Token | {{ |
Token ID | 22935 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
Hunts | +2.766 |
Scand | +2.250 |
Lat | +2.243 |
Amateur | +2.204 |
Engels | +2.200 |
Neg logit contributions | |
inyl | -5.226 |
Rah | -4.821 |
ricks | -4.819 |
liner | -4.776 |
ciples | -4.703 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
Hunts | +3.698 |
Scand | +3.167 |
Lat | +3.113 |
Engels | +3.070 |
Amateur | +3.052 |
Neg logit contributions | |
inyl | -5.217 |
ricks | -4.724 |
Rah | -4.646 |
Jinn | -4.643 |
liner | -4.641 |
Token | , |
Token ID | 11 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
inyl | +1.650 |
� | +1.476 |
Rah | +1.474 |
liner | +1.472 |
ricks | +1.466 |
Neg logit contributions | |
Hunts | -1.899 |
Scand | -1.679 |
Engels | -1.668 |
Amateur | -1.644 |
Lat | -1.624 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Hunts | +0.283 |
Scand | +0.242 |
Engels | +0.242 |
Amateur | +0.239 |
Lat | +0.238 |
Neg logit contributions | |
inyl | -0.347 |
ricks | -0.315 |
Rah | -0.313 |
liner | -0.313 |
� | -0.310 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
inyl | +1.298 |
ricks | +1.200 |
liner | +1.195 |
Rah | +1.193 |
� | +1.190 |
Neg logit contributions | |
Hunts | -0.617 |
Scand | -0.500 |
Engels | -0.494 |
Amateur | -0.481 |
Lat | -0.472 |
Token | {{ |
Token ID | 22935 |
Feature activation | +9.06e+00 |
Pos logit contributions | |
Hunts | +4.307 |
Lat | +3.699 |
Scand | +3.690 |
Engels | +3.669 |
Amateur | +3.657 |
Neg logit contributions | |
inyl | -5.049 |
Rah | -4.618 |
ricks | -4.597 |
liner | -4.570 |
ciples | -4.471 |
Token | 9 |
Token ID | 24 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Hunts | +5.522 |
Lat | +4.679 |
Scand | +4.631 |
Engels | +4.512 |
Amateur | +4.472 |
Neg logit contributions | |
inyl | -8.080 |
ricks | -7.402 |
Jinn | -7.165 |
Rah | -7.148 |
ciples | -7.145 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Hunts | +0.398 |
Scand | +0.347 |
Engels | +0.347 |
Amateur | +0.343 |
Lat | +0.342 |
Neg logit contributions | |
inyl | -0.390 |
ricks | -0.350 |
Rah | -0.347 |
liner | -0.347 |
� | -0.344 |
Token | 14 |
Token ID | 1478 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Hunts | +1.377 |
Scand | +1.167 |
Engels | +1.167 |
Amateur | +1.155 |
Lat | +1.155 |
Neg logit contributions | |
inyl | -1.834 |
ricks | -1.669 |
Rah | -1.657 |
liner | -1.655 |
� | -1.635 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
inyl | +0.822 |
ricks | +0.762 |
liner | +0.759 |
Rah | +0.757 |
� | +0.755 |
Neg logit contributions | |
Hunts | -0.384 |
Scand | -0.310 |
Engels | -0.305 |
Amateur | -0.298 |
Lat | -0.294 |
Token | { |
Token ID | 1391 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
Hunts | +4.709 |
Lat | +4.059 |
Amateur | +3.954 |
Engels | +3.924 |
Scand | +3.905 |
Neg logit contributions | |
inyl | -6.705 |
ricks | -6.167 |
Rah | -6.063 |
liner | -6.040 |
ciples | -5.981 |
Token | {{ |
Token ID | 22935 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
Hunts | +2.732 |
Scand | +2.238 |
Lat | +2.230 |
Amateur | +2.197 |
Engels | +2.196 |
Neg logit contributions | |
inyl | -4.938 |
ricks | -4.551 |
Rah | -4.547 |
liner | -4.507 |
ciples | -4.436 |
Token | 9 |
Token ID | 24 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
Hunts | +3.474 |
Scand | +3.007 |
Lat | +2.984 |
Engels | +2.936 |
Amateur | +2.933 |
Neg logit contributions | |
inyl | -4.398 |
ricks | -3.972 |
Rah | -3.890 |
liner | -3.873 |
Jinn | -3.856 |
Token | , |
Token ID | 11 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
inyl | +1.598 |
ricks | +1.427 |
� | +1.427 |
liner | +1.427 |
Rah | +1.424 |
Neg logit contributions | |
Hunts | -1.818 |
Scand | -1.602 |
Engels | -1.589 |
Amateur | -1.573 |
Lat | -1.557 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Hunts | +0.432 |
Engels | +0.370 |
Scand | +0.370 |
Amateur | +0.367 |
Lat | +0.364 |
Neg logit contributions | |
inyl | -0.510 |
ricks | -0.463 |
Rah | -0.461 |
liner | -0.460 |
� | -0.457 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
inyl | +1.611 |
ricks | +1.492 |
liner | +1.482 |
Rah | +1.482 |
� | +1.470 |
Neg logit contributions | |
Hunts | -0.747 |
Engels | -0.599 |
Scand | -0.596 |
Amateur | -0.586 |
Lat | -0.578 |
Token | {{ |
Token ID | 22935 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
Hunts | +4.268 |
Lat | +3.667 |
Scand | +3.666 |
Engels | +3.625 |
Amateur | +3.607 |
Neg logit contributions | |
inyl | -5.081 |
Rah | -4.646 |
ricks | -4.643 |
liner | -4.599 |
ciples | -4.506 |
Token | 8 |
Token ID | 23 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
Hunts | +5.399 |
Lat | +4.566 |
Scand | +4.536 |
Engels | +4.472 |
Amateur | +4.409 |
Neg logit contributions | |
inyl | -7.863 |
ricks | -7.176 |
Jinn | -6.951 |
ciples | -6.945 |
Rah | -6.930 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
Hunts | +0.688 |
Engels | +0.598 |
Scand | +0.598 |
Amateur | +0.593 |
Lat | +0.592 |
Neg logit contributions | |
inyl | -0.688 |
ricks | -0.618 |
Rah | -0.614 |
liner | -0.613 |
� | -0.606 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Hunts | +1.844 |
Scand | +1.567 |
Engels | +1.566 |
Lat | +1.555 |
Amateur | +1.552 |
Neg logit contributions | |
inyl | -2.388 |
ricks | -2.171 |
liner | -2.150 |
Rah | -2.149 |
� | -2.118 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
Hunts | +0.060 |
Scand | +0.048 |
Engels | +0.048 |
Amateur | +0.046 |
Lat | +0.046 |
Neg logit contributions | |
inyl | -0.134 |
ricks | -0.124 |
liner | -0.124 |
Rah | -0.124 |
� | -0.123 |
Token | { |
Token ID | 1391 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Hunts | +4.782 |
Lat | +4.126 |
Amateur | +4.019 |
Engels | +3.994 |
Scand | +3.985 |
Neg logit contributions | |
inyl | -6.676 |
ricks | -6.146 |
Rah | -6.048 |
liner | -6.015 |
ciples | -5.961 |
Token | offline |
Token ID | 18043 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
inyl | +0.506 |
ricks | +0.456 |
Rah | +0.453 |
liner | +0.452 |
� | +0.449 |
Neg logit contributions | |
Hunts | -0.491 |
Engels | -0.426 |
Scand | -0.425 |
Amateur | -0.420 |
Lat | -0.419 |
Token | qualifier |
Token ID | 39265 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
inyl | +0.923 |
ricks | +0.855 |
liner | +0.851 |
Rah | +0.848 |
� | +0.845 |
Neg logit contributions | |
Hunts | -0.433 |
Engels | -0.346 |
Scand | -0.346 |
Amateur | -0.337 |
Lat | -0.337 |
Token | as |
Token ID | 355 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
inyl | +0.169 |
ricks | +0.152 |
Rah | +0.151 |
liner | +0.151 |
� | +0.149 |
Neg logit contributions | |
Hunts | -0.167 |
Scand | -0.145 |
Engels | -0.145 |
Amateur | -0.144 |
Lat | -0.144 |
Token | a |
Token ID | 257 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
inyl | +0.997 |
ricks | +0.877 |
Rah | +0.870 |
liner | +0.867 |
� | +0.863 |
Neg logit contributions | |
Hunts | -1.421 |
Engels | -1.266 |
Scand | -1.261 |
Amateur | -1.252 |
Lat | -1.247 |
Token | stand |
Token ID | 1302 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
inyl | +0.481 |
liner | +0.435 |
ricks | +0.435 |
� | +0.430 |
Rah | +0.429 |
Neg logit contributions | |
Hunts | -0.467 |
Engels | -0.411 |
Scand | -0.407 |
Amateur | -0.403 |
Lat | -0.397 |
Token | - |
Token ID | 12 |
Feature activation | +7.70e+00 |
Pos logit contributions | |
Hunts | +1.460 |
Scand | +1.252 |
Engels | +1.251 |
Lat | +1.248 |
Amateur | +1.242 |
Neg logit contributions | |
inyl | -1.680 |
ricks | -1.513 |
Rah | -1.510 |
liner | -1.494 |
� | -1.480 |
Token | in |
Token ID | 259 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
Hunts | +5.588 |
Lat | +5.040 |
Scand | +4.804 |
Amateur | +4.779 |
Engels | +4.736 |
Neg logit contributions | |
inyl | -5.696 |
Rah | -5.179 |
ciples | -5.132 |
Jinn | -5.127 |
ricks | -5.052 |
Token | for |
Token ID | 329 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Hunts | +2.572 |
Lat | +2.223 |
Scand | +2.218 |
Engels | +2.206 |
Amateur | +2.204 |
Neg logit contributions | |
inyl | -2.822 |
ricks | -2.540 |
Rah | -2.537 |
liner | -2.466 |
� | -2.451 |
Token | J |
Token ID | 449 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
inyl | +1.330 |
ricks | +1.199 |
Rah | +1.195 |
liner | +1.193 |
� | +1.193 |
Neg logit contributions | |
Hunts | -1.317 |
Engels | -1.146 |
Scand | -1.142 |
Amateur | -1.134 |
Lat | -1.122 |
Token | oon |
Token ID | 2049 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Hunts | +0.194 |
Scand | +0.171 |
Engels | +0.171 |
Amateur | +0.168 |
Lat | +0.168 |
Neg logit contributions | |
inyl | -0.178 |
ricks | -0.160 |
liner | -0.159 |
Rah | -0.158 |
� | -0.157 |
Token | a |
Token ID | 64 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
inyl | +0.235 |
ricks | +0.211 |
Rah | +0.211 |
liner | +0.210 |
� | +0.208 |
Neg logit contributions | |
Hunts | -0.237 |
Scand | -0.207 |
Engels | -0.207 |
Amateur | -0.205 |
Lat | -0.204 |
Token | = |
Token ID | 796 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
inyl | +0.822 |
Rah | +0.702 |
� | +0.701 |
ricks | +0.699 |
liner | +0.697 |
Neg logit contributions | |
Hunts | -1.510 |
Scand | -1.361 |
Engels | -1.358 |
Amateur | -1.350 |
Lat | -1.336 |
Token | v |
Token ID | 410 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
Hunts | +1.977 |
Scand | +1.754 |
Engels | +1.735 |
Lat | +1.730 |
Amateur | +1.714 |
Neg logit contributions | |
inyl | -1.820 |
ricks | -1.639 |
Rah | -1.628 |
liner | -1.600 |
ciples | -1.561 |
Token | ars |
Token ID | 945 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Hunts | +3.626 |
Lat | +3.090 |
Scand | +3.081 |
Engels | +3.075 |
Amateur | +3.059 |
Neg logit contributions | |
inyl | -3.990 |
Rah | -3.637 |
liner | -3.585 |
Jinn | -3.563 |
ricks | -3.563 |
Token | ( |
Token ID | 7 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
Hunts | +0.476 |
Engels | +0.416 |
Scand | +0.415 |
Lat | +0.413 |
Amateur | +0.412 |
Neg logit contributions | |
inyl | -0.453 |
ricks | -0.407 |
Rah | -0.401 |
liner | -0.401 |
� | -0.394 |
Token | ap |
Token ID | 499 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Hunts | +2.404 |
Scand | +2.092 |
