | -0.799 |
rons | -0.782 |
enance | -0.775 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
lehem | +1.520 |
RON | +1.423 |
rans | +1.397 |
rons | +1.366 |
enance | +1.352 |
Neg logit contributions | |
jriwal | -1.353 |
kefeller | -1.252 |
impulse | -1.207 |
turmoil | -1.138 |
reaction | -1.106 |
Token | t |
Token ID | 83 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
jriwal | +10.410 |
kefeller | +9.340 |
impulse | +9.229 |
inki | +8.970 |
turmoil | +8.817 |
Neg logit contributions | |
lehem | -8.232 |
RON | -7.743 |
enance | -7.356 |
rons | -7.213 |
rans | -7.011 |
Token | ak |
Token ID | 461 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
lehem | +3.062 |
rans | +2.895 |
RON | +2.849 |
rons | +2.745 |
enance | +2.716 |
Neg logit contributions | |
jriwal | -3.196 |
kefeller | -2.985 |
impulse | -2.906 |
turmoil | -2.811 |
senal | -2.770 |
Token | to |
Token ID | 284 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
jriwal | +0.981 |
kefeller | +0.891 |
impulse | +0.864 |
turmoil | +0.809 |
reaction | +0.788 |
Neg logit contributions | |
lehem | -1.359 |
RON | -1.284 |
rans | -1.259 |
rons | -1.232 |
enance | -1.222 |
Token | Delhi |
Token ID | 12517 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
lehem | +0.951 |
RON | +0.891 |
rans | +0.873 |
rons | +0.851 |
enance | +0.843 |
Neg logit contributions | |
jriwal | -0.874 |
kefeller | -0.809 |
impulse | -0.781 |
turmoil | -0.735 |
reaction | -0.717 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
jriwal | +0.465 |
kefeller | +0.426 |
impulse | +0.415 |
turmoil | +0.389 |
reaction | +0.380 |
Neg logit contributions | |
lehem | -0.563 |
RON | -0.529 |
rans | -0.519 |
rons | -0.506 |
enance | -0.502 |
Token | att |
Token ID | 1078 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
lehem | +2.127 |
RON | +2.023 |
rans | +1.997 |
rons | +1.955 |
enance | +1.939 |
Neg logit contributions | |
jriwal | -1.383 |
kefeller | -1.259 |
impulse | -1.217 |
turmoil | -1.137 |
reaction | -1.096 |
Token | u |
Token ID | 84 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
lehem | +0.839 |
RON | +0.786 |
rans | +0.784 |
rons | +0.761 |
enance | +0.753 |
Neg logit contributions | |
jriwal | -0.598 |
kefeller | -0.545 |
impulse | -0.530 |
turmoil | -0.496 |
reaction | -0.485 |
Token | and |
Token ID | 290 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
jriwal | +2.230 |
kefeller | +2.021 |
impulse | +1.975 |
turmoil | +1.857 |
reaction | +1.821 |
Neg logit contributions | |
lehem | -2.761 |
RON | -2.601 |
rans | -2.541 |
rons | -2.490 |
enance | -2.474 |
Token | C |
Token ID | 327 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
jriwal | +4.080 |
kefeller | +3.726 |
impulse | +3.707 |
turmoil | +3.518 |
reaction | +3.482 |
Neg logit contributions | |
lehem | -4.182 |
RON | -3.876 |
rans | -3.795 |
rons | -3.694 |
enance | -3.672 |
Token | K |
Token ID | 509 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
jriwal | +0.061 |
kefeller | +0.056 |
impulse | +0.055 |
turmoil | +0.052 |
reaction | +0.051 |
Neg logit contributions | |
lehem | -0.060 |
RON | -0.056 |
rans | -0.054 |
rons | -0.053 |
enance | -0.053 |
Token | Pr |
Token ID | 1736 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
jriwal | +0.941 |
kefeller | +0.862 |
impulse | +0.841 |
turmoil | +0.794 |
reaction | +0.780 |
Neg logit contributions | |
lehem | -1.015 |
RON | -0.953 |
rans | -0.929 |
rons | -0.908 |
enance | -0.902 |
Token | as |
Token ID | 292 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
jriwal | +10.564 |
kefeller | +9.583 |
impulse | +9.278 |
inki | +8.866 |
turmoil | +8.838 |
Neg logit contributions | |
lehem | -8.268 |
RON | -7.897 |
──────── | -7.186 |
rans | -7.053 |
enance | -7.002 |
Token | ad |
Token ID | 324 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
jriwal | +0.874 |
kefeller | +0.811 |
impulse | +0.794 |
turmoil | +0.756 |
reaction | +0.744 |
Neg logit contributions | |
lehem | -0.700 |
RON | -0.650 |
rans | -0.630 |
rons | -0.614 |
enance | -0.609 |
Token | also |
Token ID | 635 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
lehem | +0.890 |
RON | +0.840 |
rans | +0.823 |
rons | +0.805 |
enance | +0.796 |
Neg logit contributions | |
jriwal | -0.763 |
kefeller | -0.706 |
impulse | -0.679 |
turmoil | -0.640 |
reaction | -0.623 |
Token | pulled |
Token ID | 5954 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
jriwal | +1.050 |
kefeller | +0.954 |
impulse | +0.929 |
turmoil | +0.872 |
reaction | +0.853 |
Neg logit contributions | |
lehem | -1.349 |
RON | -1.272 |
rans | -1.244 |
rons | -1.219 |
enance | -1.210 |
Token | up |
Token ID | 510 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
jriwal | +2.989 |
kefeller | +2.663 |
impulse | +2.609 |
turmoil | +2.434 |
reaction | +2.386 |
Neg logit contributions | |
lehem | -4.547 |
RON | -4.319 |
rans | -4.206 |
rons | -4.145 |
enance | -4.070 |
Token | a |
Token ID | 257 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
jriwal | +1.533 |
kefeller | +1.394 |
impulse | +1.366 |
turmoil | +1.282 |
reaction | +1.255 |
Neg logit contributions | |
lehem | -1.983 |
RON | -1.866 |
rans | -1.825 |
rons | -1.786 |
enance | -1.772 |
Token | long |
Token ID | 890 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
lehem | +0.614 |
RON | +0.580 |
rans | +0.567 |
rons | +0.555 |
enance | +0.551 |
Neg logit contributions | |
jriwal | -0.506 |
kefeller | -0.461 |
impulse | -0.444 |
turmoil | -0.418 |
reaction | -0.407 |
Token | time |
Token ID | 640 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
jriwal | +1.034 |
kefeller | +0.913 |
impulse | +0.892 |
turmoil | +0.821 |
reaction | +0.799 |
Neg logit contributions | |
lehem | -1.944 |
RON | -1.848 |
rans | -1.813 |
rons | -1.783 |
enance | -1.767 |
Token | ." |
Token ID | 526 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
lehem | +1.548 |
RON | +1.459 |
rans | +1.427 |
rons | +1.399 |
enance | +1.389 |
Neg logit contributions | |
jriwal | -1.307 |
kefeller | -1.199 |
impulse | -1.144 |
turmoil | -1.081 |
reaction | -1.050 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
jriwal | +0.801 |
kefeller | +0.741 |
impulse | +0.722 |
turmoil | +0.685 |
reaction | +0.673 |
Neg logit contributions | |
lehem | -0.844 |
RON | -0.787 |
rans | -0.770 |
rons | -0.752 |
enance | -0.744 |
Token | Oil |
Token ID | 44142 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
jriwal | +2.693 |
kefeller | +2.488 |
impulse | +2.434 |
turmoil | +2.314 |
reaction | +2.277 |
Neg logit contributions | |
lehem | -2.391 |
RON | -2.203 |
rans | -2.158 |
rons | -2.116 |
enance | -2.096 |
Token | from |
Token ID | 422 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
jriwal | +8.219 |
kefeller | +7.380 |
impulse | +7.283 |
turmoil | +7.148 |
reaction | +6.929 |
Neg logit contributions | |
lehem | -10.538 |
RON | -10.054 |
enance | -9.719 |
rans | -9.681 |
rons | -9.657 |
Token | a |
Token ID | 257 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
jriwal | +1.110 |
kefeller | +1.008 |
impulse | +0.979 |
turmoil | +0.918 |
reaction | +0.897 |
Neg logit contributions | |
lehem | -1.466 |
RON | -1.383 |
rans | -1.353 |
rons | -1.326 |
enance | -1.316 |
Token | wrecked |
Token ID | 44770 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
jriwal | +0.609 |
kefeller | +0.551 |
impulse | +0.535 |
turmoil | +0.501 |
reaction | +0.489 |
Neg logit contributions | |
lehem | -0.844 |
RON | -0.797 |
rans | -0.780 |
rons | -0.765 |
enance | -0.759 |
Token | tanker |
Token ID | 46335 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
jriwal | +0.304 |
kefeller | +0.276 |
impulse | +0.267 |
turmoil | +0.250 |
reaction | +0.244 |
Neg logit contributions | |
lehem | -0.408 |
RON | -0.385 |
rans | -0.377 |
rons | -0.369 |
enance | -0.366 |
Token | is |
Token ID | 318 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
jriwal | +1.937 |
kefeller | +1.753 |
impulse | +1.733 |
turmoil | +1.626 |
reaction | +1.592 |
Neg logit contributions | |
lehem | -2.550 |
RON | -2.408 |
rans | -2.354 |
rons | -2.297 |
enance | -2.284 |
Token | . |
Token ID | 13 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
lehem | +1.733 |
RON | +1.628 |
rans | +1.604 |
rons | +1.566 |
enance | +1.560 |
Neg logit contributions | |
jriwal | -1.312 |
kefeller | -1.214 |
impulse | -1.155 |
turmoil | -1.080 |
reaction | -1.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
jriwal | +0.050 |
kefeller | +0.046 |
impulse | +0.045 |
turmoil | +0.043 |
reaction | +0.042 |
Neg logit contributions | |
lehem | -0.048 |
RON | -0.045 |
rans | -0.044 |
rons | -0.043 |
enance | -0.043 |
Token | Name |
Token ID | 5376 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
jriwal | +1.965 |
kefeller | +1.817 |
impulse | +1.777 |
turmoil | +1.690 |
reaction | +1.662 |
Neg logit contributions | |
lehem | -1.733 |
RON | -1.606 |
rans | -1.568 |
rons | -1.533 |
enance | -1.518 |
Token | : |
Token ID | 25 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
jriwal | +1.586 |
kefeller | +1.453 |
impulse | +1.422 |
turmoil | +1.346 |
reaction | +1.322 |
Neg logit contributions | |
lehem | -1.685 |
RON | -1.576 |
rans | -1.540 |
rons | -1.507 |
enance | -1.492 |
Token | MSI |
Token ID | 30781 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
lehem | +0.024 |
RON | +0.023 |
rans | +0.022 |
rons | +0.022 |
enance | +0.021 |
Neg logit contributions | |
jriwal | -0.023 |
kefeller | -0.021 |
impulse | -0.021 |
turmoil | -0.020 |
reaction | -0.019 |
Token | R |
Token ID | 371 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
jriwal | +3.938 |
kefeller | +3.607 |
impulse | +3.588 |
turmoil | +3.397 |
reaction | +3.355 |
Neg logit contributions | |
lehem | -4.126 |
RON | -3.810 |
rans | -3.756 |
rons | -3.665 |
enance | -3.630 |
Token | 78 |
Token ID | 3695 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
jriwal | +9.487 |
impulse | +8.794 |
kefeller | +8.743 |
reaction | +8.257 |
turmoil | +8.257 |
Neg logit contributions | |
lehem | -9.077 |
RON | -8.105 |
enance | -7.843 |
rans | -7.774 |
rons | -7.564 |
Token | 70 |
Token ID | 2154 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
lehem | +1.463 |
RON | +1.383 |
rans | +1.346 |
rons | +1.315 |
enance | +1.301 |
Neg logit contributions | |
jriwal | -1.366 |
kefeller | -1.244 |
impulse | -1.206 |
turmoil | -1.140 |
reaction | -1.115 |
Token | Hawk |
Token ID | 26698 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
lehem | +3.017 |
RON | +2.895 |
rans | +2.798 |
rons | +2.705 |
enance | +2.657 |
Neg logit contributions | |
jriwal | -3.146 |
kefeller | -2.883 |
impulse | -2.742 |
turmoil | -2.615 |
reaction | -2.556 |
Token |
|
Token ID | 198 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
jriwal | +0.510 |
kefeller | +0.468 |
impulse | +0.455 |
turmoil | +0.432 |
reaction | +0.422 |
Neg logit contributions | |
lehem | -0.523 |
RON | -0.491 |
rans | -0.479 |
rons | -0.469 |
enance | -0.463 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
jriwal | +1.716 |
kefeller | +1.577 |
impulse | +1.548 |
turmoil | +1.465 |
reaction | +1.443 |
Neg logit contributions | |
lehem | -1.890 |
RON | -1.750 |
rans | -1.722 |
rons | -1.690 |
enance | -1.671 |
Token | started |
Token ID | 2067 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
jriwal | +0.667 |
kefeller | +0.610 |
impulse | +0.594 |
turmoil | +0.560 |
reaction | +0.548 |
Neg logit contributions | |
lehem | -0.786 |
RON | -0.739 |
rans | -0.722 |
rons | -0.707 |
enance | -0.701 |
Token | at |
Token ID | 379 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
jriwal | +1.054 |
kefeller | +0.950 |
impulse | +0.927 |
turmoil | +0.870 |