Engels | +2.079 |
Amateur | +2.079 |
Lat | +2.074 |
Neg logit contributions | |
inyl | -2.436 |
Rah | -2.179 |
ricks | -2.179 |
liner | -2.158 |
Jinn | -2.130 |
Token | . |
Token ID | 13 |
Feature activation | +7.65e+00 |
Pos logit contributions | |
Hunts | +0.441 |
Engels | +0.380 |
Scand | +0.380 |
Amateur | +0.377 |
Lat | +0.376 |
Neg logit contributions | |
inyl | -0.494 |
ricks | -0.447 |
Rah | -0.444 |
liner | -0.443 |
� | -0.438 |
Token | parse |
Token ID | 29572 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Hunts | +3.282 |
Lat | +2.609 |
Scand | +2.483 |
Amateur | +2.456 |
Engels | +2.368 |
Neg logit contributions | |
inyl | -8.010 |
Rah | -7.673 |
Jinn | -7.559 |
ricks | -7.413 |
liner | -7.400 |
Token | _ |
Token ID | 62 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Hunts | +1.959 |
Lat | +1.679 |
Engels | +1.669 |
Amateur | +1.662 |
Scand | +1.656 |
Neg logit contributions | |
inyl | -2.454 |
ricks | -2.223 |
Rah | -2.192 |
liner | -2.189 |
Jinn | -2.157 |
Token | args |
Token ID | 22046 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Hunts | +2.787 |
Engels | +2.396 |
Scand | +2.386 |
Lat | +2.382 |
Amateur | +2.379 |
Neg logit contributions | |
inyl | -3.103 |
Rah | -2.752 |
liner | -2.724 |
� | -2.721 |
ricks | -2.721 |
Token | ()) |
Token ID | 28955 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
inyl | +1.897 |
ricks | +1.678 |
liner | +1.667 |
� | +1.663 |
Rah | +1.638 |
Neg logit contributions | |
Hunts | -2.630 |
Scand | -2.326 |
Amateur | -2.323 |
Engels | -2.319 |
Lat | -2.285 |
Token | # |
Token ID | 1303 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Hunts | +2.879 |
Scand | +2.538 |
Lat | +2.508 |
Amateur | +2.491 |
Engels | +2.465 |
Neg logit contributions | |
inyl | -2.874 |
ricks | -2.586 |
liner | -2.567 |
Rah | -2.565 |
ciples | -2.485 |
Token | of |
Token ID | 286 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Hunts | +1.857 |
Engels | +1.597 |
Lat | +1.593 |
Scand | +1.587 |
Amateur | +1.583 |
Neg logit contributions | |
inyl | -2.098 |
ricks | -1.899 |
Rah | -1.876 |
liner | -1.862 |
� | -1.828 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
Hunts | +1.670 |
Engels | +1.461 |
Lat | +1.458 |
Scand | +1.457 |
Amateur | +1.447 |
Neg logit contributions | |
inyl | -1.517 |
ricks | -1.353 |
Rah | -1.340 |
liner | -1.333 |
� | -1.306 |
Token | Rift |
Token ID | 21222 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Hunts | +2.904 |
Lat | +2.492 |
Scand | +2.466 |
Engels | +2.459 |
Amateur | +2.452 |
Neg logit contributions | |
inyl | -3.387 |
ricks | -3.074 |
Rah | -3.045 |
liner | -3.019 |
ciples | -2.970 |
Token | would |
Token ID | 561 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Hunts | +2.293 |
Engels | +1.939 |
Scand | +1.938 |
Lat | +1.931 |
Amateur | +1.922 |
Neg logit contributions | |
inyl | -2.974 |
ricks | -2.700 |
Rah | -2.663 |
liner | -2.646 |
� | -2.610 |
Token | employ |
Token ID | 1873 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
Hunts | +2.577 |
Engels | +2.245 |
Scand | +2.215 |
Amateur | +2.196 |
Lat | +2.191 |
Neg logit contributions | |
inyl | -2.769 |
ricks | -2.493 |
Rah | -2.477 |
liner | -2.461 |
� | -2.421 |
Token | such |
Token ID | 884 |
Feature activation | +7.50e+00 |
Pos logit contributions | |
Hunts | +3.296 |
Engels | +2.752 |
Lat | +2.732 |
Amateur | +2.705 |
Scand | +2.675 |
Neg logit contributions | |
inyl | -5.230 |
ricks | -4.763 |
Rah | -4.730 |
liner | -4.725 |
� | -4.578 |
Token | a |
Token ID | 257 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Hunts | +4.853 |
Lat | +4.181 |
Engels | +4.093 |
Amateur | +4.002 |
Scand | +3.937 |
Neg logit contributions | |
inyl | -6.772 |
ricks | -6.227 |
Rah | -6.028 |
liner | -5.984 |
ciples | -5.896 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Hunts | +2.758 |
Lat | +2.401 |
Engels | +2.386 |
Scand | +2.380 |
Amateur | +2.350 |
Neg logit contributions | |
inyl | -3.035 |
ricks | -2.745 |
Rah | -2.708 |
liner | -2.667 |
� | -2.646 |
Token | ( |
Token ID | 357 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
Hunts | +2.054 |
Lat | +1.808 |
Engels | +1.808 |
Scand | +1.806 |
Amateur | +1.800 |
Neg logit contributions | |
inyl | -1.682 |
ricks | -1.495 |
Rah | -1.470 |
liner | -1.464 |
� | -1.430 |
Token | as |
Token ID | 292 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Hunts | +3.133 |
Lat | +2.699 |
Engels | +2.640 |
Amateur | +2.635 |
Scand | +2.633 |
Neg logit contributions | |
inyl | -3.935 |
ricks | -3.523 |
Rah | -3.512 |
Jinn | -3.507 |
liner | -3.487 |
Token | long |
Token ID | 890 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Hunts | +2.267 |
Lat | +1.941 |
Engels | +1.919 |
Scand | +1.876 |
Amateur | +1.875 |
Neg logit contributions | |
inyl | -2.985 |
ricks | -2.724 |
Rah | -2.715 |
liner | -2.681 |
� | -2.614 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
inyl | +1.611 |
ricks | +1.492 |
liner | +1.482 |
Rah | +1.482 |
� | +1.470 |
Neg logit contributions | |
Hunts | -0.747 |
Engels | -0.599 |
Scand | -0.596 |
Amateur | -0.586 |
Lat | -0.578 |
Token | {{ |
Token ID | 22935 |
Feature activation | +8.82e+00 |
Pos logit contributions | |
Hunts | +4.268 |
Lat | +3.667 |
Scand | +3.666 |
Engels | +3.625 |
Amateur | +3.607 |
Neg logit contributions | |
inyl | -5.081 |
Rah | -4.646 |
ricks | -4.643 |
liner | -4.599 |
ciples | -4.506 |
Token | 8 |
Token ID | 23 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
Hunts | +5.399 |
Lat | +4.566 |
Scand | +4.536 |
Engels | +4.472 |
Amateur | +4.409 |
Neg logit contributions | |
inyl | -7.863 |
ricks | -7.176 |
Jinn | -6.951 |
ciples | -6.945 |
Rah | -6.930 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
Hunts | +0.688 |
Engels | +0.598 |
Scand | +0.598 |
Amateur | +0.593 |
Lat | +0.592 |
Neg logit contributions | |
inyl | -0.688 |
ricks | -0.618 |
Rah | -0.614 |
liner | -0.613 |
� | -0.606 |
Token | 14 |
Token ID | 1478 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Hunts | +1.844 |
Scand | +1.567 |
Engels | +1.566 |
Lat | +1.555 |
Amateur | +1.552 |
Neg logit contributions | |
inyl | -2.388 |
ricks | -2.171 |
liner | -2.150 |
Rah | -2.149 |
� | -2.118 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
Hunts | +0.060 |
Scand | +0.048 |
Engels | +0.048 |
Amateur | +0.046 |
Lat | +0.046 |
Neg logit contributions | |
inyl | -0.134 |
ricks | -0.124 |
liner | -0.124 |
Rah | -0.124 |
� | -0.123 |
Token | { |
Token ID | 1391 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Hunts | +4.782 |
Lat | +4.126 |
Amateur | +4.019 |
Engels | +3.994 |
Scand | +3.985 |
Neg logit contributions | |
inyl | -6.676 |
ricks | -6.146 |
Rah | -6.048 |
liner | -6.015 |
ciples | -5.961 |
Token | 8 |
Token ID | 23 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Hunts | +3.651 |
Scand | +3.093 |
Lat | +3.087 |
Engels | +3.062 |
Amateur | +3.030 |
Neg logit contributions | |
inyl | -4.740 |
ricks | -4.321 |
Rah | -4.219 |
liner | -4.205 |
� | -4.185 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
inyl | +0.220 |
ricks | +0.197 |
liner | +0.196 |
Rah | +0.196 |
� | +0.195 |
Neg logit contributions | |
Hunts | -0.232 |
Scand | -0.203 |
Engels | -0.202 |
Amateur | -0.200 |
Lat | -0.199 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Hunts | +1.844 |
Engels | +1.561 |
Scand | +1.560 |
Lat | +1.559 |
Amateur | +1.546 |
Neg logit contributions | |
inyl | -2.447 |
ricks | -2.220 |
Rah | -2.205 |
liner | -2.201 |
� | -2.162 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
Hunts | +0.208 |
Scand | +0.164 |
Engels | +0.163 |
Amateur | +0.160 |
Lat | +0.159 |
Neg logit contributions | |
inyl | -0.477 |
ricks | -0.442 |
liner | -0.440 |
Rah | -0.440 |
� | -0.437 |
Token | We |
Token ID | 1135 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
inyl | +0.849 |
Rah | +0.757 |
ricks | +0.755 |
liner | +0.748 |
� | +0.740 |
Neg logit contributions | |
Hunts | -1.096 |
Engels | -0.974 |
Scand | -0.971 |
Amateur | -0.962 |
Lat | -0.957 |
Token | need |
Token ID | 761 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
inyl | +0.273 |
ricks | +0.246 |
Rah | +0.244 |
liner | +0.244 |
� | +0.241 |
Neg logit contributions | |
Hunts | -0.262 |
Scand | -0.227 |
Engels | -0.227 |
Amateur | -0.225 |
Lat | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Hunts | +1.406 |
Lat | +1.226 |
Engels | +1.224 |
Amateur | +1.219 |
Scand | +1.216 |
Neg logit contributions | |
inyl | -1.321 |
ricks | -1.180 |
Rah | -1.168 |
liner | -1.162 |
� | -1.131 |
Token | be |
Token ID | 307 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
Hunts | +1.204 |
Engels | +1.041 |
Scand | +1.040 |
Lat | +1.035 |
Amateur | +1.035 |
Neg logit contributions | |
inyl | -1.233 |
ricks | -1.112 |
Rah | -1.103 |
liner | -1.101 |
� | -1.082 |
Token | smart |
Token ID | 4451 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Hunts | +0.456 |
Lat | +0.404 |
Scand | +0.403 |
Amateur | +0.403 |
Engels | +0.401 |
Neg logit contributions | |
inyl | -0.305 |
ricks | -0.264 |
liner | -0.263 |
Rah | -0.261 |
� | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
Hunts | +1.753 |
Lat | +1.507 |
Engels | +1.504 |
Scand | +1.499 |
Amateur | +1.499 |
Neg logit contributions | |
inyl | -1.946 |
ricks | -1.756 |
liner | -1.734 |
Rah | -1.734 |
ciples | -1.687 |
Token | vigilant |
Token ID | 30257 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
Hunts | +4.289 |
Scand | +3.510 |
Amateur | +3.450 |
Lat | +3.438 |
Engels | +3.327 |
Neg logit contributions | |
inyl | -7.191 |
ricks | -6.427 |
liner | -6.382 |
Rah | -6.280 |
ciples | -6.191 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
Hunts | +2.421 |
Lat | +2.080 |
Engels | +2.041 |
Scand | +2.033 |
Amateur | +2.031 |
Neg logit contributions | |
inyl | -2.866 |
ricks | -2.577 |
Rah | -2.536 |
liner | -2.523 |
ciples | -2.489 |
Token | tough |
Token ID | 5802 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Hunts | +1.946 |
Scand | +1.680 |
Lat | +1.670 |
Amateur | +1.659 |
Engels | +1.639 |
Neg logit contributions | |
inyl | -1.850 |
liner | -1.642 |
Rah | -1.612 |
ricks | -1.608 |
ciples | -1.607 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Hunts | +0.237 |
Scand | +0.202 |
Engels | +0.201 |
Lat | +0.201 |
Amateur | +0.200 |
Neg logit contributions | |
inyl | -0.276 |
ricks | -0.252 |
Rah | -0.248 |
liner | -0.248 |
� | -0.241 |
Token | We |
Token ID | 775 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Hunts | +2.178 |
Scand | +1.869 |
Lat | +1.861 |
Amateur | +1.846 |
Engels | +1.835 |
Neg logit contributions | |
inyl | -2.217 |
ricks | -2.022 |
liner | -1.995 |
Rah | -1.971 |
ciples | -1.937 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
inyl | +1.298 |
ricks | +1.200 |
liner | +1.195 |
Rah | +1.193 |
� | +1.190 |
Neg logit contributions | |
Hunts | -0.617 |
Scand | -0.500 |
Engels | -0.494 |
Amateur | -0.481 |
Lat | -0.472 |
Token | {{ |
Token ID | 22935 |
Feature activation | +9.06e+00 |
Pos logit contributions | |
Hunts | +4.307 |
Lat | +3.699 |
Scand | +3.690 |
Engels | +3.669 |
Amateur | +3.657 |
Neg logit contributions | |
inyl | -5.049 |
Rah | -4.618 |
ricks | -4.597 |
liner | -4.570 |
ciples | -4.471 |
Token | 9 |
Token ID | 24 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Hunts | +5.522 |
Lat | +4.679 |
Scand | +4.631 |
Engels | +4.512 |
Amateur | +4.472 |
Neg logit contributions | |
inyl | -8.080 |
ricks | -7.402 |
Jinn | -7.165 |
Rah | -7.148 |
ciples | -7.145 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Hunts | +0.398 |
Scand | +0.347 |
Engels | +0.347 |
Amateur | +0.343 |
Lat | +0.342 |
Neg logit contributions | |
inyl | -0.390 |
ricks | -0.350 |
Rah | -0.347 |
liner | -0.347 |
� | -0.344 |
Token | 14 |
Token ID | 1478 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Hunts | +1.377 |
Scand | +1.167 |
Engels | +1.167 |
Amateur | +1.155 |
Lat | +1.155 |
Neg logit contributions | |
inyl | -1.834 |
ricks | -1.669 |
Rah | -1.657 |
liner | -1.655 |
� | -1.635 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
inyl | +0.822 |
ricks | +0.762 |
liner | +0.759 |
Rah | +0.757 |
� | +0.755 |
Neg logit contributions | |
Hunts | -0.384 |
Scand | -0.310 |
Engels | -0.305 |
Amateur | -0.298 |
Lat | -0.294 |
Token | { |
Token ID | 1391 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
Hunts | +4.709 |
Lat | +4.059 |
Amateur | +3.954 |
Engels | +3.924 |
Scand | +3.905 |
Neg logit contributions | |
inyl | -6.705 |
ricks | -6.167 |
Rah | -6.063 |
liner | -6.040 |
ciples | -5.981 |
Token | 9 |
Token ID | 24 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Hunts | +4.091 |
Scand | +3.528 |
Lat | +3.492 |
Engels | +3.492 |
Amateur | +3.479 |
Neg logit contributions | |
inyl | -4.162 |
ricks | -3.732 |
Rah | -3.640 |
liner | -3.632 |
Jinn | -3.617 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
inyl | +0.683 |
liner | +0.610 |
ricks | +0.610 |
Rah | +0.609 |
� | +0.607 |
Neg logit contributions | |
Hunts | -0.738 |
Scand | -0.648 |
Engels | -0.644 |
Amateur | -0.638 |
Lat | -0.632 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Hunts | +1.865 |
Engels | +1.587 |
Scand | +1.581 |
Lat | +1.578 |
Amateur | +1.570 |
Neg logit contributions | |
inyl | -2.428 |
ricks | -2.205 |
Rah | -2.187 |
liner | -2.182 |
� | -2.145 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
inyl | +0.253 |
ricks | +0.234 |
liner | +0.234 |
Rah | +0.233 |
� | +0.232 |
Neg logit contributions | |
Hunts | -0.116 |
Scand | -0.093 |
Engels | -0.092 |
Amateur | -0.090 |
Lat | -0.088 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
inyl | +0.822 |
ricks | +0.762 |
liner | +0.759 |
Rah | +0.757 |
� | +0.755 |
Neg logit contributions | |
Hunts | -0.384 |
Scand | -0.310 |
Engels | -0.305 |
Amateur | -0.298 |
Lat | -0.294 |
Token | { |
Token ID | 1391 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
Hunts | +4.709 |
Lat | +4.059 |
Amateur | +3.954 |
Engels | +3.924 |
Scand | +3.905 |
Neg logit contributions | |
inyl | -6.705 |
ricks | -6.167 |
Rah | -6.063 |
liner | -6.040 |
ciples | -5.981 |
Token | 9 |
Token ID | 24 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
Hunts | +4.091 |
Scand | +3.528 |
Lat | +3.492 |
Engels | +3.492 |
Amateur | +3.479 |
Neg logit contributions | |
inyl | -4.162 |
ricks | -3.732 |
Rah | -3.640 |
liner | -3.632 |
Jinn | -3.617 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
inyl | +0.683 |
liner | +0.610 |
ricks | +0.610 |
Rah | +0.609 |
� | +0.607 |
Neg logit contributions | |
Hunts | -0.738 |
Scand | -0.648 |
Engels | -0.644 |
Amateur | -0.638 |
Lat | -0.632 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
Hunts | +1.865 |
Engels | +1.587 |
Scand | +1.581 |
Lat | +1.578 |
Amateur | +1.570 |
Neg logit contributions | |
inyl | -2.428 |
ricks | -2.205 |
Rah | -2.187 |
liner | -2.182 |
� | -2.145 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
inyl | +0.253 |
ricks | +0.234 |
liner | +0.234 |
Rah | +0.233 |
� | +0.232 |
Neg logit contributions | |
Hunts | -0.116 |
Scand | -0.093 |
Engels | -0.092 |
Amateur | -0.090 |
Lat | -0.088 |
Token | { |
Token ID | 1391 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Hunts | +4.731 |
Lat | +4.079 |
Amateur | +3.988 |
Engels | +3.959 |
Scand | +3.953 |
Neg logit contributions | |
inyl | -6.626 |
ricks | -6.090 |
Rah | -5.996 |
liner | -5.949 |
ciples | -5.906 |
Token | 10 |
Token ID | 940 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
Hunts | +1.936 |
Scand | +1.646 |
Engels | +1.624 |
Lat | +1.614 |
Amateur | +1.612 |
Neg logit contributions | |
inyl | -2.570 |
ricks | -2.326 |
Rah | -2.303 |
liner | -2.302 |
� | -2.279 |
Token | , |
Token ID | 11 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
inyl | +0.741 |
liner | +0.662 |
Rah | +0.662 |
ricks | +0.661 |
� | +0.658 |
Neg logit contributions | |
Hunts | -0.802 |
Scand | -0.704 |
Engels | -0.701 |
Amateur | -0.692 |
Lat | -0.687 |
Token | 14 |
Token ID | 1478 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Hunts | +1.612 |
Engels | +1.364 |
Scand | +1.364 |
Lat | +1.362 |
Amateur | +1.351 |
Neg logit contributions | |
inyl | -2.156 |
ricks | -1.957 |
Rah | -1.948 |
liner | -1.939 |
� | -1.906 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
inyl | +0.021 |
ricks | +0.019 |
liner | +0.019 |
Rah | +0.019 |
� | +0.019 |
Neg logit contributions | |
Hunts | -0.009 |
Scand | -0.008 |
Engels | -0.007 |
Amateur | -0.007 |
Lat | -0.007 |
Token | :: |
Token ID | 3712 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
inyl | +0.218 |
ricks | +0.192 |
Rah | +0.192 |
liner | +0.191 |
� | +0.189 |
Neg logit contributions | |
Hunts | -0.264 |
Engels | -0.232 |
Scand | -0.232 |
Amateur | -0.230 |
Lat | -0.229 |
Token | All |
Token ID | 3237 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Hunts | +1.202 |
Scand | +1.038 |
Engels | +1.035 |
Lat | +1.030 |
Amateur | +1.027 |
Neg logit contributions | |
inyl | -1.312 |
ricks | -1.185 |
Rah | -1.173 |
liner | -1.173 |
� | -1.163 |
Token | Sc |
Token ID | 3351 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Hunts | +2.034 |
Scand | +1.733 |
Lat | +1.732 |
Engels | +1.720 |
Amateur | +1.717 |
Neg logit contributions | |
inyl | -2.651 |
ricks | -2.412 |
Rah | -2.405 |
liner | -2.404 |
� | -2.367 |
Token | reens |
Token ID | 5681 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
inyl | +0.018 |
ricks | +0.016 |
Rah | +0.016 |
liner | +0.016 |
� | +0.016 |
Neg logit contributions | |
Hunts | -0.022 |
Engels | -0.020 |
Scand | -0.020 |
Amateur | -0.019 |
Lat | -0.019 |
Token | | |
Token ID | 930 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
inyl | +0.542 |
ricks | +0.481 |
Rah | +0.479 |
liner | +0.477 |
� | +0.474 |
Neg logit contributions | |
Hunts | -0.601 |
Engels | -0.528 |
Scand | -0.527 |
Amateur | -0.522 |
Lat | -0.518 |
Token | Where |
Token ID | 6350 |
Feature activation | +7.38e+00 |
Pos logit contributions | |
Hunts | +1.795 |
Scand | +1.543 |
Engels | +1.526 |
Lat | +1.524 |
Amateur | +1.517 |
Neg logit contributions | |
inyl | -2.132 |
ricks | -1.952 |
Rah | -1.935 |
liner | -1.928 |
� | -1.894 |
Token | Primary |
Token ID | 21087 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Hunts | +5.173 |
Lat | +4.596 |
Scand | +4.514 |
Engels | +4.369 |
Amateur | +4.363 |
Neg logit contributions | |
inyl | -5.951 |
ricks | -5.686 |
Rah | -5.492 |
liner | -5.449 |
ciples | -5.390 |
Token | | |
Token ID | 930 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
Hunts | +1.185 |
Scand | +1.029 |
Engels | +1.029 |
Amateur | +1.019 |
Lat | +1.017 |
Neg logit contributions | |
inyl | -1.212 |
ricks | -1.090 |
Rah | -1.083 |
liner | -1.081 |
� | -1.070 |
Token | Select |
Token ID | 9683 |
Feature activation | +3.90e+00 |
Pos logit contributions | |
Hunts | +3.511 |
Lat | +3.097 |
Scand | +3.093 |
Engels | +3.056 |
Amateur | +3.051 |
Neg logit contributions | |
inyl | -3.152 |
ricks | -2.879 |
Rah | -2.843 |
liner | -2.831 |
� | -2.754 |
Token | - |
Token ID | 532 |
Feature activation | +4.44e+00 |
Pos logit contributions | |
Hunts | +2.970 |
Lat | +2.608 |
Scand | +2.580 |
Engels | +2.557 |
Amateur | +2.554 |
Neg logit contributions | |
inyl | -3.057 |
ricks | -2.792 |
Rah | -2.755 |
liner | -2.734 |
ciples | -2.686 |
Token | Exp |
Token ID | 16870 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
Hunts | +3.666 |
Lat | +3.231 |
Scand | +3.216 |
Engels | +3.200 |
Amateur | +3.189 |
Neg logit contributions | |
inyl | -3.179 |
ricks | -2.854 |
Rah | -2.819 |
liner | -2.812 |
� | -2.792 |
Token | trou |
Token ID | 4057 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
Hunts | +1.840 |
Lat | +1.649 |
Engels | +1.648 |
Scand | +1.648 |
Amateur | +1.642 |
Neg logit contributions | |
inyl | -1.000 |
ricks | -0.861 |
Rah | -0.847 |
liner | -0.834 |
� | -0.812 |
Token | ser |
Token ID | 2655 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
Hunts | +2.132 |
Lat | +1.679 |
Engels | +1.657 |
Amateur | +1.655 |
Scand | +1.631 |
Neg logit contributions | |
inyl | -4.673 |
Rah | -4.343 |
ricks | -4.326 |
� | -4.284 |
Jinn | -4.261 |
Token | - |
Token ID | 12 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Hunts | +2.951 |
Engels | +2.445 |
Lat | +2.437 |
Scand | +2.423 |