reaction | +0.852 |
Neg logit contributions | |
lehem | -1.406 |
RON | -1.328 |
rans | -1.298 |
rons | -1.272 |
enance | -1.264 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
lehem | +2.221 |
RON | +2.076 |
rans | +2.045 |
rons | +1.991 |
enance | +1.967 |
Neg logit contributions | |
jriwal | -2.012 |
kefeller | -1.865 |
impulse | -1.795 |
turmoil | -1.692 |
reaction | -1.648 |
Token | pl |
Token ID | 489 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
lehem | +1.517 |
RON | +1.410 |
rans | +1.392 |
rons | +1.353 |
enance | +1.335 |
Neg logit contributions | |
jriwal | -1.499 |
kefeller | -1.390 |
impulse | -1.359 |
turmoil | -1.288 |
reaction | -1.262 |
Token | a |
Token ID | 64 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
lehem | +1.084 |
RON | +0.995 |
rans | +0.983 |
rons | +0.945 |
enance | +0.932 |
Neg logit contributions | |
jriwal | -1.517 |
kefeller | -1.429 |
impulse | -1.385 |
turmoil | -1.325 |
reaction | -1.298 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
lehem | +1.269 |
RON | +1.182 |
rans | +1.166 |
rons | +1.132 |
enance | +1.119 |
Neg logit contributions | |
jriwal | -1.130 |
kefeller | -1.045 |
impulse | -1.011 |
turmoil | -0.952 |
reaction | -0.929 |
Token | t |
Token ID | 83 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
jriwal | +10.716 |
impulse | +9.608 |
kefeller | +9.601 |
inki | +9.196 |
reaction | +9.182 |
Neg logit contributions | |
lehem | -7.877 |
RON | -7.292 |
enance | -6.763 |
rons | -6.755 |
rans | -6.647 |
Token | ak |
Token ID | 461 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
lehem | +3.524 |
RON | +3.260 |
rans | +3.259 |
rons | +3.113 |
enance | +3.081 |
Neg logit contributions | |
jriwal | -3.723 |
kefeller | -3.485 |
impulse | -3.371 |
turmoil | -3.239 |
reaction | -3.149 |
Token | by |
Token ID | 416 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
jriwal | +0.943 |
kefeller | +0.864 |
impulse | +0.841 |
turmoil | +0.794 |
reaction | +0.776 |
Neg logit contributions | |
lehem | -1.076 |
RON | -1.011 |
rans | -0.989 |
rons | -0.966 |
enance | -0.958 |
Token | blocking |
Token ID | 12013 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
jriwal | +0.632 |
kefeller | +0.571 |
impulse | +0.560 |
turmoil | +0.526 |
reaction | +0.515 |
Neg logit contributions | |
lehem | -0.803 |
RON | -0.757 |
rans | -0.739 |
rons | -0.725 |
enance | -0.719 |
Token | national |
Token ID | 2260 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
jriwal | +2.244 |
kefeller | +2.035 |
impulse | +2.003 |
turmoil | +1.881 |
reaction | +1.852 |
Neg logit contributions | |
lehem | -2.616 |
RON | -2.466 |
rans | -2.388 |
rons | -2.354 |
enance | -2.323 |
Token | flagged |
Token ID | 34060 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
lehem | +0.979 |
RON | +0.925 |
rans | +0.910 |
rons | +0.891 |
enance | +0.882 |
Neg logit contributions | |
jriwal | -0.758 |
kefeller | -0.689 |
impulse | -0.658 |
turmoil | -0.616 |
reaction | -0.603 |
Token | off |
Token ID | 572 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
lehem | +0.414 |
RON | +0.392 |
rans | +0.386 |
rons | +0.378 |
enance | +0.376 |
Neg logit contributions | |
jriwal | -0.272 |
kefeller | -0.246 |
impulse | -0.236 |
turmoil | -0.219 |
reaction | -0.213 |
Token | between |
Token ID | 1022 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lehem | +0.749 |
RON | +0.708 |
rans | +0.694 |
rons | +0.682 |
enance | +0.673 |
Neg logit contributions | |
jriwal | -0.569 |
kefeller | -0.519 |
impulse | -0.499 |
turmoil | -0.469 |
reaction | -0.457 |
Token | Sar |
Token ID | 6866 |
Feature activation | +6.90e-03 |
Pos logit contributions | |
lehem | +1.505 |
RON | +1.415 |
rans | +1.385 |
rons | +1.360 |
enance | +1.337 |
Neg logit contributions | |
jriwal | -1.373 |
kefeller | -1.260 |
impulse | -1.212 |
turmoil | -1.146 |
reaction | -1.116 |
Token | ai |
Token ID | 1872 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
lehem | +0.006 |
RON | +0.006 |
rans | +0.006 |
rons | +0.006 |
enance | +0.006 |
Neg logit contributions | |
jriwal | -0.006 |
kefeller | -0.006 |
impulse | -0.006 |
turmoil | -0.005 |
reaction | -0.005 |
Token | Roh |
Token ID | 32694 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
lehem | +0.279 |
RON | +0.262 |
rans | +0.258 |
rons | +0.251 |
enance | +0.249 |
Neg logit contributions | |
jriwal | -0.229 |
kefeller | -0.210 |
impulse | -0.203 |
turmoil | -0.192 |
reaction | -0.187 |
Token | illa |
Token ID | 5049 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
jriwal | +10.753 |
kefeller | +9.706 |
impulse | +9.617 |
inki | +9.278 |
turmoil | +9.199 |
Neg logit contributions | |
lehem | -7.656 |
RON | -7.180 |
──────── | -6.616 |
enance | -6.557 |
rons | -6.546 |
Token | station |
Token ID | 4429 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
lehem | +1.417 |
RON | +1.331 |
rans | +1.308 |
rons | +1.278 |
enance | +1.263 |
Neg logit contributions | |
jriwal | -1.187 |
kefeller | -1.090 |
impulse | -1.051 |
turmoil | -0.995 |
reaction | -0.968 |
Token | in |
Token ID | 287 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
lehem | +4.986 |
RON | +4.697 |
rans | +4.604 |
rons | +4.492 |
enance | +4.440 |
Neg logit contributions | |
jriwal | -4.492 |
kefeller | -4.204 |
impulse | -3.987 |
turmoil | -3.827 |
senal | -3.681 |
Token | Delhi |
Token ID | 12517 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
jriwal | +3.298 |
kefeller | +3.000 |
impulse | +2.948 |
turmoil | +2.786 |
reaction | +2.739 |
Neg logit contributions | |
lehem | -3.687 |
RON | -3.466 |
rans | -3.377 |
rons | -3.304 |
enance | -3.284 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
jriwal | +0.479 |
kefeller | +0.440 |
impulse | +0.426 |
turmoil | +0.401 |
reaction | +0.391 |
Neg logit contributions | |
lehem | -0.592 |
RON | -0.557 |
rans | -0.545 |
rons | -0.532 |
enance | -0.528 |
Token | , |
Token ID | 11 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
jriwal | +1.344 |
kefeller | +1.214 |
impulse | +1.190 |
turmoil | +1.117 |
reaction | +1.091 |
Neg logit contributions | |
lehem | -1.931 |
RON | -1.824 |
rans | -1.789 |
rons | -1.749 |
enance | -1.739 |
Token | Senator |
Token ID | 8962 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
jriwal | +1.004 |
kefeller | +0.919 |
impulse | +0.895 |
turmoil | +0.844 |
reaction | +0.827 |
Neg logit contributions | |
lehem | -1.133 |
RON | -1.064 |
rans | -1.040 |
rons | -1.017 |
enance | -1.008 |
Token | Ted |
Token ID | 11396 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
lehem | +3.515 |
RON | +3.341 |
rans | +3.253 |
enance | +3.198 |
rons | +3.188 |
Neg logit contributions | |
jriwal | -3.491 |
kefeller | -3.188 |
impulse | -3.046 |
turmoil | -2.856 |
senal | -2.834 |
Token | Cruz |
Token ID | 8742 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
lehem | +2.744 |
RON | +2.568 |
rans | +2.502 |
rons | +2.459 |
enance | +2.436 |
Neg logit contributions | |
jriwal | -3.455 |
kefeller | -3.206 |
impulse | -3.123 |
turmoil | -2.977 |
reaction | -2.913 |
Token | ( |
Token ID | 357 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
jriwal | +2.456 |
kefeller | +2.248 |
impulse | +2.215 |
turmoil | +2.101 |
reaction | +2.068 |
Neg logit contributions | |
lehem | -2.772 |
RON | -2.592 |
rans | -2.529 |
rons | -2.468 |
enance | -2.450 |
Token | R |
Token ID | 49 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
lehem | +0.716 |
RON | +0.667 |
rans | +0.645 |
rons | +0.625 |
enance | +0.619 |
Neg logit contributions | |
jriwal | -0.979 |
kefeller | -0.910 |
impulse | -0.893 |
turmoil | -0.852 |
reaction | -0.836 |
Token | - |
Token ID | 12 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
jriwal | +5.981 |
kefeller | +5.600 |
impulse | +5.383 |
reaction | +5.106 |
turmoil | +4.966 |
Neg logit contributions | |
lehem | -12.047 |
RON | -11.295 |
rans | -10.973 |
enance | -10.892 |
rons | -10.826 |
Token | TX |
Token ID | 29551 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
lehem | +4.909 |
RON | +4.737 |
rans | +4.578 |
rons | +4.414 |
enance | +4.407 |
Neg logit contributions | |
jriwal | -4.682 |
kefeller | -4.197 |
impulse | -4.146 |
turmoil | -3.867 |
reaction | -3.738 |
Token | ), |
Token ID | 828 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
jriwal | +1.983 |
kefeller | +1.839 |
impulse | +1.788 |
turmoil | +1.699 |
reaction | +1.672 |
Neg logit contributions | |
lehem | -2.030 |
RON | -1.900 |
rans | -1.851 |
rons | -1.816 |
enance | -1.797 |
Token | who |
Token ID | 508 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
lehem | +0.212 |
RON | +0.200 |
rans | +0.195 |
rons | +0.191 |
enance | +0.190 |
Neg logit contributions | |
jriwal | -0.178 |
kefeller | -0.162 |
impulse | -0.156 |
turmoil | -0.147 |
reaction | -0.143 |
Token | apparently |
Token ID | 5729 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
lehem | +1.318 |
RON | +1.241 |
rans | +1.219 |
rons | +1.192 |
enance | +1.183 |
Neg logit contributions | |
jriwal | -1.158 |
kefeller | -1.062 |
impulse | -1.026 |
turmoil | -0.963 |
reaction | -0.943 |
Token | economic |
Token ID | 3034 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
jriwal | +2.511 |
kefeller | +2.281 |
impulse | +2.260 |
turmoil | +2.119 |
reaction | +2.074 |
Neg logit contributions | |
lehem | -3.521 |
RON | -3.322 |
rans | -3.227 |
rons | -3.167 |
enance | -3.148 |
Token | recovery |
Token ID | 7628 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
jriwal | +2.522 |
impulse | +2.219 |
kefeller | +2.213 |
turmoil | +2.075 |
reaction | +1.996 |
Neg logit contributions | |
lehem | -4.810 |
RON | -4.551 |
rans | -4.435 |
enance | -4.361 |
rons | -4.360 |
Token | . |
Token ID | 13 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
jriwal | +1.931 |
kefeller | +1.736 |
impulse | +1.712 |
turmoil | +1.608 |
reaction | +1.571 |
Neg logit contributions | |
lehem | -2.558 |
RON | -2.417 |
rans | -2.350 |
rons | -2.308 |
enance | -2.289 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
jriwal | +0.608 |
kefeller | +0.560 |
impulse | +0.546 |
turmoil | +0.520 |
reaction | +0.511 |
Neg logit contributions | |
lehem | -0.663 |
RON | -0.622 |
rans | -0.607 |
rons | -0.595 |
enance | -0.587 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
jriwal | +1.051 |
kefeller | +0.966 |
impulse | +0.945 |
turmoil | +0.896 |
reaction | +0.880 |
Neg logit contributions | |
lehem | -1.103 |
RON | -1.029 |
rans | -1.005 |
rons | -0.983 |
enance | -0.973 |
Token | R |
Token ID | 49 |
Feature activation | -1.04e+01 |
Pos logit contributions | |
jriwal | +1.022 |
kefeller | +0.944 |
impulse | +0.925 |
turmoil | +0.881 |
reaction | +0.866 |
Neg logit contributions | |
lehem | -0.961 |
RON | -0.887 |
rans | -0.870 |
rons | -0.851 |
enance | -0.840 |
Token | ates |
Token ID | 689 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
jriwal | +8.646 |
kefeller | +7.880 |
impulse | +7.773 |
reaction | +7.410 |
turmoil | +7.392 |
Neg logit contributions | |
lehem | -9.654 |
RON | -9.231 |
rans | -8.690 |
rons | -8.526 |
enance | -8.502 |
Token | were |
Token ID | 547 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
jriwal | +0.168 |
kefeller | +0.154 |
impulse | +0.150 |
turmoil | +0.142 |
reaction | +0.139 |
Neg logit contributions | |
lehem | -0.169 |
RON | -0.159 |
rans | -0.155 |
rons | -0.152 |
enance | -0.151 |
Token | expected |
Token ID | 2938 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
jriwal | +0.804 |
kefeller | +0.733 |
impulse | +0.710 |
turmoil | +0.666 |
reaction | +0.651 |
Neg logit contributions | |
lehem | -0.969 |
RON | -0.915 |
rans | -0.897 |
rons | -0.878 |
enance | -0.872 |
Token | to |