Amateur | +2.400 |
Neg logit contributions | |
inyl | -4.013 |
ricks | -3.634 |
Rah | -3.601 |
liner | -3.526 |
ciples | -3.452 |
Token | w |
Token ID | 86 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Hunts | +1.285 |
Engels | +1.090 |
Scand | +1.086 |
Lat | +1.083 |
Amateur | +1.081 |
Neg logit contributions | |
inyl | -1.592 |
Rah | -1.434 |
ricks | -1.431 |
liner | -1.411 |
� | -1.406 |
Token | earing |
Token ID | 6648 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
Hunts | +0.182 |
Engels | +0.160 |
Scand | +0.159 |
Amateur | +0.158 |
Lat | +0.158 |
Neg logit contributions | |
inyl | -0.156 |
ricks | -0.139 |
Rah | -0.138 |
liner | -0.138 |
� | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
Hunts | +2.925 |
Scand | +2.512 |
Lat | +2.506 |
Engels | +2.497 |
Amateur | +2.495 |
Neg logit contributions | |
inyl | -3.377 |
ricks | -3.076 |
Rah | -3.041 |
liner | -3.021 |
ciples | -2.923 |
Token | eff |
Token ID | 914 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
Hunts | +2.909 |
Engels | +2.246 |
Amateur | +2.246 |
Lat | +2.241 |
Scand | +2.052 |
Neg logit contributions | |
inyl | -8.113 |
Rah | -7.612 |
ricks | -7.570 |
liner | -7.553 |
ciples | -7.364 |
Token | em |
Token ID | 368 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Hunts | +2.348 |
Lat | +1.880 |
Amateur | +1.858 |
Engels | +1.835 |
Scand | +1.738 |
Neg logit contributions | |
inyl | -5.858 |
Rah | -5.498 |
ricks | -5.451 |
Jinn | -5.413 |
liner | -5.403 |
Token | inate |
Token ID | 4559 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
Hunts | +1.088 |
Amateur | +0.994 |
Lat | +0.987 |
Scand | +0.984 |
Engels | +0.975 |
Neg logit contributions | |
inyl | -0.580 |
ricks | -0.508 |
Rah | -0.507 |
liner | -0.502 |
� | -0.488 |
Token | , |
Token ID | 11 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
Hunts | +3.944 |
Lat | +3.425 |
Engels | +3.383 |
Amateur | +3.360 |
Scand | +3.325 |
Neg logit contributions | |
inyl | -4.820 |
ricks | -4.400 |
Rah | -4.387 |
liner | -4.324 |
ciples | -4.232 |
Token | decad |
Token ID | 46734 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Hunts | +3.170 |
Lat | +2.673 |
Engels | +2.648 |
Scand | +2.624 |
Amateur | +2.601 |
Neg logit contributions | |
inyl | -5.953 |
ricks | -5.573 |
Rah | -5.564 |
liner | -5.510 |
Jinn | -5.365 |
Token | Renault |
Token ID | 44083 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Hunts | +0.085 |
Scand | +0.074 |
Engels | +0.074 |
Amateur | +0.073 |
Lat | +0.073 |
Neg logit contributions | |
inyl | -0.086 |
ricks | -0.078 |
Rah | -0.077 |
liner | -0.077 |
� | -0.077 |
Token | as |
Token ID | 355 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Hunts | +1.111 |
Scand | +0.975 |
Engels | +0.973 |
Amateur | +0.966 |
Lat | +0.966 |
Neg logit contributions | |
inyl | -1.009 |
ricks | -0.894 |
Rah | -0.888 |
liner | -0.885 |
� | -0.874 |
Token | a |
Token ID | 257 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Hunts | +0.289 |
Engels | +0.256 |
Scand | +0.256 |
Amateur | +0.254 |
Lat | +0.254 |
Neg logit contributions | |
inyl | -0.215 |
ricks | -0.190 |
Rah | -0.188 |
liner | -0.188 |
� | -0.186 |
Token | potential |
Token ID | 2785 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Hunts | +0.292 |
Engels | +0.253 |
Scand | +0.251 |
Amateur | +0.250 |
Lat | +0.246 |
Neg logit contributions | |
inyl | -0.322 |
ricks | -0.292 |
liner | -0.292 |
Rah | -0.290 |
� | -0.288 |
Token | stand |
Token ID | 1302 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Hunts | +0.356 |
Engels | +0.309 |
Scand | +0.308 |
Amateur | +0.305 |
Lat | +0.303 |
Neg logit contributions | |
inyl | -0.378 |
ricks | -0.342 |
liner | -0.341 |
Rah | -0.340 |
� | -0.337 |
Token | - |
Token ID | 12 |
Feature activation | +7.17e+00 |
Pos logit contributions | |
Hunts | +1.366 |
Scand | +1.170 |
Engels | +1.167 |
Lat | +1.165 |
Amateur | +1.160 |
Neg logit contributions | |
inyl | -1.623 |
ricks | -1.464 |
Rah | -1.460 |
liner | -1.445 |
� | -1.435 |
Token | in |
Token ID | 259 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
Hunts | +5.227 |
Lat | +4.685 |
Scand | +4.533 |
Amateur | +4.472 |
Engels | +4.431 |
Neg logit contributions | |
inyl | -5.434 |
Rah | -4.860 |
Jinn | -4.825 |
ricks | -4.812 |
ciples | -4.785 |
Token | for |
Token ID | 329 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
Hunts | +2.730 |
Lat | +2.381 |
Scand | +2.378 |
Engels | +2.368 |
Amateur | +2.350 |
Neg logit contributions | |
inyl | -2.817 |
ricks | -2.514 |
Rah | -2.489 |
� | -2.436 |
liner | -2.434 |
Token | Kub |
Token ID | 24921 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
inyl | +0.812 |
ricks | +0.739 |
Rah | +0.735 |
liner | +0.734 |
� | +0.729 |
Neg logit contributions | |
Hunts | -0.680 |
Scand | -0.582 |
Engels | -0.582 |
Amateur | -0.577 |
Lat | -0.571 |
Token | ica |
Token ID | 3970 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
Hunts | +2.195 |
Scand | +1.951 |
Engels | +1.950 |
Lat | +1.942 |
Amateur | +1.935 |
Neg logit contributions | |
inyl | -1.623 |
Rah | -1.426 |
ricks | -1.417 |
liner | -1.404 |
� | -1.388 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
Hunts | +1.697 |
Scand | +1.481 |
Engels | +1.481 |
Lat | +1.478 |
Amateur | +1.465 |
Neg logit contributions | |
inyl | -1.679 |
ricks | -1.498 |
Rah | -1.489 |
liner | -1.471 |
� | -1.454 |
Token | K |
Token ID | 509 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Hunts | +0.152 |
Scand | +0.132 |
Engels | +0.132 |
Amateur | +0.130 |
Lat | +0.130 |
Neg logit contributions | |
inyl | -0.158 |
ricks | -0.142 |
Rah | -0.141 |
liner | -0.141 |
� | -0.140 |
Token | ild |
Token ID | 688 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
inyl | +1.136 |
ricks | +1.022 |
Rah | +1.013 |
liner | +1.011 |
� | +1.000 |
Neg logit contributions | |
Hunts | -1.079 |
Scand | -0.936 |
Engels | -0.935 |
Amateur | -0.927 |
Lat | -0.921 |
Token | on |
Token ID | 261 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Hunts | +1.016 |
Scand | +0.878 |
Engels | +0.877 |
Amateur | +0.872 |
Lat | +0.871 |
Neg logit contributions | |
inyl | -1.092 |
ricks | -0.985 |
Rah | -0.981 |
liner | -0.978 |
� | -0.967 |
Token | an |
Token ID | 272 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
Hunts | +1.358 |
Scand | +1.149 |
Engels | +1.148 |
Amateur | +1.144 |
Lat | +1.139 |
Neg logit contributions | |
inyl | -1.815 |
ricks | -1.647 |
Rah | -1.646 |
liner | -1.640 |
� | -1.616 |
Token | Un |
Token ID | 791 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
Hunts | +2.505 |
Scand | +2.162 |
Lat | +2.147 |
Amateur | +2.137 |
Engels | +2.135 |
Neg logit contributions | |
inyl | -2.727 |
ricks | -2.463 |
Rah | -2.444 |
liner | -2.430 |
� | -2.377 |
Token | iting |
Token ID | 1780 |
Feature activation | +7.14e+00 |
Pos logit contributions | |
Hunts | +0.309 |
Engels | +0.278 |
Scand | +0.277 |
Lat | +0.276 |
Amateur | +0.275 |
Neg logit contributions | |
inyl | -0.180 |
ricks | -0.155 |
Rah | -0.154 |
liner | -0.153 |
� | -0.151 |
Token | Care |
Token ID | 7276 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
Hunts | +5.057 |
Lat | +4.339 |
Amateur | +4.291 |
Scand | +4.285 |
Cable | +4.247 |
Neg logit contributions | |
inyl | -5.997 |
ricks | -5.412 |
liner | -5.319 |
Rah | -5.316 |
ciples | -5.123 |
Token | 's |
Token ID | 338 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
Hunts | +1.973 |
Engels | +1.704 |
Scand | +1.704 |
Lat | +1.702 |
Amateur | +1.699 |
Neg logit contributions | |
inyl | -2.037 |
ricks | -1.817 |
Rah | -1.806 |
liner | -1.792 |
� | -1.762 |
Token | financial |
Token ID | 3176 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Hunts | +1.954 |
Lat | +1.685 |
Scand | +1.684 |
Engels | +1.683 |
Amateur | +1.677 |
Neg logit contributions | |
inyl | -2.089 |
ricks | -1.887 |
Rah | -1.873 |
liner | -1.867 |
� | -1.831 |
Token | counselling |
Token ID | 47586 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Hunts | +1.284 |
Scand | +1.126 |
Engels | +1.126 |
Lat | +1.120 |
Amateur | +1.114 |
Neg logit contributions | |
inyl | -1.127 |
ricks | -1.001 |
Rah | -0.994 |
liner | -0.986 |
� | -0.974 |
Token | service |
Token ID | 2139 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
Hunts | +0.956 |
Engels | +0.835 |
Scand | +0.834 |
Lat | +0.831 |
Amateur | +0.827 |
Neg logit contributions | |
inyl | -0.874 |
ricks | -0.777 |
Rah | -0.771 |
liner | -0.766 |
� | -0.754 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
Hunts | +0.060 |
Scand | +0.048 |
Engels | +0.048 |
Amateur | +0.046 |
Lat | +0.046 |
Neg logit contributions | |
inyl | -0.134 |
ricks | -0.124 |
liner | -0.124 |
Rah | -0.124 |
� | -0.123 |
Token | { |
Token ID | 1391 |
Feature activation | +5.46e+00 |
Pos logit contributions | |
Hunts | +4.782 |
Lat | +4.126 |
Amateur | +4.019 |
Engels | +3.994 |
Scand | +3.985 |
Neg logit contributions | |
inyl | -6.676 |
ricks | -6.146 |
Rah | -6.048 |
liner | -6.015 |
ciples | -5.961 |
Token | 8 |
Token ID | 23 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
Hunts | +3.651 |
Scand | +3.093 |
Lat | +3.087 |
Engels | +3.062 |
Amateur | +3.030 |
Neg logit contributions | |
inyl | -4.740 |
ricks | -4.321 |
Rah | -4.219 |
liner | -4.205 |
� | -4.185 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
inyl | +0.220 |
ricks | +0.197 |
liner | +0.196 |
Rah | +0.196 |
� | +0.195 |
Neg logit contributions | |
Hunts | -0.232 |
Scand | -0.203 |
Engels | -0.202 |
Amateur | -0.200 |
Lat | -0.199 |
Token | 15 |
Token ID | 1315 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
Hunts | +1.844 |
Engels | +1.561 |
Scand | +1.560 |
Lat | +1.559 |
Amateur | +1.546 |
Neg logit contributions | |
inyl | -2.447 |
ricks | -2.220 |
Rah | -2.205 |
liner | -2.201 |
� | -2.162 |
Token | }, |
Token ID | 5512 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
Hunts | +0.208 |
Scand | +0.164 |
Engels | +0.163 |
Amateur | +0.160 |
Lat | +0.159 |
Neg logit contributions | |
inyl | -0.477 |
ricks | -0.442 |
liner | -0.440 |
Rah | -0.440 |
� | -0.437 |
Token | { |
Token ID | 1391 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