Token ID | 284 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
lehem | +1.264 |
RON | +1.207 |
rans | +1.190 |
rons | +1.170 |
enance | +1.156 |
Neg logit contributions | |
jriwal | -0.712 |
kefeller | -0.629 |
impulse | -0.608 |
turmoil | -0.554 |
reaction | -0.536 |
Token | rise |
Token ID | 4485 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
lehem | +0.939 |
RON | +0.891 |
rans | +0.878 |
rons | +0.859 |
enance | +0.851 |
Neg logit contributions | |
jriwal | -0.647 |
kefeller | -0.584 |
impulse | -0.560 |
turmoil | -0.522 |
reaction | -0.509 |
Token | multiplayer |
Token ID | 16913 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
jriwal | +2.939 |
kefeller | +2.644 |
impulse | +2.615 |
turmoil | +2.428 |
reaction | +2.390 |
Neg logit contributions | |
lehem | -4.659 |
RON | -4.398 |
rans | -4.322 |
rons | -4.230 |
enance | -4.204 |
Token | mayhem |
Token ID | 43744 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
jriwal | +1.632 |
kefeller | +1.476 |
impulse | +1.426 |
turmoil | +1.334 |
reaction | +1.301 |
Neg logit contributions | |
lehem | -2.212 |
RON | -2.092 |
rans | -2.047 |
rons | -2.011 |
enance | -1.994 |
Token | . |
Token ID | 13 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
jriwal | +1.772 |
kefeller | +1.607 |
impulse | +1.563 |
turmoil | +1.465 |
reaction | +1.432 |
Neg logit contributions | |
lehem | -2.374 |
RON | -2.240 |
rans | -2.192 |
rons | -2.148 |
enance | -2.132 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
jriwal | +1.300 |
kefeller | +1.199 |
impulse | +1.177 |
turmoil | +1.116 |
reaction | +1.099 |
Neg logit contributions | |
lehem | -1.341 |
RON | -1.244 |
rans | -1.219 |
rons | -1.191 |
enance | -1.184 |
Token |
|
Token ID | 198 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
jriwal | +1.485 |
kefeller | +1.364 |
impulse | +1.338 |
turmoil | +1.268 |
reaction | +1.247 |
Neg logit contributions | |
lehem | -1.598 |
RON | -1.486 |
rans | -1.452 |
rons | -1.423 |
enance | -1.407 |
Token | R |
Token ID | 49 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
jriwal | +1.504 |
kefeller | +1.391 |
impulse | +1.363 |
turmoil | +1.297 |
reaction | +1.275 |
Neg logit contributions | |
lehem | -1.294 |
RON | -1.195 |
rans | -1.167 |
rons | -1.138 |
enance | -1.128 |
Token | acing |
Token ID | 4092 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
jriwal | +7.355 |
kefeller | +6.732 |
impulse | +6.556 |
turmoil | +6.083 |
reaction | +6.065 |
Neg logit contributions | |
lehem | -10.836 |
RON | -10.150 |
rans | -9.860 |
rons | -9.620 |
enance | -9.445 |
Token | Apex |
Token ID | 49440 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
lehem | +1.701 |
RON | +1.593 |
rans | +1.554 |
rons | +1.524 |
enance | +1.512 |
Neg logit contributions | |
jriwal | -1.820 |
kefeller | -1.698 |
impulse | -1.628 |
turmoil | -1.546 |
reaction | -1.518 |
Token | is |
Token ID | 318 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
jriwal | +0.563 |
kefeller | +0.513 |
impulse | +0.498 |
turmoil | +0.468 |
reaction | +0.457 |
Neg logit contributions | |
lehem | -0.692 |
RON | -0.653 |
rans | -0.638 |
rons | -0.625 |
enance | -0.620 |
Token | targeting |
Token ID | 10822 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
jriwal | +2.975 |
kefeller | +2.690 |
impulse | +2.639 |
turmoil | +2.470 |
reaction | +2.420 |
Neg logit contributions | |
lehem | -4.067 |
RON | -3.823 |
rans | -3.737 |
rons | -3.668 |
enance | -3.638 |
Token | Windows |
Token ID | 3964 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
lehem | +1.025 |
RON | +0.977 |
rans | +0.958 |
rons | +0.936 |
enance | +0.928 |
Neg logit contributions | |
jriwal | -0.818 |
kefeller | -0.739 |
impulse | -0.704 |
turmoil | -0.666 |
reaction | -0.643 |
Token | K |
Token ID | 509 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
jriwal | +3.133 |
kefeller | +2.961 |
impulse | +2.865 |
turmoil | +2.761 |
reaction | +2.732 |
Neg logit contributions | |
lehem | -1.921 |
RON | -1.760 |
rans | -1.700 |
enance | -1.643 |
rons | -1.626 |
Token | lim |
Token ID | 2475 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
jriwal | +0.562 |
kefeller | +0.529 |
impulse | +0.522 |
turmoil | +0.501 |
reaction | +0.493 |
Neg logit contributions | |
lehem | -0.282 |
RON | -0.252 |
rans | -0.245 |
rons | -0.238 |
enance | -0.230 |
Token | enty |
Token ID | 3787 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
jriwal | +2.725 |
kefeller | +2.439 |
impulse | +2.331 |
turmoil | +2.170 |
reaction | +2.159 |
Neg logit contributions | |
lehem | -4.751 |
RON | -4.548 |
rans | -4.389 |
enance | -4.354 |
rons | -4.328 |
Token | ev |
Token ID | 1990 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
jriwal | +0.263 |
kefeller | +0.246 |
impulse | +0.244 |
turmoil | +0.235 |
reaction | +0.233 |
Neg logit contributions | |
lehem | -0.119 |
RON | -0.107 |
rans | -0.101 |
enance | -0.097 |
rons | -0.097 |
Token | / |
Token ID | 14 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
lehem | +4.859 |
RON | +4.610 |
rans | +4.495 |
rons | +4.442 |
enance | +4.377 |
Neg logit contributions | |
jriwal | -3.953 |
kefeller | -3.568 |
impulse | -3.497 |
turmoil | -3.235 |
reaction | -3.154 |
Token | R |
Token ID | 49 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
jriwal | +0.984 |
kefeller | +0.908 |
impulse | +0.885 |
turmoil | +0.839 |
reaction | +0.826 |
Neg logit contributions | |
lehem | -0.963 |
RON | -0.897 |
rans | -0.877 |
rons | -0.857 |
enance | -0.851 |
Token | IA |
Token ID | 3539 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
jriwal | +9.707 |
kefeller | +9.086 |
impulse | +8.648 |
reaction | +8.360 |
turmoil | +8.308 |
Neg logit contributions | |
lehem | -8.695 |
RON | -7.988 |
rons | -7.615 |
rans | -7.552 |
enance | -7.457 |
Token | Nov |
Token ID | 5267 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
jriwal | +0.186 |
kefeller | +0.169 |
impulse | +0.165 |
turmoil | +0.157 |
reaction | +0.153 |
Neg logit contributions | |
lehem | -0.166 |
RON | -0.155 |
rans | -0.153 |
rons | -0.146 |
enance | -0.144 |
Token | ost |
Token ID | 455 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
lehem | +0.561 |
RON | +0.519 |
rans | +0.506 |
rons | +0.491 |
enance | +0.485 |
Neg logit contributions | |
jriwal | -0.732 |
kefeller | -0.679 |
impulse | -0.662 |
turmoil | -0.634 |
reaction | -0.622 |
Token | i |
Token ID | 72 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
lehem | +0.938 |
rans | +0.882 |
RON | +0.875 |
rons | +0.830 |
enance | +0.814 |
Neg logit contributions | |
jriwal | -1.294 |
kefeller | -1.202 |
impulse | -1.152 |
senal | -1.114 |
turmoil | -1.109 |
Token | / |
Token ID | 14 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
jriwal | +2.598 |
kefeller | +2.369 |
impulse | +2.280 |
turmoil | +2.143 |
reaction | +2.086 |
Neg logit contributions | |
lehem | -4.210 |
RON | -3.975 |
rans | -3.892 |
rons | -3.841 |
enance | -3.809 |
Token | Oak |
Token ID | 9121 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
lehem | +1.916 |
RON | +1.811 |
rans | +1.776 |
rons | +1.736 |
enance | +1.704 |
Neg logit contributions | |
jriwal | -1.647 |
kefeller | -1.508 |
impulse | -1.445 |
turmoil | -1.361 |
reaction | -1.319 |
Token | sterdam |
Token ID | 22506 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
lehem | +1.814 |
RON | +1.698 |
rans | +1.669 |
rons | +1.622 |
enance | +1.581 |
Neg logit contributions | |
jriwal | -1.713 |
kefeller | -1.568 |
impulse | -1.529 |
turmoil | -1.445 |
reaction | -1.414 |
Token | , |
Token ID | 11 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
lehem | +0.103 |
RON | +0.097 |
rans | +0.095 |
rons | +0.093 |
enance | +0.092 |
Neg logit contributions | |
jriwal | -0.098 |
kefeller | -0.090 |
impulse | -0.087 |
turmoil | -0.082 |
reaction | -0.081 |
Token | a |
Token ID | 257 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
jriwal | +0.704 |
kefeller | +0.642 |
impulse | +0.624 |
turmoil | +0.586 |
reaction | +0.573 |
Neg logit contributions | |
lehem | -0.857 |
RON | -0.807 |
rans | -0.789 |
rons | -0.772 |
enance | -0.765 |
Token | how |
Token ID | 703 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
lehem | +0.529 |
RON | +0.503 |
rans | +0.494 |
rons | +0.484 |
enance | +0.478 |
Neg logit contributions | |
jriwal | -0.334 |
kefeller | -0.297 |
impulse | -0.285 |
turmoil | -0.263 |
reaction | -0.254 |
Token | - |
Token ID | 12 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
jriwal | +2.093 |
kefeller | +1.911 |
impulse | +1.865 |
turmoil | +1.759 |
reaction | +1.733 |
Neg logit contributions | |
lehem | -2.441 |
RON | -2.290 |
rans | -2.223 |
rons | -2.185 |
enance | -2.182 |
Token | to |
Token ID | 1462 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
lehem | +4.613 |
rans | +4.344 |
RON | +4.252 |
rons | +4.099 |
enance | +3.957 |
Neg logit contributions | |
jriwal | -6.749 |
kefeller | -6.326 |
impulse | -6.181 |
turmoil | -5.883 |
earthquake | -5.732 |
Token | about |
Token ID | 546 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
lehem | +2.653 |
RON | +2.532 |
rans | +2.484 |
rons | +2.448 |
enance | +2.405 |
Neg logit contributions | |
jriwal | -1.702 |
kefeller | -1.555 |
impulse | -1.421 |
turmoil | -1.314 |
reaction | -1.267 |
Token | opening |
Token ID | 4756 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
lehem | +0.694 |
RON | +0.665 |
rans | +0.652 |
rons | +0.638 |
enance | +0.635 |
Neg logit contributions | |
jriwal | -0.457 |
kefeller | -0.413 |
impulse | -0.391 |
turmoil | -0.365 |
reaction | -0.353 |
Token | and |
Token ID | 290 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
jriwal | +1.360 |
kefeller | +1.224 |
impulse | +1.185 |
turmoil | +1.104 |
reaction | +1.076 |
Neg logit contributions | |
lehem | -2.084 |
RON | -1.974 |
rans | -1.935 |
rons | -1.898 |
enance | -1.885 |
Token | running |
Token ID | 2491 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
jriwal | +1.999 |
kefeller | +1.751 |
impulse | +1.710 |
turmoil | +1.581 |
reaction | +1.536 |
Neg logit contributions | |
lehem | -3.997 |
RON | -3.788 |
rans | -3.711 |
rons | -3.651 |
enance | -3.626 |
Token | how |
Token ID | 703 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
jriwal | +0.852 |
kefeller | +0.774 |
impulse | +0.754 |
turmoil | +0.707 |
reaction | +0.691 |
Neg logit contributions | |
lehem | -1.125 |
RON | -1.061 |
rans | -1.038 |
rons | -1.017 |
enance | -1.009 |
Token | I |
Token ID | 314 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
jriwal | +1.665 |
kefeller | +1.491 |
impulse | +1.475 |
turmoil | +1.376 |
reaction | +1.343 |
Neg logit contributions | |
lehem | -2.529 |
RON | -2.390 |
rans | -2.337 |
rons | -2.294 |
enance | -2.270 |
Token | had |
Token ID | 550 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lehem | +2.222 |
RON | +2.081 |
rans | +2.041 |
rons | +1.994 |
enance | +1.979 |
Neg logit contributions | |
jriwal | -2.259 |
kefeller | -2.084 |
impulse | -2.012 |
turmoil | -1.909 |
reaction | -1.866 |
Token | failed |
Token ID | 4054 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
lehem | +1.569 |
RON | +1.482 |
rans | +1.456 |
rons | +1.428 |
enance | +1.421 |
Neg logit contributions | |
jriwal | -1.308 |
kefeller | -1.197 |
impulse | -1.141 |
turmoil | -1.079 |
reaction | -1.048 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
jriwal | +0.791 |
kefeller | +0.709 |
impulse | +0.690 |
turmoil | +0.641 |
reaction | +0.625 |
Neg logit contributions | |
lehem | -1.252 |
RON | -1.186 |
rans | -1.163 |
rons | -1.141 |
enance | -1.132 |
Token | realize |
Token ID | 6537 |
Feature activation | +6.89e+00 |
Pos logit contributions | |
lehem | +1.371 |