Hunts | +4.543 |
Lat | +3.925 |
Amateur | +3.832 |
Engels | +3.816 |
Scand | +3.806 |
Neg logit contributions | |
inyl | -6.279 |
ricks | -5.779 |
Rah | -5.696 |
liner | -5.645 |
ciples | -5.601 |
Token | 9 |
Token ID | 24 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
Hunts | +2.788 |
Scand | +2.430 |
Lat | +2.408 |
Engels | +2.404 |
Amateur | +2.395 |
Neg logit contributions | |
inyl | -2.739 |
ricks | -2.455 |
Rah | -2.417 |
liner | -2.403 |
� | -2.379 |
Token | , |
Token ID | 11 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
inyl | +0.291 |
ricks | +0.260 |
Rah | +0.260 |
liner | +0.260 |
� | +0.258 |
Neg logit contributions | |
Hunts | -0.308 |
Scand | -0.269 |
Engels | -0.268 |
Amateur | -0.266 |
Lat | -0.264 |
Token | 14 |
Token ID | 1478 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
Hunts | +1.573 |
Scand | +1.333 |
Engels | +1.333 |
Lat | +1.329 |
Amateur | +1.320 |
Neg logit contributions | |
inyl | -2.070 |
ricks | -1.878 |
Rah | -1.869 |
liner | -1.863 |
� | -1.832 |
Token | }, |
Token ID | 5512 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
inyl | +0.471 |
ricks | +0.435 |
liner | +0.435 |
Rah | +0.434 |
� | +0.432 |
Neg logit contributions | |
Hunts | -0.217 |
Scand | -0.175 |
Engels | -0.172 |
Amateur | -0.168 |
Lat | -0.167 |
Token |
|
Token ID | 198 |
Feature activation | +7.55e-02 |
Pos logit contributions | |
inyl | +0.862 |
Rah | +0.764 |
ricks | +0.762 |
liner | +0.760 |
� | +0.759 |
Neg logit contributions | |
Hunts | -1.032 |
Engels | -0.915 |
Scand | -0.911 |
Amateur | -0.900 |
Lat | -0.896 |
Token |
|
Token ID | 198 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
Hunts | +0.069 |
Engels | +0.061 |
Scand | +0.061 |
Amateur | +0.061 |
Lat | +0.061 |
Neg logit contributions | |
inyl | -0.048 |
ricks | -0.042 |
Rah | -0.042 |
liner | -0.042 |
� | -0.041 |
Token | Rated |
Token ID | 15322 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
Hunts | +0.542 |
Engels | +0.452 |
Scand | +0.451 |
Amateur | +0.444 |
Lat | +0.443 |
Neg logit contributions | |
inyl | -0.867 |
ricks | -0.796 |
Rah | -0.793 |
liner | -0.791 |
� | -0.784 |
Token | 5 |
Token ID | 642 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
Hunts | +2.597 |
Amateur | +2.276 |
Lat | +2.269 |
Engels | +2.261 |
Scand | +2.260 |
Neg logit contributions | |
inyl | -2.284 |
ricks | -2.034 |
Rah | -2.021 |
liner | -2.018 |
ciples | -1.962 |
Token | out |
Token ID | 503 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Hunts | +3.660 |
Amateur | +3.146 |
Lat | +3.130 |
Scand | +3.122 |
Engels | +3.110 |
Neg logit contributions | |
inyl | -4.815 |
ricks | -4.385 |
Rah | -4.325 |
liner | -4.308 |
Jinn | -4.221 |
Token | of |
Token ID | 286 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
Hunts | +1.767 |
Engels | +1.520 |
Lat | +1.519 |
Scand | +1.516 |
Amateur | +1.512 |
Neg logit contributions | |
inyl | -1.967 |
ricks | -1.774 |
Rah | -1.747 |
liner | -1.741 |
� | -1.708 |
Token | 5 |
Token ID | 642 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
Hunts | +5.291 |
Lat | +4.667 |
Amateur | +4.521 |
Engels | +4.483 |
Redmond | +4.381 |
Neg logit contributions | |
inyl | -5.548 |
ricks | -4.942 |
liner | -4.852 |
Rah | -4.805 |
ciples | -4.717 |
Token | by |
Token ID | 416 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Hunts | +2.343 |
Lat | +1.923 |
Amateur | +1.888 |
Engels | +1.880 |
Scand | +1.868 |
Neg logit contributions | |
inyl | -4.339 |
ricks | -3.984 |
liner | -3.902 |
Rah | -3.887 |
ciples | -3.877 |
Token | Cory |
Token ID | 28785 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Hunts | +2.695 |
Scand | +2.342 |
Lat | +2.339 |
Amateur | +2.333 |
Engels | +2.326 |
Neg logit contributions | |
inyl | -2.653 |
ricks | -2.386 |
liner | -2.358 |
Rah | -2.353 |
ciples | -2.305 |
Token | B |
Token ID | 33 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
Hunts | +0.016 |
Engels | +0.014 |
Scand | +0.014 |
Amateur | +0.014 |
Lat | +0.014 |
Neg logit contributions | |
inyl | -0.017 |
ricks | -0.015 |
Rah | -0.015 |
liner | -0.015 |
� | -0.015 |
Token | from |
Token ID | 422 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Hunts | +0.197 |
Scand | +0.170 |
Engels | +0.170 |
Amateur | +0.169 |
Lat | +0.168 |
Neg logit contributions | |
inyl | -0.221 |
ricks | -0.200 |
Rah | -0.198 |
liner | -0.198 |
� | -0.196 |
Token | use |
Token ID | 779 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Hunts | +0.786 |
Scand | +0.668 |
Engels | +0.667 |
Lat | +0.658 |
Amateur | +0.657 |
Neg logit contributions | |
inyl | -1.033 |
ricks | -0.941 |
Rah | -0.936 |
liner | -0.934 |
� | -0.923 |
Token | it |
Token ID | 340 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Hunts | +0.153 |
Scand | +0.134 |
Engels | +0.134 |
Amateur | +0.133 |
Lat | +0.133 |
Neg logit contributions | |
inyl | -0.141 |
ricks | -0.126 |
Rah | -0.125 |
liner | -0.125 |
� | -0.124 |
Token | to |
Token ID | 284 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
inyl | +0.199 |
ricks | +0.177 |
Rah | +0.176 |
liner | +0.176 |
� | +0.174 |
Neg logit contributions | |
Hunts | -0.229 |
Scand | -0.201 |
Engels | -0.201 |
Amateur | -0.200 |
Lat | -0.199 |
Token | ' |
Token ID | 705 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Hunts | +0.290 |
Engels | +0.248 |
Scand | +0.247 |
Amateur | +0.245 |
Lat | +0.245 |
Neg logit contributions | |
inyl | -0.350 |
ricks | -0.318 |
Rah | -0.316 |
liner | -0.315 |
� | -0.312 |
Token | lead |
Token ID | 28230 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Hunts | +0.593 |
Engels | +0.518 |
Scand | +0.517 |
Lat | +0.515 |
Amateur | +0.514 |
Neg logit contributions | |
inyl | -0.526 |
ricks | -0.467 |
Rah | -0.463 |
liner | -0.461 |
� | -0.457 |
Token | by |
Token ID | 416 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
Hunts | +0.887 |
Engels | +0.725 |
Scand | +0.723 |
Lat | +0.723 |
Amateur | +0.721 |
Neg logit contributions | |
inyl | -1.478 |
ricks | -1.365 |
liner | -1.347 |
Rah | -1.346 |
� | -1.331 |
Token | example |
Token ID | 1672 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Hunts | +4.902 |
Lat | +4.371 |
Engels | +4.331 |
Amateur | +4.259 |
Redmond | +4.180 |
Neg logit contributions | |
inyl | -5.704 |
ricks | -5.290 |
Rah | -5.093 |
liner | -4.978 |
ciples | -4.935 |
Token | with |
Token ID | 351 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Hunts | +0.824 |
Scand | +0.712 |
Engels | +0.709 |
Lat | +0.705 |
Amateur | +0.701 |
Neg logit contributions | |
inyl | -0.890 |
ricks | -0.801 |
Rah | -0.793 |
liner | -0.792 |
� | -0.781 |
Token | hope |
Token ID | 2911 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Hunts | +1.345 |
Engels | +1.100 |
Scand | +1.096 |
Lat | +1.096 |
Amateur | +1.086 |
Neg logit contributions | |
inyl | -2.259 |
ricks | -2.077 |
liner | -2.062 |
Rah | -2.061 |
� | -2.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Hunts | +1.691 |
Scand | +1.451 |
Engels | +1.448 |
Lat | +1.439 |
Amateur | +1.435 |
Neg logit contributions | |
inyl | -1.891 |
ricks | -1.718 |
liner | -1.693 |
Rah | -1.690 |
� | -1.654 |
Token | never |
Token ID | 1239 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Hunts | +1.395 |
Scand | +1.185 |
Engels | +1.184 |
Lat | +1.175 |
Amateur | +1.172 |
Neg logit contributions | |
inyl | -1.784 |
ricks | -1.625 |
Rah | -1.613 |
liner | -1.611 |
� | -1.591 |
Token | k |
Token ID | 479 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Hunts | +1.079 |
Scand | +0.941 |
Engels | +0.939 |
Amateur | +0.932 |
Lat | +0.932 |
Neg logit contributions | |
inyl | -1.049 |
ricks | -0.943 |
Rah | -0.935 |
liner | -0.933 |
� | -0.920 |
Token | imp |
Token ID | 11011 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Hunts | +1.913 |
Scand | +1.668 |
Engels | +1.665 |
Amateur | +1.659 |
Lat | +1.658 |
Neg logit contributions | |
inyl | -1.733 |
Rah | -1.549 |
ricks | -1.546 |
liner | -1.528 |
� | -1.525 |
Token | unk |
Token ID | 2954 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Hunts | +0.493 |
Scand | +0.428 |
Engels | +0.428 |
Amateur | +0.424 |
Lat | +0.423 |
Neg logit contributions | |
inyl | -0.502 |
ricks | -0.451 |
Rah | -0.448 |
liner | -0.447 |
� | -0.443 |
Token | rock |
Token ID | 10823 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Hunts | +0.334 |
Scand | +0.285 |
Engels | +0.285 |
Amateur | +0.282 |
Lat | +0.282 |
Neg logit contributions | |
inyl | -0.405 |
ricks | -0.367 |
Rah | -0.365 |
liner | -0.364 |
� | -0.361 |
Token | - |
Token ID | 532 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Hunts | +0.720 |
Scand | +0.610 |
Engels | +0.609 |
Amateur | +0.603 |
Lat | +0.602 |
Neg logit contributions | |
inyl | -0.971 |
ricks | -0.885 |
Rah | -0.880 |
liner | -0.877 |
� | -0.869 |
Token | favorite |
Token ID | 4004 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Hunts | +2.105 |
Lat | +1.819 |
Scand | +1.812 |
Amateur | +1.810 |
Engels | +1.777 |
Neg logit contributions | |
inyl | -2.292 |
ricks | -2.105 |
Rah | -2.077 |
liner | -2.064 |
ciples | -2.040 |
Token | favorite |
Token ID | 4004 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
Hunts | +4.778 |
Lat | +4.102 |
Scand | +4.072 |
Amateur | +4.059 |
Engels | +3.961 |
Neg logit contributions | |
inyl | -5.843 |
ricks | -5.474 |
Rah | -5.352 |
ciples | -5.280 |
liner | -5.223 |
Token | favorite |
Token ID | 4004 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Hunts | +4.678 |
Lat | +4.005 |
Scand | +3.989 |
Amateur | +3.956 |
Engels | +3.890 |
Neg logit contributions | |
inyl | -5.603 |
ricks | -5.238 |
Rah | -5.127 |
ciples | -5.048 |
liner | -5.006 |
Token | favorite |
Token ID | 4004 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
Hunts | +3.868 |
Scand | +3.315 |
Lat | +3.298 |
Amateur | +3.273 |
Engels | +3.245 |
Neg logit contributions | |
inyl | -4.444 |
ricks | -4.110 |
Rah | -4.050 |
liner | -3.971 |
ciples | -3.968 |
Token | - |
Token ID | 532 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Hunts | +2.402 |
Scand | +2.051 |
Lat | +2.034 |
Amateur | +2.026 |
Engels | +2.023 |
Neg logit contributions | |
inyl | -2.886 |
ricks | -2.650 |
Rah | -2.620 |
liner | -2.589 |
ciples | -2.559 |
Token | December |
Token ID | 3426 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Hunts | +1.095 |
Scand | +0.968 |
Engels | +0.966 |
Lat | +0.962 |
Amateur | +0.961 |
Neg logit contributions | |
inyl | -0.830 |
ricks | -0.732 |
Rah | -0.725 |
liner | -0.723 |
� | -0.713 |
Token | command |
Token ID | 3141 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
inyl | +1.737 |
� | +1.567 |
ricks | +1.561 |
liner | +1.561 |
Rah | +1.542 |
Neg logit contributions | |
Hunts | -1.591 |
Engels | -1.391 |
Amateur | -1.384 |
Scand | -1.381 |
Lat | -1.351 |
Token | sl |
Token ID | 1017 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
inyl | +1.334 |
ricks | +1.191 |
liner | +1.184 |
� | +1.183 |
Rah | +1.170 |
Neg logit contributions | |
Hunts | -1.442 |
Engels | -1.273 |
Scand | -1.266 |
Amateur | -1.261 |
Lat | -1.246 |
Token | s |
Token ID | 82 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
Hunts | +1.285 |
Scand | +1.091 |
Engels | +1.091 |
Amateur | +1.079 |
Lat | +1.077 |
Neg logit contributions | |
inyl | -1.676 |
ricks | -1.525 |
Rah | -1.517 |
liner | -1.513 |
� | -1.500 |
Token | logs |
Token ID | 17259 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Hunts | +2.608 |
Scand | +2.221 |
Lat | +2.196 |
Engels | +2.193 |
Amateur | +2.168 |
Neg logit contributions | |
inyl | -3.366 |
ricks | -3.059 |
liner | -3.045 |
Rah | -3.042 |
ciples | -2.963 |
Token | - |
Token ID | 532 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
Hunts | +1.354 |
Scand | +1.160 |
Engels | +1.156 |
Lat | +1.147 |
Amateur | +1.146 |
Neg logit contributions | |
inyl | -1.628 |
ricks | -1.477 |
Rah | -1.468 |
liner | -1.464 |
� | -1.446 |
Token | f |
Token ID | 69 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
Hunts | +3.210 |
Scand | +2.786 |
Lat | +2.783 |
Amateur | +2.755 |
Engels | +2.739 |
Neg logit contributions | |
inyl | -3.528 |
ricks | -3.178 |
Rah | -3.155 |
� | -3.120 |
liner | -3.113 |
Token | test |
Token ID | 1332 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
Hunts | +4.720 |
Scand | +4.043 |
Lat | +4.037 |
Amateur | +3.945 |
Engels | +3.906 |
Neg logit contributions | |
inyl | -5.936 |
ricks | -5.398 |
Rah | -5.388 |
liner | -5.336 |
ciples | -5.262 |
Token | -- |
Token ID | 1377 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Hunts | +1.839 |
Scand | +1.586 |
Engels | +1.573 |
Lat | +1.572 |
Amateur | +1.563 |
Neg logit contributions | |
inyl | -2.049 |
ricks | -1.853 |
Rah | -1.842 |
liner | -1.830 |
� | -1.799 |
Token | start |
Token ID | 9688 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Hunts | +2.210 |
Scand | +1.912 |
Lat | +1.906 |
Engels | +1.892 |
Amateur | +1.888 |
Neg logit contributions | |
inyl | -2.404 |
Rah | -2.162 |
ricks | -2.159 |
liner | -2.132 |
� | -2.120 |
Token | Time |
Token ID | 7575 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
inyl | +0.833 |
ricks | +0.753 |
liner | +0.750 |
Rah | +0.744 |
� | +0.743 |
Neg logit contributions | |
Hunts | -0.793 |
Engels | -0.694 |
Scand | -0.688 |
Amateur | -0.682 |
Lat | -0.673 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
Hunts | +0.930 |
Scand | +0.809 |
Engels | +0.806 |
Lat | +0.803 |
Amateur | +0.801 |
Neg logit contributions | |
inyl | -0.928 |
ricks | -0.832 |
Rah | -0.827 |
liner | -0.825 |
� | -0.814 |
Token | with |
Token ID | 351 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
inyl | +0.470 |
ricks | +0.422 |
Rah | +0.420 |
liner | +0.417 |
� | +0.412 |
Neg logit contributions | |
Hunts | -0.465 |
Scand | -0.404 |
Engels | -0.403 |
Amateur | -0.401 |
Lat | -0.400 |
Token | a |
Token ID | 257 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Hunts | +2.276 |
Lat | +1.945 |
Scand | +1.944 |
Amateur | +1.942 |
Engels | +1.938 |
Neg logit contributions | |
inyl | -2.582 |
ricks | -2.341 |
Rah | -2.332 |
liner | -2.330 |
� | -2.254 |
Token | Gl |
Token ID | 2671 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
Hunts | +2.296 |
Lat | +1.952 |
Scand | +1.932 |
Amateur | +1.924 |
Engels | +1.914 |
Neg logit contributions | |
inyl | -3.067 |
Rah | -2.797 |
ricks | -2.797 |
liner | -2.756 |
� | -2.688 |
Token | ance |
Token ID | 590 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Hunts | +4.928 |
Lat | +4.359 |
Amateur | +4.354 |
Engels | +4.341 |
Scand | +4.301 |
Neg logit contributions | |
inyl | -4.584 |
Rah | -4.131 |
ricks | -4.064 |
Jinn | -4.044 |
liner | -4.006 |
Token | at |
Token ID | 379 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Hunts | +0.202 |
Scand | +0.178 |
Engels | +0.178 |
Amateur | +0.177 |
Lat | +0.177 |
Neg logit contributions | |
inyl | -0.162 |
ricks | -0.143 |
Rah | -0.142 |
liner | -0.141 |
� | -0.139 |
Token | Bad |
Token ID | 7772 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
Hunts | +3.139 |
Lat | +2.684 |
Scand | +2.684 |
Amateur | +2.670 |
Engels | +2.625 |
Neg logit contributions | |
inyl | -3.740 |
liner | -3.388 |
Rah | -3.387 |
ricks | -3.360 |
ciples | -3.270 |
Token | Hab |
Token ID | 19654 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Hunts | +3.207 |
Lat | +2.541 |
Amateur | +2.441 |
Scand | +2.439 |
Engels | +2.395 |
Neg logit contributions | |
inyl | -7.724 |
liner | -7.082 |
ricks | -7.073 |
Rah | -7.016 |
ciples | -6.862 |
Token | its |
Token ID | 896 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
Hunts | +1.342 |
Engels | +1.127 |
Lat | +1.125 |
Scand | +1.113 |
Amateur | +1.110 |
Neg logit contributions | |
inyl | -1.878 |
Rah | -1.711 |
liner | -1.701 |
ricks | -1.690 |
� | -1.678 |
Token | , |
Token ID | 11 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
Hunts | +0.237 |
Engels | +0.206 |
Scand | +0.206 |
Amateur | +0.204 |
Lat | +0.204 |
Neg logit contributions | |
inyl | -0.244 |
ricks | -0.219 |
Rah | -0.218 |
liner | -0.217 |
� | -0.214 |
Token | 18 |
Token ID | 1248 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Hunts | +0.423 |
Engels | +0.356 |
Scand | +0.355 |
Amateur | +0.352 |
Lat | +0.350 |
Neg logit contributions | |
inyl | -0.628 |
ricks | -0.573 |
Rah | -0.570 |
liner | -0.569 |
� | -0.563 |
Token | 44 |
Token ID | 2598 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
Hunts | +0.817 |
Scand | +0.666 |
Engels | +0.664 |
Amateur | +0.657 |
Lat | +0.655 |
Neg logit contributions | |
inyl | -1.536 |
ricks | -1.415 |
liner | -1.403 |
Rah | -1.403 |
� | -1.388 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
Hunts | +0.486 |
Scand | +0.381 |
Engels | +0.380 |
Amateur | +0.374 |
Lat | +0.373 |
Neg logit contributions | |
inyl | -1.122 |
ricks | -1.041 |
Rah | -1.036 |
liner | -1.034 |
� | -1.027 |
Token | {{ |
Token ID | 22935 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
Hunts | +4.474 |
Lat | +3.828 |
Scand | +3.812 |
Engels | +3.771 |
Amateur | +3.740 |
Neg logit contributions | |
inyl | -5.672 |
ricks | -5.207 |
Rah | -5.194 |
liner | -5.145 |
ciples | -5.044 |
Token | 1 |
Token ID | 16 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
Hunts | +3.217 |
Scand | +2.784 |
Lat | +2.760 |
Engels | +2.760 |
Amateur | +2.707 |
Neg logit contributions | |
inyl | -3.835 |
ricks | -3.495 |
Rah | -3.471 |
liner | -3.437 |
� | -3.416 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Hunts | +0.764 |
Engels | +0.664 |
Scand | +0.664 |
Amateur | +0.658 |
Lat | +0.657 |
Neg logit contributions | |
inyl | -0.765 |
ricks | -0.687 |
Rah | -0.682 |
liner | -0.681 |
� | -0.674 |
Token | 6 |
Token ID | 718 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
Hunts | +1.778 |
Scand | +1.556 |
Engels | +1.555 |
Lat | +1.546 |
Amateur | +1.544 |
Neg logit contributions | |
inyl | -1.621 |
ricks | -1.449 |
Rah | -1.433 |
liner | -1.431 |
� | -1.408 |
Token | }, |
Token ID | 5512 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
Hunts | +0.324 |
Scand | +0.254 |
Engels | +0.254 |
Amateur | +0.250 |
Lat | +0.249 |
Neg logit contributions | |
inyl | -0.747 |
ricks | -0.693 |
Rah | -0.689 |
liner | -0.689 |
� | -0.684 |
Token | { |
Token ID | 1391 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
Hunts | +4.592 |
Lat | +3.911 |
Scand | +3.898 |
Engels | +3.847 |
Amateur | +3.815 |
Neg logit contributions | |
inyl | -6.019 |
ricks | -5.542 |
Rah | -5.527 |
liner | -5.471 |
ciples | -5.374 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Hunts | +2.365 |
Scand | +2.019 |
Engels | +2.014 |
Lat | +2.004 |
Amateur | +1.985 |
Neg logit contributions | |
inyl | -2.943 |
ricks | -2.670 |
Rah | -2.647 |
liner | -2.641 |
� | -2.610 |
Token | , |
Token ID | 11 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
inyl | +0.763 |
Rah | +0.682 |
liner | +0.682 |
� | +0.682 |
ricks | +0.679 |
Neg logit contributions | |
Hunts | -0.839 |
Scand | -0.740 |
Engels | -0.734 |
Amateur | -0.726 |
Lat | -0.720 |
Token | 7 |
Token ID | 767 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Hunts | +2.163 |
Scand | +1.882 |
Engels | +1.880 |
Lat | +1.872 |
Amateur | +1.867 |
Neg logit contributions | |
inyl | -2.132 |
ricks | -1.914 |
Rah | -1.891 |
liner | -1.885 |
� | -1.853 |
Token | }, |
Token ID | 5512 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
Hunts | +1.056 |
Engels | +0.827 |
Scand | +0.825 |
Lat | +0.814 |
Amateur | +0.813 |
Neg logit contributions | |
inyl | -2.422 |
ricks | -2.246 |
Rah | -2.237 |
liner | -2.229 |
� | -2.212 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Hunts | +0.352 |
Engels | +0.302 |
Scand | +0.302 |
Amateur | +0.299 |
Lat | +0.299 |
Neg logit contributions | |
inyl | -0.419 |
ricks | -0.379 |
Rah | -0.376 |
liner | -0.375 |
� | -0.371 |
Token | 25 |
Token ID | 1495 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
Hunts | +0.286 |
Scand | +0.244 |
Engels | +0.244 |
Amateur | +0.241 |
Lat | +0.241 |
Neg logit contributions | |
inyl | -0.364 |
ricks | -0.331 |
Rah | -0.328 |
liner | -0.328 |
� | -0.325 |
Token | million |
Token ID | 1510 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
inyl | +0.840 |
ricks | +0.763 |
Rah | +0.759 |
liner | +0.757 |
� | +0.750 |