RON | +1.286 |
rans | +1.259 |
rons | +1.230 |
enance | +1.221 |
Neg logit contributions | |
jriwal | -1.361 |
kefeller | -1.256 |
impulse | -1.208 |
turmoil | -1.148 |
reaction | -1.122 |
Token | this |
Token ID | 428 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lehem | +6.441 |
RON | +6.065 |
enance | +6.019 |
rans | +5.988 |
rons | +5.860 |
Neg logit contributions | |
jriwal | -5.991 |
kefeller | -5.531 |
impulse | -4.965 |
senal | -4.955 |
inki | -4.798 |
Token | in |
Token ID | 287 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
jriwal | +1.254 |
kefeller | +1.130 |
impulse | +1.101 |
turmoil | +1.027 |
reaction | +1.002 |
Neg logit contributions | |
lehem | -1.845 |
RON | -1.745 |
rans | -1.709 |
rons | -1.677 |
enance | -1.663 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
jriwal | +2.639 |
kefeller | +2.364 |
impulse | +2.359 |
turmoil | +2.200 |
reaction | +2.159 |
Neg logit contributions | |
lehem | -4.013 |
RON | -3.794 |
rans | -3.718 |
rons | -3.638 |
enance | -3.619 |
Token | very |
Token ID | 845 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
jriwal | +0.165 |
kefeller | +0.150 |
impulse | +0.144 |
turmoil | +0.134 |
reaction | +0.131 |
Neg logit contributions | |
lehem | -0.219 |
RON | -0.206 |
rans | -0.202 |
rons | -0.198 |
enance | -0.197 |
Token | beginning |
Token ID | 3726 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
jriwal | +2.252 |
kefeller | +2.028 |
impulse | +2.007 |
turmoil | +1.880 |
reaction | +1.837 |
Neg logit contributions | |
lehem | -3.117 |
RON | -2.948 |
rans | -2.885 |
rons | -2.823 |
enance | -2.799 |
Token | -, |
Token ID | 20995 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
lehem | +1.645 |
RON | +1.553 |
rans | +1.520 |
rons | +1.491 |
enance | +1.474 |
Neg logit contributions | |
jriwal | -1.277 |
kefeller | -1.154 |
impulse | -1.123 |
turmoil | -1.056 |
reaction | -1.029 |
Token | five |
Token ID | 1936 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
lehem | +4.386 |
RON | +4.079 |
rans | +4.038 |
rons | +3.958 |
enance | +3.881 |
Neg logit contributions | |
jriwal | -3.828 |
kefeller | -3.505 |
impulse | -3.316 |
turmoil | -3.172 |
reaction | -3.082 |
Token | -, |
Token ID | 20995 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
lehem | +1.616 |
RON | +1.524 |
rans | +1.493 |
rons | +1.464 |
enance | +1.444 |
Neg logit contributions | |
jriwal | -1.324 |
kefeller | -1.202 |
impulse | -1.168 |
turmoil | -1.101 |
reaction | -1.074 |
Token | and |
Token ID | 290 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
lehem | +4.190 |
RON | +3.937 |
rans | +3.905 |
rons | +3.787 |
enance | +3.711 |
Neg logit contributions | |
jriwal | -3.613 |
kefeller | -3.278 |
impulse | -3.105 |
turmoil | -2.965 |
reaction | -2.855 |
Token | ten |
Token ID | 3478 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
jriwal | +1.613 |
kefeller | +1.465 |
impulse | +1.437 |
turmoil | +1.345 |
reaction | +1.321 |
Neg logit contributions | |
lehem | -2.211 |
RON | -2.084 |
rans | -2.030 |
rons | -1.996 |
enance | -1.985 |
Token | - |
Token ID | 12 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
lehem | +3.376 |
RON | +3.200 |
rans | +3.149 |
rons | +3.102 |
enance | +3.034 |
Neg logit contributions | |
jriwal | -2.530 |
kefeller | -2.260 |
impulse | -2.183 |
turmoil | -2.059 |
reaction | -1.992 |
Token | cent |
Token ID | 1087 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
lehem | +6.428 |
rans | +5.980 |
RON | +5.975 |
rons | +5.834 |
enance | +5.568 |
Neg logit contributions | |
jriwal | -6.437 |
kefeller | -5.806 |
impulse | -5.692 |
turmoil | -5.452 |
reaction | -5.255 |
Token | pieces |
Token ID | 5207 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
lehem | +5.047 |
RON | +4.790 |
rans | +4.752 |
rons | +4.739 |
enance | +4.592 |
Neg logit contributions | |
jriwal | -3.775 |
kefeller | -3.408 |
impulse | -3.183 |
turmoil | -3.004 |
senal | -2.950 |
Token | of |
Token ID | 286 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
jriwal | +0.769 |
kefeller | +0.700 |
impulse | +0.683 |
turmoil | +0.642 |
reaction | +0.628 |
Neg logit contributions | |
lehem | -0.978 |
RON | -0.920 |
rans | -0.899 |
rons | -0.880 |
enance | -0.873 |
Token | an |
Token ID | 281 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
lehem | +2.044 |
RON | +1.937 |
rans | +1.906 |
rons | +1.868 |
enance | +1.854 |
Neg logit contributions | |
jriwal | -1.591 |
kefeller | -1.422 |
impulse | -1.365 |
turmoil | -1.287 |
reaction | -1.247 |
Token | alloy |
Token ID | 36186 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
lehem | +0.973 |
RON | +0.927 |
rans | +0.913 |
rons | +0.893 |
enance | +0.886 |
Neg logit contributions | |
jriwal | -0.638 |
kefeller | -0.572 |
impulse | -0.545 |
turmoil | -0.515 |
reaction | -0.499 |
Token | ; |
Token ID | 26 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
jriwal | +0.211 |
kefeller | +0.193 |
impulse | +0.187 |
turmoil | +0.176 |
reaction | +0.172 |
Neg logit contributions | |
lehem | -0.258 |
RON | -0.243 |
rans | -0.238 |
rons | -0.232 |
enance | -0.231 |
Token | the |
Token ID | 262 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
lehem | +1.714 |
RON | +1.615 |
rans | +1.587 |
rons | +1.550 |
enance | +1.541 |
Neg logit contributions | |
jriwal | -1.450 |
kefeller | -1.317 |
impulse | -1.269 |
turmoil | -1.202 |
reaction | -1.173 |
Token | Vin |
Token ID | 11820 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
lehem | +0.001 |
RON | +0.001 |
rans | +0.001 |
rons | +0.001 |
enance | +0.001 |
Neg logit contributions | |
jriwal | -0.001 |
kefeller | -0.001 |
impulse | -0.001 |
turmoil | -0.001 |
reaction | -0.001 |
Token | cci |
Token ID | 35764 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
lehem | +2.265 |
RON | +2.126 |
rans | +2.092 |
rons | +2.045 |
enance | +2.011 |
Neg logit contributions | |
jriwal | -1.998 |
kefeller | -1.815 |
impulse | -1.774 |
turmoil | -1.681 |
reaction | -1.641 |
Token | La |
Token ID | 4689 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
lehem | +0.464 |
RON | +0.437 |
rans | +0.428 |
rons | +0.419 |
enance | +0.415 |
Neg logit contributions | |
jriwal | -0.409 |
kefeller | -0.373 |
impulse | -0.362 |
turmoil | -0.342 |
reaction | -0.335 |
Token | Plant |
Token ID | 16561 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
lehem | +0.195 |
RON | +0.183 |
rans | +0.178 |
rons | +0.174 |
enance | +0.173 |
Neg logit contributions | |
jriwal | -0.186 |
kefeller | -0.170 |
impulse | -0.166 |
turmoil | -0.157 |
reaction | -0.154 |
Token | aci |
Token ID | 32009 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
lehem | +5.791 |
RON | +5.448 |
rans | +5.415 |
rons | +5.287 |
enance | +5.211 |
Neg logit contributions | |
jriwal | -6.706 |
kefeller | -6.192 |
impulse | -5.960 |
turmoil | -5.677 |
reaction | -5.560 |
Token | ón |
Token ID | 18840 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
lehem | +2.104 |
RON | +1.975 |
rans | +1.942 |
rons | +1.886 |
enance | +1.873 |
Neg logit contributions | |
jriwal | -2.380 |
kefeller | -2.183 |
impulse | -2.120 |
turmoil | -2.019 |
reaction | -1.981 |
Token | del |
Token ID | 1619 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
lehem | +0.107 |
RON | +0.101 |
rans | +0.099 |
rons | +0.097 |
enance | +0.096 |
Neg logit contributions | |
jriwal | -0.080 |
kefeller | -0.072 |
impulse | -0.070 |
turmoil | -0.065 |
reaction | -0.064 |
Token | Sur |
Token ID | 4198 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
jriwal | +0.953 |
kefeller | +0.876 |
impulse | +0.858 |
turmoil | +0.812 |
reaction | +0.796 |
Neg logit contributions | |
lehem | -0.999 |
RON | -0.935 |
rans | -0.913 |
rons | -0.892 |
enance | -0.885 |
Token | on |
Token ID | 319 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
jriwal | +1.120 |
kefeller | +1.013 |
impulse | +0.990 |
turmoil | +0.923 |
reaction | +0.901 |
Neg logit contributions | |
lehem | -1.610 |
RON | -1.525 |
rans | -1.486 |
rons | -1.458 |
enance | -1.445 |
Token | For |
Token ID | 1890 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
lehem | +0.134 |
RON | +0.125 |
rans | +0.122 |
rons | +0.119 |
enance | +0.117 |
Neg logit contributions | |
jriwal | -0.155 |
kefeller | -0.143 |
impulse | -0.140 |
turmoil | -0.133 |
reaction | -0.131 |
Token | more |
Token ID | 517 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
jriwal | +0.474 |
kefeller | +0.431 |
impulse | +0.418 |
turmoil | +0.392 |
reaction | +0.382 |
Neg logit contributions | |
lehem | -0.620 |
RON | -0.584 |
rans | -0.572 |
rons | -0.561 |
enance | -0.556 |
Token | information |
Token ID | 1321 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
jriwal | +2.613 |
kefeller | +2.290 |
impulse | +2.244 |
turmoil | +2.077 |
reaction | +2.033 |
Neg logit contributions | |
lehem | -5.030 |
RON | -4.773 |
rans | -4.682 |
rons | -4.594 |
enance | -4.569 |
Token | on |
Token ID | 319 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
jriwal | +0.848 |
kefeller | +0.768 |
impulse | +0.745 |
turmoil | +0.696 |
reaction | +0.678 |
Neg logit contributions | |
lehem | -1.185 |
RON | -1.119 |
rans | -1.096 |
rons | -1.075 |
enance | -1.067 |
Token | O |
Token ID | 440 |
Feature activation | -6.08e+00 |
Pos logit contributions | |
jriwal | +1.967 |
kefeller | +1.775 |
impulse | +1.748 |
turmoil | +1.644 |
reaction | +1.610 |
Neg logit contributions | |
lehem | -2.688 |
RON | -2.530 |
rans | -2.474 |
rons | -2.428 |
enance | -2.412 |
Token | VD |
Token ID | 8898 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
jriwal | +5.750 |
kefeller | +5.308 |
impulse | +5.204 |
turmoil | +4.951 |
reaction | +4.873 |
Neg logit contributions | |
lehem | -5.228 |
RON | -4.830 |
rans | -4.748 |
enance | -4.639 |
rons | -4.572 |
Token | - |
Token ID | 12 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
lehem | +7.467 |
RON | +7.268 |
rans | +7.099 |
rons | +6.907 |
enance | +6.707 |
Neg logit contributions | |
jriwal | -5.385 |
kefeller | -4.998 |
impulse | -4.696 |
turmoil | -4.236 |
earthquake | -4.124 |
Token | Info |
Token ID | 12360 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
lehem | +5.424 |
RON | +5.182 |
rans | +5.026 |
rons | +4.868 |
enance | +4.743 |
Neg logit contributions | |
jriwal | -5.730 |
kefeller | -5.292 |
impulse | -5.191 |
turmoil | -4.859 |
earthquake | -4.762 |
Token | , |
Token ID | 11 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
jriwal | +0.068 |
kefeller | +0.062 |
impulse | +0.060 |
turmoil | +0.056 |
reaction | +0.055 |
Neg logit contributions | |
lehem | -0.078 |
RON | -0.073 |
rans | -0.072 |
rons | -0.070 |
enance | -0.069 |
Token | read |
Token ID | 1100 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
jriwal | +0.410 |
kefeller | +0.377 |
impulse | +0.367 |
turmoil | +0.347 |
reaction | +0.339 |
Neg logit contributions | |
lehem | -0.439 |
RON | -0.412 |
rans | -0.403 |
rons | -0.394 |
enance | -0.390 |
Token | this |
Token ID | 428 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
jriwal | +0.127 |
kefeller | +0.116 |
impulse | +0.112 |
turmoil | +0.106 |
reaction | +0.103 |
Neg logit contributions | |
lehem | -0.156 |
RON | -0.147 |
rans | -0.144 |
rons | -0.141 |
enance | -0.140 |
Token | create |
Token ID | 2251 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
jriwal | +2.161 |
kefeller | +1.960 |
impulse | +1.915 |
turmoil | +1.795 |
reaction | +1.755 |
Neg logit contributions | |
lehem | -2.917 |
RON | -2.755 |
rans | -2.693 |
rons | -2.637 |
enance | -2.619 |
Token | a |
Token ID | 257 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
lehem | +1.916 |
RON | +1.801 |
rans | +1.768 |
rons | +1.745 |
enance | +1.726 |
Neg logit contributions | |
jriwal | -1.330 |
kefeller | -1.200 |
impulse | -1.139 |
turmoil | -1.037 |
senal | -1.025 |
Token | reason |
Token ID | 1738 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
lehem | +1.080 |
RON | +1.020 |
rans | +1.003 |
rons | +0.980 |
enance | +0.968 |
Neg logit contributions | |
jriwal | -0.749 |
kefeller | -0.671 |
impulse | -0.641 |
turmoil | -0.590 |
reaction | -0.572 |
Token | for |
Token ID | 329 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
jriwal | +0.153 |
kefeller | +0.137 |
impulse | +0.131 |
turmoil | +0.121 |
reaction | +0.117 |
Neg logit contributions | |
lehem | -0.272 |
RON | -0.258 |
rans | -0.253 |
rons | -0.249 |
enance | -0.247 |
Token | her |
Token ID | 607 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
jriwal | +0.539 |
kefeller | +0.489 |
impulse | +0.469 |
turmoil | +0.434 |
reaction | +0.424 |
Neg logit contributions | |
lehem | -0.789 |
RON | -0.747 |
rans | -0.732 |
rons | -0.720 |
enance | -0.714 |
Token | termination |
Token ID | 19883 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
lehem | +0.925 |
RON | +0.887 |
rans | +0.869 |
rons | +0.857 |
enance | +0.851 |
Neg logit contributions | |
jriwal | -0.502 |
kefeller | -0.454 |
impulse | -0.414 |
turmoil | -0.377 |
senal | -0.362 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
lehem | +2.619 |
RON | +2.465 |
rans | +2.421 |
rons | +2.361 |
enance | +2.347 |
Neg logit contributions | |
jriwal | -2.308 |
kefeller | -2.139 |
impulse | -2.032 |
turmoil | -1.908 |
senal | -1.857 |
Token |
|
Token ID | 198 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
jriwal | +0.203 |
kefeller | +0.187 |
impulse | +0.183 |
turmoil | +0.173 |
reaction | +0.170 |
Neg logit contributions | |
lehem | -0.205 |
RON | -0.192 |
rans | -0.187 |
rons | -0.183 |
enance | -0.182 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
jriwal | +0.377 |
kefeller | +0.347 |
impulse | +0.338 |
turmoil | +0.320 |
reaction | +0.314 |
Neg logit contributions | |
lehem | -0.381 |
RON | -0.357 |
rans | -0.348 |
rons | -0.340 |
enance | -0.337 |
Token | � |
Token ID | 447 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
jriwal | +0.162 |
kefeller | +0.150 |
impulse | +0.147 |
turmoil | +0.139 |
reaction | +0.137 |
Neg logit contributions | |
lehem | -0.146 |
RON | -0.136 |
rans | -0.132 |
rons | -0.129 |
enance | -0.128 |
Token | � |
Token ID | 250 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
jriwal | +1.278 |
kefeller | +1.187 |
impulse | +1.162 |
turmoil | +1.107 |
reaction | +1.088 |
Neg logit contributions | |
lehem | -1.013 |
RON | -0.940 |
rans | -0.914 |
rons | -0.888 |
enance | -0.880 |
Token | is |
Token ID | 318 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
lehem | +0.035 |
RON | +0.033 |
rans | +0.033 |
rons | +0.032 |
enance | +0.032 |
Neg logit contributions | |
jriwal | -0.028 |
kefeller | -0.026 |
impulse | -0.025 |
turmoil | -0.023 |
reaction | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
jriwal | +1.849 |
kefeller | +1.675 |
impulse | +1.630 |
turmoil | +1.529 |
reaction | +1.495 |
Neg logit contributions | |
lehem | -2.552 |
RON | -2.410 |
rans | -2.358 |
rons | -2.312 |
enance | -2.292 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
lehem | +0.282 |
RON | +0.266 |
rans | +0.262 |
rons | +0.256 |
enance | +0.255 |
Neg logit contributions | |
jriwal | -0.219 |
kefeller | -0.199 |
impulse | -0.192 |
turmoil | -0.179 |
reaction | -0.174 |
Token | documents |
Token ID | 4963 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
lehem | +0.023 |
RON | +0.022 |
rans | +0.022 |
rons | +0.021 |
enance | +0.021 |
Neg logit contributions | |
jriwal | -0.014 |
kefeller | -0.013 |
impulse | -0.012 |
turmoil | -0.011 |
reaction | -0.011 |
Token | may |
Token ID | 743 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
lehem | +1.446 |
RON | +1.355 |
rans | +1.330 |
rons | +1.303 |
enance | +1.294 |
Neg logit contributions | |
jriwal | -1.416 |
kefeller | -1.298 |
impulse | -1.253 |
turmoil | -1.178 |
reaction | -1.155 |
Token | reveal |
Token ID | 7766 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
lehem | +3.574 |
RON | +3.364 |
rans | +3.340 |
rons | +3.254 |
enance | +3.213 |
Neg logit contributions | |
jriwal | -3.135 |
kefeller | -2.887 |
impulse | -2.691 |
senal | -2.547 |
turmoil | -2.528 |
Token | the |
Token ID | 262 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
lehem | +3.419 |
RON | +3.253 |
rans | +3.206 |
enance | +3.141 |
rons | +3.137 |
Neg logit contributions | |
jriwal | -2.251 |
kefeller | -1.983 |
impulse | -1.885 |
senal | -1.715 |
turmoil | -1.699 |
Token | kinds |
Token ID | 6982 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
lehem | +0.040 |
RON | +0.038 |
rans | +0.037 |
rons | +0.036 |
enance | +0.036 |
Neg logit contributions | |
jriwal | -0.025 |
kefeller | -0.022 |
impulse | -0.021 |
turmoil | -0.020 |
reaction | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
lehem | +0.312 |
RON | +0.294 |
rans | +0.287 |
rons | +0.280 |
enance | +0.278 |
Neg logit contributions | |
jriwal | -0.325 |
kefeller | -0.300 |
impulse | -0.291 |
turmoil | -0.275 |
reaction | -0.269 |
Token | pressure |
Token ID | 3833 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
lehem | +2.468 |
RON | +2.361 |
rans | +2.325 |
rons | +2.281 |
enance | +2.272 |
Neg logit contributions | |
jriwal | -1.381 |
kefeller | -1.213 |
impulse | -1.119 |
senal | -1.020 |
turmoil | -1.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
jriwal | +2.720 |
kefeller | +2.388 |
impulse | +2.344 |
turmoil | +2.156 |
reaction | +2.104 |
Neg logit contributions | |
lehem | -5.869 |
RON | -5.575 |
rans | -5.473 |
rons | -5.352 |
enance | -5.341 |
Token | We |
Token ID | 1135 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
jriwal | +0.069 |
kefeller | +0.064 |
impulse | +0.062 |
turmoil | +0.059 |
reaction | +0.058 |
Neg logit contributions | |
lehem | -0.061 |
RON | -0.057 |
rans | -0.055 |
rons | -0.054 |
enance | -0.054 |
Token | pay |
Token ID | 1414 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
lehem | +2.867 |
RON | +2.684 |
rans | +2.630 |
rons | +2.576 |
enance | +2.543 |
Neg logit contributions | |
jriwal | -2.843 |
kefeller | -2.631 |
impulse | -2.552 |
turmoil | -2.420 |
reaction | -2.358 |
Token | for |
Token ID | 329 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
jriwal | +2.104 |
impulse | +1.734 |
kefeller | +1.732 |
turmoil | +1.596 |
reaction | +1.590 |
Neg logit contributions | |
lehem | -4.866 |
RON | -4.633 |
rans | -4.626 |
rons | -4.538 |
enance | -4.408 |
Token | your |
Token ID | 534 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
jriwal | +1.567 |
kefeller | +1.487 |
impulse | +1.397 |
turmoil | +1.301 |
reaction | +1.271 |
Neg logit contributions | |
lehem | -1.932 |
RON | -1.801 |
rans | -1.745 |
rons | -1.728 |
enance | -1.709 |
Token | stories |
Token ID | 3923 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
lehem | +0.335 |
RON | +0.313 |
rans | +0.302 |
rons | +0.297 |
enance | +0.296 |
Neg logit contributions | |
jriwal | -0.301 |
kefeller | -0.281 |
impulse | -0.267 |
turmoil | -0.250 |
reaction | -0.245 |
Token | ! |
Token ID | 0 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
jriwal | +3.545 |
kefeller | +3.227 |
impulse | +3.187 |
turmoil | +3.016 |
reaction | +2.950 |
Neg logit contributions | |
lehem | -4.465 |
RON | -4.141 |
rans | -4.071 |
rons | -3.990 |
enance | -3.943 |
Token | Do |
Token ID | 2141 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
lehem | +0.880 |
RON | +0.811 |
rans | +0.786 |
rons | +0.761 |
enance | +0.759 |
Neg logit contributions | |
jriwal | -1.308 |
kefeller | -1.221 |
impulse | -1.193 |
turmoil | -1.142 |
reaction | -1.123 |
Token | you |
Token ID | 345 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
lehem | +0.471 |
RON | +0.442 |
rans | +0.430 |
rons | +0.421 |
enance | +0.416 |
Neg logit contributions | |
jriwal | -0.469 |
kefeller | -0.430 |
impulse | -0.420 |
turmoil | -0.398 |
reaction | -0.388 |
Token | have |
Token ID | 423 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
lehem | +1.469 |
RON | +1.365 |
rans | +1.326 |
rons | +1.290 |
enance | +1.277 |
Neg logit contributions | |
jriwal | -1.867 |
kefeller | -1.737 |
impulse | -1.695 |
turmoil | -1.614 |
reaction | -1.587 |
Token | a |
Token ID | 257 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
lehem | +1.381 |
RON | +1.314 |
rans | +1.287 |
enance | +1.255 |
rons | +1.244 |
Neg logit contributions | |
jriwal | -1.183 |
kefeller | -1.091 |
impulse | -1.035 |
turmoil | -0.960 |
reaction | -0.955 |
Token | story |
Token ID | 1621 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
lehem | +1.009 |
RON | +0.957 |
rans | +0.941 |
rons | +0.926 |
enance | +0.919 |
Neg logit contributions | |
jriwal | -0.505 |
kefeller | -0.441 |
impulse | -0.428 |
turmoil | -0.395 |
reaction | -0.384 |
Token | [ |
Token ID | 685 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
lehem | +1.549 |
RON | +1.457 |
rans | +1.426 |
rons | +1.397 |
enance | +1.379 |
Neg logit contributions | |
jriwal | -1.468 |
kefeller | -1.350 |
impulse | -1.309 |
turmoil | -1.240 |
reaction | -1.212 |
Token | feel |
Token ID | 36410 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
lehem | +0.532 |
RON | +0.494 |
rans | +0.480 |
rons | +0.466 |
enance | +0.462 |
Neg logit contributions | |
jriwal | -0.677 |
kefeller | -0.630 |
impulse | -0.616 |
turmoil | -0.587 |
reaction | -0.577 |
Token | ] |
Token ID | 60 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
jriwal | +1.717 |
kefeller | +1.588 |
impulse | +1.563 |
turmoil | +1.487 |
reaction | +1.463 |
Neg logit contributions | |
lehem | -1.463 |
RON | -1.357 |
rans | -1.317 |
rons | -1.284 |
enance | -1.270 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
lehem | +0.642 |
RON | +0.608 |
rans | +0.596 |
rons | +0.583 |
enance | +0.579 |
Neg logit contributions | |
jriwal | -0.485 |
kefeller | -0.441 |
impulse | -0.425 |
turmoil | -0.398 |
reaction | -0.388 |
Token | little |
Token ID | 1310 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
lehem | +1.198 |
RON | +1.134 |
rans | +1.113 |
rons | +1.083 |
enance | +1.075 |
Neg logit contributions | |
jriwal | -0.940 |
kefeller | -0.857 |
impulse | -0.819 |
turmoil | -0.771 |
reaction | -0.747 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
jriwal | +1.783 |
kefeller | +1.601 |
impulse | +1.582 |
turmoil | +1.478 |
reaction | +1.443 |
Neg logit contributions | |
lehem | -2.579 |
RON | -2.430 |
rans | -2.378 |
rons | -2.333 |
enance | -2.310 |
Token | like |
Token ID | 588 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
lehem | +2.120 |
RON | +2.014 |
rans | +1.981 |
rons | +1.937 |
enance | +1.935 |
Neg logit contributions | |
jriwal | -1.494 |
kefeller | -1.365 |
impulse | -1.288 |
turmoil | -1.203 |
reaction | -1.173 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
lehem | +0.082 |
RON | +0.078 |
rans | +0.076 |
rons | +0.074 |
enance | +0.074 |
Neg logit contributions | |
jriwal | -0.071 |
kefeller | -0.065 |
impulse | -0.064 |
turmoil | -0.060 |
reaction | -0.059 |
Token | spinning |
Token ID | 19493 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
lehem | +1.256 |
RON | +1.192 |
rans | +1.168 |
rons | +1.142 |
enance | +1.135 |
Neg logit contributions | |
jriwal | -0.848 |
kefeller | -0.767 |
impulse | -0.730 |
turmoil | -0.679 |
reaction | -0.656 |
Token | cup |
Token ID | 6508 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
jriwal | +2.253 |
kefeller | +2.012 |
impulse | +1.971 |
turmoil | +1.830 |
reaction | +1.787 |