Neg logit contributions | |
Hunts | -0.659 |
Scand | -0.562 |
Engels | -0.561 |
Amateur | -0.556 |
Lat | -0.555 |
Token | ( |
Token ID | 357 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
inyl | +0.208 |
ricks | +0.184 |
Rah | +0.182 |
liner | +0.182 |
� | +0.179 |
Neg logit contributions | |
Hunts | -0.274 |
Scand | -0.243 |
Engels | -0.242 |
Amateur | -0.241 |
Lat | -0.240 |
Token | 21 |
Token ID | 2481 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
inyl | +2.902 |
ricks | +2.682 |
Rah | +2.679 |
liner | +2.670 |
� | +2.628 |
Neg logit contributions | |
Hunts | -2.398 |
Engels | -2.065 |
Scand | -2.057 |
Amateur | -2.026 |
Lat | -2.004 |
Token | st |
Token ID | 301 |
Feature activation | -7.98e+00 |
Pos logit contributions | |
inyl | +3.020 |
ricks | +2.818 |
liner | +2.781 |
� | +2.774 |
Rah | +2.741 |
Neg logit contributions | |
Hunts | -2.381 |
Engels | -2.027 |
Scand | -2.012 |
Lat | -1.955 |
Amateur | -1.955 |
Token | among |
Token ID | 1871 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
inyl | +5.327 |
� | +4.859 |
liner | +4.812 |
ricks | +4.699 |
Rah | +4.661 |
Neg logit contributions | |
Hunts | -6.586 |
Engels | -5.786 |
Scand | -5.739 |
Amateur | -5.682 |
Redmond | -5.617 |
Token | guards |
Token ID | 10942 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
inyl | +4.444 |
ricks | +4.145 |
� | +4.126 |
liner | +4.118 |
Rah | +4.056 |
Neg logit contributions | |
Hunts | -4.918 |
Engels | -4.368 |
Amateur | -4.222 |
Scand | -4.215 |
Redmond | -4.116 |
Token | ) |
Token ID | 8 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
inyl | +1.615 |
ricks | +1.441 |
liner | +1.437 |
� | +1.428 |
Rah | +1.426 |
Neg logit contributions | |
Hunts | -1.792 |
Engels | -1.572 |
Scand | -1.564 |
Amateur | -1.549 |
Lat | -1.543 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Hunts | +0.832 |
Scand | +0.736 |
Engels | +0.730 |
Amateur | +0.730 |
Lat | +0.728 |
Neg logit contributions | |
inyl | -0.631 |
ricks | -0.556 |
Rah | -0.554 |
liner | -0.550 |
� | -0.535 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
inyl | +0.827 |
ricks | +0.723 |
Rah | +0.721 |
liner | +0.719 |
� | +0.718 |
Neg logit contributions | |
Hunts | -1.241 |
Scand | -1.110 |
Engels | -1.107 |
Amateur | -1.097 |
Lat | -1.089 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
Hunts | +0.049 |
Engels | +0.039 |
Scand | +0.039 |
Amateur | +0.039 |
Lat | +0.039 |
Neg logit contributions | |
inyl | -0.095 |
ricks | -0.088 |
Rah | -0.087 |
liner | -0.087 |
� | -0.087 |
Token | | |
Token ID | 930 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Hunts | +1.481 |
Scand | +1.267 |
Lat | +1.259 |
Engels | +1.255 |
Amateur | +1.250 |
Neg logit contributions | |
inyl | -1.933 |
ricks | -1.764 |
Rah | -1.748 |
liner | -1.730 |
� | -1.702 |
Token | + |
Token ID | 1343 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
inyl | +0.705 |
ricks | +0.597 |
liner | +0.590 |
Rah | +0.590 |
� | +0.587 |
Neg logit contributions | |
Hunts | -1.411 |
Engels | -1.276 |
Scand | -1.273 |
Amateur | -1.266 |
Lat | -1.260 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
inyl | +3.726 |
Rah | +3.463 |
ricks | +3.427 |
� | +3.384 |
liner | +3.323 |
Neg logit contributions | |
Hunts | -3.832 |
Scand | -3.414 |
Engels | -3.340 |
Amateur | -3.296 |
Lat | -3.280 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
inyl | +0.228 |
ricks | +0.185 |
Rah | +0.182 |
liner | +0.182 |
� | +0.181 |
Neg logit contributions | |
Hunts | -0.600 |
Scand | -0.546 |
Engels | -0.546 |
Amateur | -0.541 |
Lat | -0.540 |
Token | + |
Token ID | 1343 |
Feature activation | -7.93e+00 |
Pos logit contributions | |
inyl | +1.277 |
ricks | +1.072 |
liner | +1.062 |
Rah | +1.061 |
� | +1.055 |
Neg logit contributions | |
Hunts | -2.715 |
Engels | -2.461 |
Scand | -2.453 |
Amateur | -2.442 |
Lat | -2.428 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
inyl | +5.440 |
Rah | +5.186 |
ricks | +5.050 |
� | +5.027 |
liner | +4.846 |
Neg logit contributions | |
Hunts | -6.397 |
Scand | -5.815 |
Engels | -5.633 |
Amateur | -5.547 |
Lat | -5.518 |
Token | --+ |
Token ID | 44785 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
inyl | +0.862 |
� | +0.688 |
ricks | +0.685 |
Rah | +0.673 |
liner | +0.670 |
Neg logit contributions | |
Hunts | -2.529 |
Scand | -2.307 |
Engels | -2.305 |
Amateur | -2.275 |
Lat | -2.272 |
Token | < |
Token ID | 1279 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
inyl | +2.555 |
ricks | +2.292 |
liner | +2.289 |
� | +2.287 |
Rah | +2.271 |
Neg logit contributions | |
Hunts | -2.560 |
Engels | -2.236 |
Scand | -2.225 |
Amateur | -2.209 |
Lat | -2.185 |
Token | -- |
Token ID | 438 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
inyl | +1.183 |
liner | +1.099 |
Rah | +1.096 |
ricks | +1.095 |
� | +1.091 |
Neg logit contributions | |
Hunts | -0.629 |
Scand | -0.516 |
Engels | -0.511 |
Amateur | -0.504 |
Lat | -0.491 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
inyl | +0.559 |
ricks | +0.501 |
Rah | +0.498 |
liner | +0.497 |
� | +0.493 |
Neg logit contributions | |
Hunts | -0.558 |
Engels | -0.485 |
Scand | -0.485 |
Amateur | -0.481 |
Lat | -0.479 |
Token | fun |
Token ID | 1257 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
inyl | +0.014 |
ricks | +0.012 |
Rah | +0.012 |
liner | +0.012 |
� | +0.012 |
Neg logit contributions | |
Hunts | -0.014 |
Scand | -0.012 |
Engels | -0.012 |
Amateur | -0.012 |
Lat | -0.012 |
Token | cs |
Token ID | 6359 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Hunts | +0.595 |
Scand | +0.527 |
Engels | +0.526 |
Amateur | +0.523 |
Lat | +0.522 |
Neg logit contributions | |
inyl | -0.452 |
ricks | -0.397 |
Rah | -0.396 |
liner | -0.393 |
� | -0.388 |
Token | will |
Token ID | 481 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
inyl | +1.016 |
ricks | +0.913 |
liner | +0.905 |
Rah | +0.903 |
� | +0.901 |
Neg logit contributions | |
Hunts | -1.057 |
Scand | -0.922 |
Engels | -0.921 |
Amateur | -0.912 |
Lat | -0.910 |
Token | go |
Token ID | 467 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
inyl | +0.777 |
ricks | +0.697 |
Rah | +0.691 |
liner | +0.691 |
� | +0.685 |
Neg logit contributions | |
Hunts | -0.794 |
Scand | -0.691 |
Engels | -0.691 |
Amateur | -0.685 |
Lat | -0.683 |
Token | here |
Token ID | 994 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
inyl | +0.528 |
ricks | +0.474 |
Rah | +0.471 |
liner | +0.469 |
� | +0.463 |
Neg logit contributions | |
Hunts | -0.529 |
Scand | -0.460 |
Engels | -0.459 |
Amateur | -0.456 |
Lat | -0.455 |
Token | + |
Token ID | 1343 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
inyl | +1.635 |
ricks | +1.461 |
liner | +1.451 |
Rah | +1.446 |
� | +1.441 |
Neg logit contributions | |
Hunts | -1.863 |
Engels | -1.640 |
Scand | -1.633 |
Amateur | -1.617 |
Lat | -1.611 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
inyl | +5.794 |
ricks | +5.344 |
Rah | +5.340 |
� | +5.308 |
liner | +5.213 |
Neg logit contributions | |
Hunts | -5.876 |
Engels | -5.160 |
Scand | -5.135 |
Amateur | -5.028 |
Lat | -4.987 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
inyl | +1.374 |
ricks | +1.118 |
Rah | +1.105 |
liner | +1.100 |
� | +1.095 |
Neg logit contributions | |
Hunts | -3.608 |
Engels | -3.300 |
Scand | -3.287 |
Amateur | -3.262 |
Lat | -3.249 |
Token | + |
Token ID | 1343 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
inyl | +1.002 |
ricks | +0.901 |
Rah | +0.895 |
liner | +0.894 |
� | +0.885 |
Neg logit contributions | |
Hunts | -0.972 |
Engels | -0.843 |
Scand | -0.843 |
Amateur | -0.835 |
Lat | -0.833 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
inyl | +4.678 |
ricks | +4.288 |
Rah | +4.285 |
� | +4.243 |
liner | +4.221 |
Neg logit contributions | |
Hunts | -4.555 |
Engels | -3.984 |
Scand | -3.962 |
Amateur | -3.909 |
Lat | -3.859 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
inyl | +0.183 |
ricks | +0.151 |
Rah | +0.149 |
liner | +0.148 |
� | +0.146 |
Neg logit contributions | |
Hunts | -0.441 |
Scand | -0.400 |
Engels | -0.400 |
Amateur | -0.398 |
Lat | -0.397 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Hunts | +0.410 |
Scand | +0.331 |
Engels | +0.330 |
Amateur | +0.326 |
Lat | +0.326 |
Neg logit contributions | |
inyl | -0.794 |
ricks | -0.733 |
Rah | -0.729 |
liner | -0.727 |
� | -0.721 |
Token | | |
Token ID | 930 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Hunts | +1.447 |
Scand | +1.237 |
Engels | +1.229 |
Lat | +1.224 |
Amateur | +1.217 |
Neg logit contributions | |
inyl | -1.839 |
ricks | -1.678 |
Rah | -1.661 |
liner | -1.649 |
� | -1.622 |
Token | + |
Token ID | 1343 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
inyl | +0.610 |
ricks | +0.527 |
liner | +0.522 |
Rah | +0.521 |
� | +0.520 |
Neg logit contributions | |
Hunts | -0.995 |
Engels | -0.893 |
Scand | -0.890 |
Amateur | -0.886 |
Lat | -0.881 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
inyl | +3.362 |
Rah | +3.113 |
ricks | +3.086 |
� | +3.047 |
liner | +2.993 |
Neg logit contributions | |
Hunts | -3.418 |
Scand | -3.031 |
Engels | -2.972 |
Amateur | -2.937 |
Lat | -2.922 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
inyl | +0.475 |
ricks | +0.383 |
� | +0.378 |
Rah | +0.377 |
liner | +0.376 |
Neg logit contributions | |
Hunts | -1.312 |
Scand | -1.196 |
Engels | -1.193 |
Amateur | -1.181 |
Lat | -1.181 |
Token | + |
Token ID | 1343 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
inyl | +1.536 |
ricks | +1.313 |
liner | +1.302 |
Rah | +1.301 |
� | +1.298 |
Neg logit contributions | |
Hunts | -2.815 |
Engels | -2.539 |
Scand | -2.530 |
Amateur | -2.521 |
Lat | -2.503 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
inyl | +5.328 |
Rah | +5.065 |
ricks | +4.924 |
� | +4.907 |
liner | +4.737 |
Neg logit contributions | |
Hunts | -6.239 |
Scand | -5.660 |
Engels | -5.478 |
Amateur | -5.404 |
Lat | -5.370 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
inyl | +0.892 |
� | +0.712 |
ricks | +0.708 |
Rah | +0.694 |
liner | +0.693 |
Neg logit contributions | |
Hunts | -2.653 |
Scand | -2.423 |