Neg logit contributions | |
lehem | -3.632 |
RON | -3.439 |
rans | -3.371 |
rons | -3.314 |
enance | -3.289 |
Token | at |
Token ID | 379 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
lehem | +4.350 |
RON | +4.083 |
rans | +4.051 |
rons | +3.923 |
enance | +3.860 |
Neg logit contributions | |
jriwal | -4.373 |
kefeller | -4.049 |
impulse | -3.864 |
turmoil | -3.666 |
senal | -3.546 |
Token | a |
Token ID | 257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
jriwal | +1.695 |
kefeller | +1.527 |
impulse | +1.487 |
turmoil | +1.387 |
reaction | +1.354 |
Neg logit contributions | |
lehem | -2.544 |
RON | -2.407 |
rans | -2.356 |
rons | -2.312 |
enance | -2.295 |
Token | little |
Token ID | 1310 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
lehem | +1.279 |
RON | +1.210 |
rans | +1.185 |
rons | +1.163 |
enance | +1.152 |
Neg logit contributions | |
jriwal | -0.867 |
kefeller | -0.781 |
impulse | -0.741 |
turmoil | -0.694 |
reaction | -0.670 |
Token | fir |
Token ID | 37979 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
jriwal | +1.891 |
kefeller | +1.709 |
impulse | +1.654 |
turmoil | +1.546 |
reaction | +1.508 |
Neg logit contributions | |
lehem | -2.704 |
RON | -2.557 |
rans | -2.504 |
rons | -2.457 |
enance | -2.439 |
Token | mer |
Token ID | 647 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
lehem | +1.913 |
RON | +1.810 |
rans | +1.787 |
rons | +1.750 |
enance | +1.735 |
Neg logit contributions | |
jriwal | -1.147 |
kefeller | -1.024 |
impulse | -0.984 |
turmoil | -0.914 |
reaction | -0.886 |
Token | in |
Token ID | 287 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
jriwal | +1.630 |
kefeller | +1.481 |
impulse | +1.437 |
turmoil | +1.349 |
reaction | +1.317 |
Neg logit contributions | |
lehem | -2.128 |
RON | -2.007 |
rans | -1.965 |
rons | -1.925 |
enance | -1.911 |
Token | texture |
Token ID | 11743 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
jriwal | +2.483 |
kefeller | +2.228 |
impulse | +2.156 |
turmoil | +2.004 |
reaction | +1.951 |
Neg logit contributions | |
lehem | -3.936 |
RON | -3.728 |
rans | -3.655 |
rons | -3.587 |
enance | -3.563 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
lehem | +1.615 |
RON | +1.515 |
rans | +1.494 |
rons | +1.461 |
enance | +1.449 |
Neg logit contributions | |
jriwal | -1.373 |
kefeller | -1.266 |
impulse | -1.212 |
turmoil | -1.139 |
reaction | -1.101 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
lehem | +0.174 |
RON | +0.162 |
rans | +0.158 |
rons | +0.154 |
enance | +0.153 |
Neg logit contributions | |
jriwal | -0.189 |
kefeller | -0.175 |
impulse | -0.171 |
turmoil | -0.162 |
reaction | -0.159 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
jriwal | +0.197 |
kefeller | +0.182 |
impulse | +0.177 |
turmoil | +0.168 |
reaction | +0.164 |
Neg logit contributions | |
lehem | -0.197 |
RON | -0.185 |
rans | -0.180 |
rons | -0.176 |
enance | -0.174 |
Token | Sun |
Token ID | 16012 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
jriwal | +0.026 |
kefeller | +0.024 |
impulse | +0.024 |
turmoil | +0.023 |
reaction | +0.022 |
Neg logit contributions | |
lehem | -0.023 |
RON | -0.021 |
rans | -0.021 |
rons | -0.020 |
enance | -0.020 |
Token | flower |
Token ID | 25547 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
jriwal | +0.090 |
kefeller | +0.083 |
impulse | +0.081 |
turmoil | +0.077 |
reaction | +0.076 |
Neg logit contributions | |
lehem | -0.078 |
RON | -0.073 |
rans | -0.071 |
rons | -0.069 |
enance | -0.068 |
Token | isn |
Token ID | 2125 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
jriwal | +1.570 |
kefeller | +1.430 |
impulse | +1.401 |
turmoil | +1.320 |
reaction | +1.294 |
Neg logit contributions | |
lehem | -1.858 |
RON | -1.745 |
rans | -1.703 |
rons | -1.669 |
enance | -1.655 |
Token | � |
Token ID | 447 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
jriwal | +3.357 |
kefeller | +3.103 |
impulse | +3.046 |
turmoil | +2.900 |
reaction | +2.873 |
Neg logit contributions | |
lehem | -3.448 |
RON | -3.158 |
rans | -3.080 |
rons | -3.042 |
enance | -2.982 |
Token | � |
Token ID | 247 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
jriwal | +1.643 |
kefeller | +1.536 |
impulse | +1.516 |
turmoil | +1.455 |
reaction | +1.434 |
Neg logit contributions | |
lehem | -0.952 |
RON | -0.862 |
rans | -0.832 |
rons | -0.810 |
enance | -0.793 |
Token | t |
Token ID | 83 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
jriwal | +1.956 |
kefeller | +1.819 |
impulse | +1.788 |
turmoil | +1.715 |
reaction | +1.691 |
Neg logit contributions | |
lehem | -1.297 |
RON | -1.179 |
rans | -1.122 |
rons | -1.104 |
enance | -1.079 |
Token | just |
Token ID | 655 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
lehem | +4.378 |
RON | +4.168 |
rans | +4.114 |
rons | +4.002 |
enance | +3.946 |
Neg logit contributions | |
jriwal | -3.417 |
kefeller | -3.113 |
impulse | -2.911 |
turmoil | -2.734 |
reaction | -2.657 |
Token | full |
Token ID | 1336 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
lehem | +0.353 |
RON | +0.336 |
rans | +0.329 |
rons | +0.322 |
enance | +0.318 |
Neg logit contributions | |
jriwal | -0.261 |
kefeller | -0.237 |
impulse | -0.226 |
turmoil | -0.212 |
reaction | -0.206 |
Token | of |
Token ID | 286 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
jriwal | +0.920 |
kefeller | +0.845 |
impulse | +0.826 |
turmoil | +0.782 |
reaction | +0.767 |
Neg logit contributions | |
lehem | -0.974 |
RON | -0.911 |
rans | -0.889 |
rons | -0.870 |
enance | -0.862 |
Token | Typh |
Token ID | 27282 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
lehem | +2.298 |
RON | +2.200 |
rans | +2.153 |
rons | +2.122 |
enance | +2.091 |
Neg logit contributions | |
jriwal | -1.354 |
kefeller | -1.210 |
impulse | -1.127 |
turmoil | -1.039 |
reaction | -1.010 |
Token | on |
Token ID | 261 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
lehem | +2.998 |
RON | +2.742 |
rons | +2.623 |
rans | +2.620 |
enance | +2.479 |
Neg logit contributions | |
jriwal | -6.998 |
kefeller | -6.517 |
impulse | -6.393 |
turmoil | -6.211 |
reaction | -6.072 |
Token | . |
Token ID | 13 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
jriwal | +1.191 |
kefeller | +1.075 |
impulse | +1.043 |
turmoil | +0.974 |
reaction | +0.950 |
Neg logit contributions | |
lehem | -1.723 |
RON | -1.629 |
rans | -1.596 |
rons | -1.565 |
enance | -1.553 |
Token | There |
Token ID | 1318 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
lehem | +0.530 |
RON | +0.495 |
rans | +0.482 |
rons | +0.470 |
enance | +0.466 |
Neg logit contributions | |
jriwal | -0.577 |
kefeller | -0.533 |
impulse | -0.521 |
turmoil | -0.495 |
reaction | -0.486 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
lehem | +0.112 |
RON | +0.106 |
rans | +0.104 |
rons | +0.101 |
enance | +0.101 |
Neg logit contributions | |
jriwal | -0.093 |
kefeller | -0.085 |
impulse | -0.082 |
turmoil | -0.077 |
reaction | -0.075 |
Token | say |
Token ID | 910 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
lehem | +1.682 |
RON | +1.588 |
rans | +1.554 |
rons | +1.520 |
enance | +1.510 |
Neg logit contributions | |
jriwal | -1.385 |
kefeller | -1.272 |
impulse | -1.220 |
turmoil | -1.150 |
reaction | -1.121 |
Token | � |
Token ID | 564 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
lehem | +1.325 |
RON | +1.248 |
rans | +1.223 |
rons | +1.193 |
enance | +1.189 |
Neg logit contributions | |
jriwal | -1.102 |
kefeller | -1.016 |
impulse | -0.977 |
turmoil | -0.921 |
reaction | -0.897 |
Token | � |
Token ID | 246 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
lehem | +2.819 |
RON | +2.637 |
rans | +2.565 |
rons | +2.412 |
enance | +2.393 |
Neg logit contributions | |
jriwal | -5.453 |
kefeller | -5.167 |
impulse | -5.012 |
turmoil | -4.823 |
reaction | -4.748 |
Token | Yes |
Token ID | 5297 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
jriwal | +2.828 |
kefeller | +2.582 |
impulse | +2.543 |
turmoil | +2.403 |
reaction | +2.373 |
Neg logit contributions | |
lehem | -2.913 |
RON | -2.709 |
rans | -2.628 |
rons | -2.609 |
enance | -2.580 |
Token | � |
Token ID | 447 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
jriwal | +0.503 |
kefeller | +0.462 |
impulse | +0.450 |
turmoil | +0.425 |
reaction | +0.416 |
Neg logit contributions | |
lehem | -0.557 |
RON | -0.522 |
rans | -0.510 |
rons | -0.499 |
enance | -0.495 |
Token | � |
Token ID | 247 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
jriwal | +1.554 |
kefeller | +1.452 |
impulse | +1.431 |
turmoil | +1.370 |
reaction | +1.351 |
Neg logit contributions | |
lehem | -0.923 |
RON | -0.842 |
rans | -0.811 |
rons | -0.787 |
enance | -0.773 |
Token | to |
Token ID | 284 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
jriwal | +1.124 |
kefeller | +1.028 |
impulse | +1.009 |
turmoil | +0.952 |
reaction | +0.935 |
Neg logit contributions | |
lehem | -1.219 |
RON | -1.145 |
rans | -1.110 |
rons | -1.088 |
enance | -1.077 |
Token | life |
Token ID | 1204 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
lehem | +1.967 |
RON | +1.863 |
rans | +1.827 |
rons | +1.786 |
enance | +1.781 |
Neg logit contributions | |
jriwal | -1.397 |
kefeller | -1.273 |
impulse | -1.209 |
turmoil | -1.135 |
reaction | -1.107 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
jriwal | +0.534 |
kefeller | +0.488 |
impulse | +0.476 |
turmoil | +0.449 |
reaction | +0.439 |
Neg logit contributions | |
lehem | -0.614 |
RON | -0.577 |
rans | -0.564 |
rons | -0.552 |
enance | -0.547 |
Token | no |
Token ID | 645 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
lehem | +0.342 |
RON | +0.322 |
rans | +0.316 |
rons | +0.310 |
enance | +0.309 |
Neg logit contributions | |
jriwal | -0.252 |
kefeller | -0.229 |
impulse | -0.219 |
turmoil | -0.205 |
reaction | -0.200 |
Token | a |
Token ID | 257 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
jriwal | +0.729 |
kefeller | +0.660 |
impulse | +0.647 |
turmoil | +0.608 |
reaction | +0.593 |
Neg logit contributions | |
lehem | -1.002 |
RON | -0.946 |
rans | -0.924 |
rons | -0.906 |
enance | -0.901 |
Token | sc |
Token ID | 629 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
lehem | +1.156 |
RON | +1.103 |
rans | +1.087 |
rons | +1.064 |
enance | +1.054 |
Neg logit contributions | |
jriwal | -0.640 |
kefeller | -0.568 |
impulse | -0.533 |
turmoil | -0.486 |
reaction | -0.469 |
Token | uffle |
Token ID | 18137 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
lehem | +0.345 |
RON | +0.326 |
rans | +0.320 |
rons | +0.313 |
enance | +0.310 |
Neg logit contributions | |
jriwal | -0.257 |
kefeller | -0.233 |
impulse | -0.227 |
turmoil | -0.212 |
reaction | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
lehem | +0.675 |
RON | +0.638 |
rans | +0.625 |
rons | +0.612 |
enance | +0.606 |
Neg logit contributions | |
jriwal | -0.538 |
kefeller | -0.491 |
impulse | -0.471 |
turmoil | -0.441 |
reaction | -0.430 |
Token | with |
Token ID | 351 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
jriwal | +0.236 |
kefeller | +0.215 |
impulse | +0.208 |
turmoil | +0.195 |
reaction | +0.190 |
Neg logit contributions | |
lehem | -0.311 |
RON | -0.294 |
rans | -0.288 |
rons | -0.282 |
enance | -0.279 |
Token | Hew |
Token ID | 30446 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
lehem | +0.444 |
RON | +0.418 |
rans | +0.409 |
rons | +0.401 |
enance | +0.396 |
Neg logit contributions | |
jriwal | -0.379 |
kefeller | -0.347 |
impulse | -0.336 |
turmoil | -0.317 |
reaction | -0.310 |
Token | ett |
Token ID | 3087 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
jriwal | +0.409 |
kefeller | +0.366 |
impulse | +0.355 |
turmoil | +0.329 |
reaction | +0.320 |
Neg logit contributions | |
lehem | -0.669 |
RON | -0.634 |
rans | -0.622 |
rons | -0.610 |
enance | -0.606 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
lehem | +3.093 |
RON | +2.960 |
rans | +2.908 |
rons | +2.862 |
enance | +2.811 |
Neg logit contributions | |
jriwal | -2.123 |
kefeller | -1.963 |
impulse | -1.791 |
turmoil | -1.665 |
senal | -1.613 |
Token | hit |
Token ID | 2277 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
jriwal | +0.148 |
kefeller | +0.133 |
impulse | +0.128 |
turmoil | +0.120 |
reaction | +0.117 |
Neg logit contributions | |
lehem | -0.221 |
RON | -0.209 |
rans | -0.205 |
rons | -0.202 |
enance | -0.200 |
Token | in |
Token ID | 287 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
lehem | +1.546 |
RON | +1.456 |
rans | +1.431 |
rons | +1.404 |
enance | +1.387 |
Neg logit contributions | |
jriwal | -1.203 |
kefeller | -1.098 |
impulse | -1.058 |
turmoil | -0.993 |
reaction | -0.967 |
Token | the |
Token ID | 262 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
jriwal | +2.907 |
kefeller | +2.610 |
impulse | +2.563 |
turmoil | +2.395 |
reaction | +2.362 |
Neg logit contributions | |
lehem | -4.240 |
RON | -4.010 |
rans | -3.914 |
rons | -3.823 |
enance | -3.823 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
jriwal | +0.234 |
kefeller | +0.215 |
impulse | +0.210 |
turmoil | +0.198 |
reaction | +0.194 |
Neg logit contributions | |
lehem | -0.231 |
RON | -0.217 |
rans | -0.212 |
rons | -0.207 |
enance | -0.205 |
Token | Things |
Token ID | 22248 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
jriwal | +0.109 |
kefeller | +0.101 |
impulse | +0.099 |
turmoil | +0.094 |
reaction | +0.093 |
Neg logit contributions | |
lehem | -0.093 |
RON | -0.086 |
rans | -0.084 |
rons | -0.082 |
enance | -0.081 |
Token | started |
Token ID | 2067 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
jriwal | +0.207 |
kefeller | +0.188 |
impulse | +0.182 |
turmoil | +0.170 |
reaction | +0.165 |
Neg logit contributions | |
lehem | -0.268 |
RON | -0.253 |
rans | -0.249 |
rons | -0.243 |
enance | -0.240 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
jriwal | +0.597 |
kefeller | +0.532 |
impulse | +0.510 |
turmoil | +0.471 |
reaction | +0.456 |
Neg logit contributions | |
lehem | -1.040 |
RON | -0.989 |
rans | -0.973 |
rons | -0.953 |
enance | -0.946 |
Token | become |
Token ID | 1716 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
lehem | +1.528 |
RON | +1.434 |
rans | +1.418 |
rons | +1.378 |
enance | +1.361 |
Neg logit contributions | |
jriwal | -1.390 |
kefeller | -1.279 |
impulse | -1.220 |
turmoil | -1.147 |
senal | -1.124 |
Token | confusing |
Token ID | 15337 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
lehem | +2.040 |
RON | +1.933 |
rans | +1.905 |
rons | +1.863 |
enance | +1.847 |
Neg logit contributions | |
jriwal | -1.360 |
kefeller | -1.231 |
impulse | -1.159 |
turmoil | -1.070 |
reaction | -1.043 |
Token | here |
Token ID | 994 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
jriwal | +0.557 |
kefeller | +0.506 |
impulse | +0.490 |
turmoil | +0.459 |
reaction | +0.448 |
Neg logit contributions | |
lehem | -0.737 |
RON | -0.695 |
rans | -0.681 |
rons | -0.667 |
enance | -0.662 |
Token | for |
Token ID | 329 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
jriwal | +0.357 |
kefeller | +0.325 |
impulse | +0.316 |
turmoil | +0.297 |
reaction | +0.290 |
Neg logit contributions | |
lehem | -0.448 |
RON | -0.422 |
rans | -0.412 |
rons | -0.404 |
enance | -0.401 |
Token | two |
Token ID | 734 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
jriwal | +1.035 |
kefeller | +0.935 |
impulse | +0.909 |
turmoil | +0.849 |
reaction | +0.829 |
Neg logit contributions | |
lehem | -1.471 |
RON | -1.390 |
rans | -1.361 |
rons | -1.335 |
enance | -1.325 |
Token | reasons |
Token ID | 3840 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
lehem | +0.702 |
RON | +0.667 |
rans | +0.656 |
rons | +0.645 |
enance | +0.638 |
Neg logit contributions | |
jriwal | -0.442 |
kefeller | -0.397 |
impulse | -0.378 |
turmoil | -0.353 |
reaction | -0.340 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
jriwal | +0.317 |
kefeller | +0.291 |
impulse | +0.282 |
turmoil | +0.266 |
reaction | +0.260 |
Neg logit contributions | |
lehem | -0.362 |
RON | -0.340 |
rans | -0.332 |
rons | -0.325 |
enance | -0.322 |
Token | exceptions |
Token ID | 13269 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
lehem | +3.503 |
RON | +3.280 |
rans | +3.219 |
rons | +3.145 |
enance | +3.116 |
Neg logit contributions | |
jriwal | -3.623 |
kefeller | -3.354 |
impulse | -3.142 |
senal | -2.935 |
turmoil | -2.925 |
Token | , |
Token ID | 11 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
lehem | +3.893 |
RON | +3.634 |
rans | +3.568 |
enance | +3.474 |
rons | +3.456 |
Neg logit contributions | |
jriwal | -3.607 |
kefeller | -3.347 |
impulse | -3.209 |
turmoil | -2.998 |
reaction | -2.921 |
Token | public |
Token ID | 1171 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
lehem | +0.044 |
RON | +0.041 |
rans | +0.040 |
rons | +0.039 |
enance | +0.039 |
Neg logit contributions | |
jriwal | -0.037 |
kefeller | -0.034 |
impulse | -0.032 |
turmoil | -0.030 |
reaction | -0.030 |
Token | reaction |
Token ID | 6317 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
jriwal | +0.630 |
kefeller | +0.562 |
impulse | +0.542 |
turmoil | +0.501 |
reaction | +0.487 |
Neg logit contributions | |
lehem | -1.075 |
RON | -1.020 |
rans | -1.001 |
rons | -0.982 |
enance | -0.976 |
Token | was |
Token ID | 373 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
jriwal | +2.971 |
kefeller | +2.626 |
impulse | +2.580 |
turmoil | +2.416 |
reaction | +2.374 |
Neg logit contributions | |
lehem | -4.958 |
RON | -4.678 |
rans | -4.574 |
rons | -4.480 |
enance | -4.465 |
Token | swift |
Token ID | 14622 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
jriwal | +0.667 |
kefeller | +0.604 |
impulse | +0.576 |
turmoil | +0.537 |
reaction | +0.521 |
Neg logit contributions | |
lehem | -0.944 |
RON | -0.892 |
rans | -0.877 |
rons | -0.859 |
enance | -0.854 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
jriwal | +2.088 |
kefeller | +1.897 |
impulse | +1.853 |
turmoil | +1.741 |
reaction | +1.711 |
Neg logit contributions | |
lehem | -2.663 |
RON | -2.508 |
rans | -2.449 |
rons | -2.401 |
enance | -2.379 |
Token | harsh |
Token ID | 11859 |
Feature activation | -5.23e+00 |
Pos logit contributions | |
jriwal | +2.000 |
kefeller | +1.785 |
impulse | +1.747 |
turmoil | +1.620 |
reaction | +1.584 |
Neg logit contributions | |
lehem | -3.451 |
RON | -3.274 |
rans | -3.206 |
rons | -3.150 |
enance | -3.128 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
jriwal | +4.121 |
kefeller | +3.702 |
impulse | +3.693 |
turmoil | +3.468 |
reaction | +3.465 |
Neg logit contributions | |
lehem | -5.441 |
RON | -5.119 |
rans | -4.961 |
rons | -4.884 |
enance | -4.809 |
Token | The |
Token ID | 383 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
lehem | +0.452 |
RON | +0.423 |
rans | +0.412 |
rons | +0.402 |
enance | +0.399 |
Neg logit contributions | |
jriwal | -0.469 |
kefeller | -0.432 |
impulse | -0.420 |
turmoil | -0.398 |
reaction | -0.389 |
Token | D |
Token ID | 360 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
lehem | +0.176 |
RON | +0.167 |
rans | +0.164 |
rons | +0.160 |
enance | +0.159 |
Neg logit contributions | |
jriwal | -0.124 |
kefeller | -0.113 |
impulse | -0.107 |
turmoil | -0.100 |
reaction | -0.097 |
Token |
|
Token ID | 198 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
lehem | +2.526 |
RON | +2.372 |
rans | +2.313 |
enance | +2.263 |
rons | +2.261 |
Neg logit contributions | |
jriwal | -2.247 |
kefeller | -2.055 |
impulse | -1.995 |
turmoil | -1.881 |
reaction | -1.837 |
Token |
|
Token ID | 198 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
lehem | +0.004 |
RON | +0.004 |
rans | +0.003 |
rons | +0.003 |
enance | +0.003 |
Neg logit contributions | |
jriwal | -0.004 |
kefeller | -0.004 |
impulse | -0.004 |
turmoil | -0.003 |
reaction | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
lehem | +0.135 |
RON | +0.125 |
rans | +0.122 |
rons | +0.119 |
enance | +0.118 |
Neg logit contributions | |
jriwal | -0.162 |
kefeller | -0.150 |
impulse | -0.147 |
turmoil | -0.140 |
reaction | -0.138 |
Token | asure |
Token ID | 5015 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
lehem | +0.922 |
RON | +0.862 |
rans | +0.847 |
rons | +0.830 |
enance | +0.817 |
Neg logit contributions | |
jriwal | -0.907 |
kefeller | -0.831 |
impulse | -0.817 |
turmoil | -0.774 |
reaction | -0.756 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
lehem | +2.811 |
RON | +2.645 |
rans | +2.607 |
rons | +2.538 |
enance | +2.506 |
Neg logit contributions | |
jriwal | -2.678 |
kefeller | -2.468 |
impulse | -2.385 |
turmoil | -2.248 |
reaction | -2.173 |
Token | R |
Token ID | 371 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
jriwal | +0.147 |
kefeller | +0.136 |
impulse | +0.133 |
turmoil | +0.126 |
reaction | +0.124 |
Neg logit contributions | |
lehem | -0.147 |
RON | -0.137 |
rans | -0.134 |
rons | -0.131 |
enance | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
jriwal | +5.738 |
kefeller | +5.261 |
impulse | +5.234 |
turmoil | +4.887 |
reaction | +4.823 |
Neg logit contributions | |
lehem | -8.381 |
RON | -7.810 |
rans | -7.637 |
enance | -7.460 |
rons | -7.412 |
Token | H |
Token ID | 367 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
lehem | +1.278 |
RON | +1.197 |
rans | +1.160 |
rons | +1.132 |
enance | +1.122 |
Neg logit contributions | |
jriwal | -1.444 |
kefeller | -1.329 |
impulse | -1.294 |
turmoil | -1.230 |
reaction | -1.204 |
Token | ., |
Token ID | 1539 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
jriwal | +2.664 |
kefeller | +2.450 |
impulse | +2.390 |
turmoil | +2.240 |
reaction | +2.215 |
Neg logit contributions | |
lehem | -3.105 |
RON | -2.923 |
rans | -2.840 |
enance | -2.768 |
rons | -2.767 |
Token | Al |
Token ID | 978 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
lehem | +0.571 |
RON | +0.534 |
rans | +0.521 |
rons | +0.510 |
enance | +0.506 |
Neg logit contributions | |
jriwal | -0.551 |
kefeller | -0.504 |
impulse | -0.492 |
turmoil | -0.465 |
reaction | -0.454 |
Token | lee |
Token ID | 7197 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
jriwal | +1.071 |
kefeller | +0.986 |
impulse | +0.962 |
turmoil | +0.910 |
reaction | +0.893 |
Neg logit contributions | |
lehem | -1.091 |
RON | -1.022 |
rans | -0.996 |
rons | -0.973 |
enance | -0.965 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
lehem | +4.643 |
RON | +4.396 |
rons | +4.300 |
rans | +4.291 |
enance | +4.168 |
Neg logit contributions | |
jriwal | -3.844 |
kefeller | -3.548 |
impulse | -3.284 |
turmoil | -3.087 |
reaction | -2.993 |
Token | ants |
Token ID | 1187 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
lehem | +0.832 |
RON | +0.765 |
rans | +0.743 |
rons | +0.721 |
enance | +0.712 |
Neg logit contributions | |
jriwal | -1.276 |
kefeller | -1.194 |
impulse | -1.169 |
turmoil | -1.120 |
reaction | -1.101 |
Token | . |
Token ID | 13 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
lehem | +4.207 |
RON | +3.988 |
rans | +3.896 |
rons | +3.874 |
enance | +3.804 |
Neg logit contributions | |
jriwal | -3.630 |
kefeller | -3.357 |
impulse | -3.131 |
turmoil | -2.941 |
senal | -2.857 |
Token | Par |
Token ID | 10044 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
lehem | +0.468 |
RON | +0.439 |
rans | +0.427 |
rons | +0.418 |
enance | +0.414 |
Neg logit contributions | |
jriwal | -0.474 |
kefeller | -0.436 |
impulse | -0.425 |
turmoil | -0.403 |
reaction | -0.395 |
Token | le |
Token ID | 443 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
lehem | +3.283 |
RON | +3.107 |
rans | +3.030 |
rons | +2.990 |
enance | +2.945 |
Neg logit contributions | |
jriwal | -2.780 |
kefeller | -2.566 |
impulse | -2.446 |
turmoil | -2.304 |
reaction | -2.232 |
Token | pr |
Token ID | 778 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
jriwal | +1.719 |
kefeller | +1.557 |
impulse | +1.527 |
turmoil | +1.437 |
reaction | +1.409 |
Neg logit contributions | |
lehem | -2.201 |
RON | -2.068 |
rans | -2.024 |
rons | -1.978 |
enance | -1.971 |
Token | és |
Token ID | 20954 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
jriwal | +5.613 |
kefeller | +5.066 |
impulse | +5.011 |
turmoil | +4.714 |
reaction | +4.640 |
Neg logit contributions | |
lehem | -6.182 |
RON | -5.799 |
rans | -5.584 |
rons | -5.412 |
enance | -5.345 |
Token | ent |
Token ID | 298 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
jriwal | +0.353 |
kefeller | +0.329 |
impulse | +0.322 |
turmoil | +0.308 |
reaction | +0.303 |
Neg logit contributions | |
lehem | -0.263 |
RON | -0.243 |
rans | -0.237 |
rons | -0.231 |
enance | -0.229 |
Token | act |
Token ID | 719 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
lehem | +5.982 |
RON | +5.725 |
rans | +5.627 |
rons | +5.573 |
enance | +5.513 |
Neg logit contributions | |
jriwal | -5.395 |
kefeller | -5.047 |
impulse | -4.642 |
turmoil | -4.416 |
senal | -4.274 |
Token | e |
Token ID | 68 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
lehem | +3.633 |
RON | +3.435 |
rans | +3.381 |
rons | +3.325 |
enance | +3.310 |
Neg logit contributions | |
jriwal | -3.289 |
kefeller | -3.032 |
impulse | -2.890 |
turmoil | -2.735 |
reaction | -2.657 |
Token | , |
Token ID | 11 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
jriwal | +0.845 |
kefeller | +0.770 |
impulse | +0.751 |
turmoil | +0.707 |
reaction | +0.692 |
Neg logit contributions | |
lehem | -1.023 |
RON | -0.962 |
rans | -0.941 |
rons | -0.921 |
enance | -0.913 |
Token | city |
Token ID | 1748 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
jriwal | +0.934 |
kefeller | +0.847 |
impulse | +0.811 |
turmoil | +0.757 |
reaction | +0.738 |
Neg logit contributions | |
lehem | -1.338 |
RON | -1.269 |
rans | -1.242 |
rons | -1.216 |
enance | -1.208 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
lehem | +2.027 |
RON | +1.924 |
rans | +1.891 |
rons | +1.849 |
enance | +1.821 |
Neg logit contributions | |
jriwal | -1.708 |
kefeller | -1.569 |
impulse | -1.495 |
turmoil | -1.401 |
reaction | -1.369 |
Token | This |
Token ID | 770 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
jriwal | +1.083 |
kefeller | +0.999 |
impulse | +0.984 |
turmoil | +0.935 |
reaction | +0.921 |
Neg logit contributions | |
lehem | -1.036 |
RON | -0.963 |
rans | -0.940 |
rons | -0.918 |
enance | -0.911 |
Token | series |
Token ID | 2168 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
jriwal | +2.370 |
kefeller | +2.129 |
impulse | +2.091 |
turmoil | +1.947 |
reaction | +1.905 |
Neg logit contributions | |
lehem | -3.526 |
RON | -3.326 |
rans | -3.261 |
rons | -3.195 |
enance | -3.175 |
Token | of |
Token ID | 286 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
lehem | +0.195 |
RON | +0.184 |
rans | +0.180 |
rons | +0.176 |
enance | +0.175 |
Neg logit contributions | |
jriwal | -0.167 |
kefeller | -0.153 |
impulse | -0.148 |
turmoil | -0.139 |
reaction | -0.136 |
Token | blog |
Token ID | 4130 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
lehem | +0.612 |
RON | +0.582 |
rans | +0.571 |
rons | +0.562 |
enance | +0.554 |
Neg logit contributions | |
jriwal | -0.396 |
kefeller | -0.359 |
impulse | -0.338 |
turmoil | -0.316 |
reaction | -0.305 |
Token | posts |
Token ID | 6851 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
jriwal | +4.687 |
impulse | +4.133 |
kefeller | +4.133 |
reaction | +3.858 |
turmoil | +3.848 |
Neg logit contributions | |
lehem | -7.222 |
RON | -6.773 |
rans | -6.584 |
enance | -6.543 |
rons | -6.400 |
Token | is |
Token ID | 318 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
jriwal | +2.741 |
kefeller | +2.498 |
impulse | +2.459 |
turmoil | +2.318 |
reaction | +2.278 |
Neg logit contributions | |
lehem | -3.211 |
RON | -3.017 |
rans | -2.939 |
rons | -2.872 |
enance | -2.857 |
Token | an |
Token ID | 281 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
jriwal | +2.904 |
kefeller | +2.606 |
impulse | +2.567 |
turmoil | +2.391 |
reaction | +2.348 |
Neg logit contributions | |
lehem | -4.230 |
RON | -3.991 |
rans | -3.899 |
rons | -3.827 |
enance | -3.798 |
Token | introduction |
Token ID | 9793 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
jriwal | +0.628 |
kefeller | +0.554 |
impulse | +0.497 |
turmoil | +0.463 |
reaction | +0.430 |
Neg logit contributions | |
lehem | -1.525 |
RON | -1.469 |
rans | -1.447 |
rons | -1.427 |
enance | -1.412 |
Token | to |
Token ID | 284 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
jriwal | +0.368 |
kefeller | +0.329 |
impulse | +0.314 |
turmoil | +0.290 |
reaction | +0.279 |
Neg logit contributions | |
lehem | -0.666 |
RON | -0.634 |
rans | -0.622 |
rons | -0.612 |
enance | -0.607 |
Token | ort |
Token ID | 419 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
lehem | +0.093 |
RON | +0.087 |
rans | +0.084 |
rons | +0.082 |
enance | +0.081 |
Neg logit contributions | |
jriwal | -0.105 |
kefeller | -0.097 |
impulse | -0.095 |
turmoil | -0.090 |
reaction | -0.089 |
Token | ic |
Token ID | 291 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
lehem | +3.295 |
RON | +3.052 |
rans | +3.050 |
rons | +2.919 |
enance | +2.901 |
Neg logit contributions | |
jriwal | -4.778 |
kefeller | -4.382 |
impulse | -4.322 |
turmoil | -4.156 |
reaction | -4.028 |
Token | otrop |
Token ID | 34248 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
jriwal | +2.110 |
kefeller | +1.962 |
impulse | +1.914 |
turmoil | +1.811 |
reaction | +1.783 |
Neg logit contributions | |
lehem | -2.028 |
RON | -1.887 |
rans | -1.829 |
enance | -1.793 |
rons | -1.784 |
Token | in |
Token ID | 259 |
Feature activation | -5.73e+00 |
Pos logit contributions | |
lehem | +0.667 |
RON | +0.615 |
rans | +0.598 |
rons | +0.581 |
enance | +0.574 |
Neg logit contributions | |
jriwal | -0.951 |
kefeller | -0.887 |
impulse | -0.868 |
turmoil | -0.831 |
reaction | -0.816 |
Token | - |
Token ID | 12 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
jriwal | +4.463 |
impulse | +4.069 |
kefeller | +4.041 |
reaction | +3.814 |
turmoil | +3.806 |
Neg logit contributions | |
lehem | -5.978 |
RON | -5.530 |
rans | -5.403 |
enance | -5.360 |
rons | -5.325 |
Token | re |
Token ID | 260 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
lehem | +2.633 |
RON | +2.436 |
rans | +2.380 |
rons | +2.229 |
enance | +2.122 |
Neg logit contributions | |
jriwal | -5.601 |
kefeller | -5.271 |
impulse | -5.095 |
turmoil | -4.939 |
reaction | -4.827 |
Token | leasing |
Token ID | 48764 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
jriwal | +6.418 |
impulse | +5.916 |
kefeller | +5.682 |
turmoil | +5.393 |
reaction | +5.310 |
Neg logit contributions | |
lehem | -8.920 |
RON | -8.481 |
rans | -8.116 |
rons | -8.048 |
enance | -8.042 |
Token | factor |
Token ID | 5766 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
jriwal | +0.042 |
kefeller | +0.037 |
impulse | +0.036 |
turmoil | +0.033 |
reaction | +0.032 |
Neg logit contributions | |
lehem | -0.082 |
RON | -0.078 |
rans | -0.077 |
rons | -0.076 |
enance | -0.075 |
Token | ( |
Token ID | 357 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
jriwal | +0.521 |
kefeller | +0.477 |
impulse | +0.463 |
turmoil | +0.438 |
reaction | +0.428 |
Neg logit contributions | |
lehem | -0.585 |
RON | -0.550 |
rans | -0.538 |
rons | -0.526 |
enance | -0.520 |
Token | CR |
Token ID | 9419 |
Feature activation | -8.68e+00 |
Pos logit contributions | |
lehem | +0.333 |
RON | +0.310 |
rans | +0.303 |
rons | +0.297 |
enance | +0.295 |
Neg logit contributions | |
jriwal | -0.316 |
kefeller | -0.290 |
impulse | -0.283 |
turmoil | -0.268 |
reaction | -0.263 |
Token | F |
Token ID | 37 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
jriwal | +7.244 |
kefeller | +6.831 |
impulse | +6.807 |
reaction | +6.395 |
turmoil | +6.326 |
Neg logit contributions | |
lehem | -8.410 |
RON | -7.532 |
rons | -7.300 |
rans | -7.232 |
enance | -7.130 |
Token | I |
Token ID | 314 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
lehem | +1.300 |
RON | +1.234 |
rans | +1.207 |
rons | +1.188 |
enance | +1.175 |
Neg logit contributions | |
jriwal | -1.068 |
kefeller | -0.980 |
impulse | -0.921 |
turmoil | -0.872 |
reaction | -0.844 |
Token | refer |
Token ID | 3522 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
lehem | +2.286 |
RON | +2.176 |
rans | +2.148 |
rons | +2.108 |
enance | +2.091 |
Neg logit contributions | |
jriwal | -1.565 |
kefeller | -1.420 |
impulse | -1.328 |
turmoil | -1.251 |
reaction | -1.212 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
jriwal | +0.023 |
kefeller | +0.020 |
impulse | +0.019 |
turmoil | +0.018 |
reaction | +0.017 |
Neg logit contributions | |
lehem | -0.041 |
RON | -0.039 |
rans | -0.038 |
rons | -0.038 |
enance | -0.038 |
Token | � |
Token ID | 564 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
lehem | +1.825 |
RON | +1.733 |
rans | +1.700 |
rons | +1.671 |
enance | +1.667 |
Neg logit contributions | |
jriwal | -1.288 |
kefeller | -1.168 |
impulse | -1.101 |
turmoil | -1.036 |
reaction | -0.998 |
Token | � |
Token ID | 250 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
lehem | +2.272 |
RON | +2.098 |
rans | +2.022 |
enance | +1.925 |
rons | +1.885 |
Neg logit contributions | |
jriwal | -5.480 |
kefeller | -5.203 |
impulse | -5.007 |
turmoil | -4.827 |
reaction | -4.768 |
Token | R |
Token ID | 49 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
lehem | +1.316 |
RON | +1.230 |
rans | +1.197 |
rons | +1.162 |
enance | +1.151 |
Neg logit contributions | |
jriwal | -1.559 |
kefeller | -1.449 |
impulse | -1.413 |
turmoil | -1.344 |
reaction | -1.317 |
Token | alph |
Token ID | 17307 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
jriwal | +8.073 |
kefeller | +7.487 |
impulse | +7.353 |
reaction | +6.976 |
turmoil | +6.953 |
Neg logit contributions | |
lehem | -7.462 |
RON | -6.944 |
rans | -6.689 |
rons | -6.470 |
enance | -6.332 |
Token | � |
Token ID | 447 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
lehem | +2.926 |
RON | +2.733 |
rans | +2.660 |
enance | +2.607 |
rons | +2.597 |
Neg logit contributions | |
jriwal | -3.129 |
kefeller | -2.840 |
impulse | -2.772 |
turmoil | -2.620 |
reaction | -2.546 |
Token | � |
Token ID | 251 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
jriwal | +2.252 |
kefeller | +2.092 |
impulse | +2.057 |
turmoil | +1.969 |
reaction | +1.935 |
Neg logit contributions | |
lehem | -1.675 |
RON | -1.545 |
rans | -1.500 |
rons | -1.463 |
enance | -1.439 |
Token | , |
Token ID | 11 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
lehem | +4.033 |
RON | +3.817 |
rans | +3.734 |
rons | +3.685 |
enance | +3.655 |
Neg logit contributions | |
jriwal | -3.469 |
kefeller | -3.173 |
impulse | -3.026 |
turmoil | -2.840 |
reaction | -2.753 |
Token | the |
Token ID | 262 |
Feature activation | -8.46e-02 |
Pos logit contributions | |
jriwal | +0.289 |
kefeller | +0.264 |
impulse | +0.255 |
turmoil | +0.240 |
reaction | +0.234 |
Neg logit contributions | |
lehem | -0.357 |
RON | -0.336 |
rans | -0.329 |
rons | -0.322 |
enance | -0.320 |