Engels | -2.417 |
Amateur | -2.386 |
Lat | -2.384 |
Token | < |
Token ID | 1279 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
inyl | +2.069 |
ricks | +1.857 |
liner | +1.852 |
� | +1.847 |
Rah | +1.842 |
Neg logit contributions | |
Hunts | -2.010 |
Engels | -1.751 |
Scand | -1.744 |
Amateur | -1.731 |
Lat | -1.715 |
Token | -- |
Token ID | 438 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
inyl | +0.634 |
liner | +0.587 |
ricks | +0.586 |
Rah | +0.586 |
� | +0.583 |
Neg logit contributions | |
Hunts | -0.329 |
Scand | -0.269 |
Engels | -0.266 |
Amateur | -0.263 |
Lat | -0.257 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Hunts | +0.323 |
Scand | +0.280 |
Engels | +0.279 |
Lat | +0.277 |
Amateur | +0.276 |
Neg logit contributions | |
inyl | -0.346 |
ricks | -0.312 |
Rah | -0.310 |
liner | -0.309 |
� | -0.305 |
Token | Image |
Token ID | 5159 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
Hunts | +2.373 |
Scand | +2.094 |
Engels | +2.084 |
Lat | +2.079 |
Amateur | +2.078 |
Neg logit contributions | |
inyl | -1.886 |
ricks | -1.659 |
liner | -1.639 |
Rah | -1.620 |
� | -1.619 |
Token | by |
Token ID | 416 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
inyl | +0.029 |
ricks | +0.024 |
Rah | +0.024 |
liner | +0.024 |
� | +0.024 |
Neg logit contributions | |
Hunts | -0.064 |
Scand | -0.058 |
Engels | -0.058 |
Amateur | -0.057 |
Lat | -0.057 |
Token | Boston |
Token ID | 6182 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Hunts | +0.035 |
Scand | +0.030 |
Engels | +0.030 |
Amateur | +0.029 |
Lat | +0.029 |
Neg logit contributions | |
inyl | -0.038 |
ricks | -0.034 |
Rah | -0.034 |
liner | -0.034 |
� | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Hunts | +1.225 |
Scand | +1.041 |
Engels | +1.041 |
Amateur | +1.033 |
Lat | +1.030 |
Neg logit contributions | |
inyl | -1.562 |
ricks | -1.418 |
Rah | -1.410 |
liner | -1.407 |
� | -1.393 |
Token | com |
Token ID | 785 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
inyl | +0.193 |
ricks | +0.175 |
Rah | +0.174 |
liner | +0.173 |
� | +0.172 |
Neg logit contributions | |
Hunts | -0.169 |
Scand | -0.146 |
Engels | -0.146 |
Amateur | -0.144 |
Lat | -0.144 |
Token | The |
Token ID | 383 |
Feature activation | -7.47e+00 |
Pos logit contributions | |
Hunts | +0.664 |
Scand | +0.579 |
Engels | +0.579 |
Amateur | +0.573 |
Lat | +0.572 |
Neg logit contributions | |
inyl | -0.643 |
ricks | -0.576 |
Rah | -0.572 |
liner | -0.571 |
� | -0.565 |
Token | old |
Token ID | 1468 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
inyl | +4.564 |
ricks | +3.983 |
liner | +3.964 |
� | +3.948 |
Rah | +3.922 |
Neg logit contributions | |
Hunts | -6.461 |
Scand | -5.844 |
Engels | -5.822 |
Lat | -5.759 |
Amateur | -5.719 |
Token | building |
Token ID | 16894 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
inyl | +3.136 |
ricks | +2.911 |
liner | +2.896 |
Rah | +2.881 |
� | +2.866 |
Neg logit contributions | |
Hunts | -1.635 |
Scand | -1.355 |
Engels | -1.326 |
Lat | -1.316 |
Amateur | -1.294 |
Token | was |
Token ID | 373 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
inyl | +1.353 |
ricks | +1.225 |
Rah | +1.216 |
� | +1.209 |
liner | +1.208 |
Neg logit contributions | |
Hunts | -1.058 |
Engels | -0.915 |
Scand | -0.909 |
Amateur | -0.902 |
Lat | -0.897 |
Token | renamed |
Token ID | 25121 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
inyl | +1.779 |
ricks | +1.604 |
Rah | +1.589 |
� | +1.583 |
liner | +1.569 |
Neg logit contributions | |
Hunts | -1.605 |
Engels | -1.403 |
Scand | -1.395 |
Amateur | -1.391 |
Lat | -1.376 |
Token | for |
Token ID | 1640 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
inyl | +3.404 |
ricks | +3.117 |
Rah | +3.107 |
liner | +3.050 |
� | +3.035 |
Neg logit contributions | |
Hunts | -3.097 |
Scand | -2.749 |
Engels | -2.700 |
Lat | -2.686 |
Amateur | -2.671 |
Token | has |
Token ID | 468 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
inyl | +1.218 |
ricks | +1.089 |
Rah | +1.083 |
liner | +1.083 |
� | +1.078 |
Neg logit contributions | |
Hunts | -1.240 |
Scand | -1.087 |
Engels | -1.082 |
Amateur | -1.078 |
Lat | -1.067 |
Token | repeatedly |
Token ID | 7830 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Hunts | +0.083 |
Scand | +0.072 |
Engels | +0.072 |
Amateur | +0.071 |
Lat | +0.071 |
Neg logit contributions | |
inyl | -0.085 |
ricks | -0.076 |
Rah | -0.076 |
liner | -0.075 |
� | -0.075 |
Token | criticized |
Token ID | 12318 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
Hunts | +0.109 |
Engels | +0.094 |
Scand | +0.094 |
Amateur | +0.093 |
Lat | +0.093 |
Neg logit contributions | |
inyl | -0.111 |
ricks | -0.100 |
Rah | -0.099 |
liner | -0.099 |
� | -0.098 |
Token | President |
Token ID | 1992 |
Feature activation | -9.94e-01 |
Pos logit contributions | |
inyl | +0.533 |
ricks | +0.478 |
Rah | +0.476 |
liner | +0.474 |
� | +0.470 |
Neg logit contributions | |
Hunts | -0.548 |
Scand | -0.478 |
Engels | -0.477 |
Amateur | -0.474 |
Lat | -0.471 |
Token | Trump |
Token ID | 1301 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
inyl | +0.681 |
ricks | +0.601 |
Rah | +0.600 |
liner | +0.597 |
� | +0.592 |
Neg logit contributions | |
Hunts | -0.856 |
Engels | -0.759 |
Scand | -0.758 |
Amateur | -0.753 |
Lat | -0.748 |
Token | Donald |
Token ID | 3759 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
inyl | +1.124 |
ricks | +1.009 |
Rah | +1.001 |
liner | +1.001 |
� | +0.991 |
Neg logit contributions | |
Hunts | -1.161 |
Scand | -1.013 |
Engels | -1.012 |
Amateur | -1.003 |
Lat | -0.999 |
Token | John |
Token ID | 1757 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
inyl | +4.520 |
ricks | +4.224 |
Rah | +4.195 |
� | +4.126 |
liner | +4.058 |
Neg logit contributions | |
Hunts | -6.438 |
Scand | -5.834 |
Engels | -5.800 |
Amateur | -5.750 |
Lat | -5.645 |
Token | Trump |
Token ID | 1301 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
inyl | +1.436 |
� | +1.268 |
ricks | +1.266 |
liner | +1.263 |
Rah | +1.256 |
Neg logit contributions | |
Hunts | -2.505 |
Engels | -2.276 |
Scand | -2.267 |
Amateur | -2.260 |
Lat | -2.227 |
Token | House |
Token ID | 18102 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
inyl | +1.859 |
Rah | +1.709 |
ricks | +1.684 |
liner | +1.661 |
� | +1.642 |
Neg logit contributions | |
Hunts | -2.428 |
Scand | -2.183 |
Engels | -2.181 |
Amateur | -2.179 |
Lat | -2.130 |
Token | committee |
Token ID | 5583 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
inyl | +4.038 |
� | +3.818 |
liner | +3.766 |
Rah | +3.662 |
ricks | +3.624 |
Neg logit contributions | |
Hunts | -3.080 |
Scand | -2.800 |
Amateur | -2.731 |
Engels | -2.639 |
Redmond | -2.575 |
Token | believes |
Token ID | 5804 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
inyl | +3.996 |
� | +3.809 |
liner | +3.795 |
ricks | +3.756 |
Rah | +3.706 |
Neg logit contributions | |
Hunts | -1.485 |
Scand | -1.155 |
Engels | -1.153 |
Amateur | -1.120 |
Lat | -1.082 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Hunts | +0.324 |
Scand | +0.250 |
Engels | +0.248 |
Lat | +0.244 |
Amateur | +0.244 |
Neg logit contributions | |
inyl | -0.824 |
ricks | -0.766 |
Rah | -0.762 |
liner | -0.760 |
� | -0.753 |
Token | | |
Token ID | 930 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Hunts | +1.620 |
Engels | +1.381 |
Lat | +1.378 |
Scand | +1.376 |
Amateur | +1.372 |
Neg logit contributions | |
inyl | -2.053 |
ricks | -1.870 |
Rah | -1.846 |
liner | -1.837 |
ciples | -1.800 |
Token | + |
Token ID | 1343 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
inyl | +1.177 |
ricks | +0.965 |
� | +0.957 |
Rah | +0.954 |
liner | +0.952 |
Neg logit contributions | |
Hunts | -2.928 |
Engels | -2.672 |
Scand | -2.662 |
Amateur | -2.649 |
Lat | -2.637 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
inyl | +3.691 |
Rah | +3.426 |
ricks | +3.380 |
� | +3.353 |
liner | +3.294 |
Neg logit contributions | |
Hunts | -3.777 |
Scand | -3.356 |
Engels | -3.286 |
Amateur | -3.242 |
Lat | -3.228 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
inyl | +0.048 |
ricks | +0.040 |
Rah | +0.039 |
liner | +0.039 |
� | +0.039 |
Neg logit contributions | |
Hunts | -0.125 |
Scand | -0.114 |
Engels | -0.114 |
Amateur | -0.113 |
Lat | -0.113 |
Token | + |
Token ID | 1343 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
inyl | +1.021 |
� | +0.849 |
Rah | +0.834 |
ricks | +0.833 |
liner | +0.830 |
Neg logit contributions | |
Hunts | -2.642 |
Engels | -2.408 |
Scand | -2.407 |
Amateur | -2.383 |
Lat | -2.365 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
inyl | +5.195 |
Rah | +4.936 |
� | +4.798 |
ricks | +4.788 |
liner | +4.635 |
Neg logit contributions | |
Hunts | -5.951 |
Scand | -5.380 |
Engels | -5.221 |
Amateur | -5.151 |
Lat | -5.119 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
inyl | +0.739 |
� | +0.591 |
ricks | +0.589 |
Rah | +0.581 |
liner | +0.575 |
Neg logit contributions | |
Hunts | -2.166 |
Scand | -1.976 |
Engels | -1.972 |
Lat | -1.948 |
Amateur | -1.948 |
Token | < |
Token ID | 1279 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
inyl | +2.186 |
ricks | +1.965 |
liner | +1.953 |
� | +1.950 |
Rah | +1.950 |
Neg logit contributions | |
Hunts | -2.163 |
Engels | -1.887 |
Scand | -1.883 |
Amateur | -1.865 |
Lat | -1.852 |
Token | -- |
Token ID | 438 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
inyl | +0.592 |
liner | +0.549 |
Rah | +0.548 |
ricks | +0.547 |
� | +0.545 |
Neg logit contributions | |
Hunts | -0.308 |
Scand | -0.252 |
Engels | -0.250 |
Amateur | -0.246 |
Lat | -0.241 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
Hunts | +0.468 |
Scand | +0.395 |
Engels | +0.394 |
Lat | +0.391 |
Amateur | +0.390 |
Neg logit contributions | |
inyl | -0.652 |
ricks | -0.595 |
Rah | -0.591 |
liner | -0.588 |
� | -0.581 |
Token | , |
Token ID | 11 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
inyl | +0.672 |
ricks | +0.600 |
Rah | +0.596 |
liner | +0.595 |
� | +0.590 |
Neg logit contributions | |
Hunts | -0.718 |
Engels | -0.627 |
Scand | -0.627 |
Amateur | -0.621 |
Lat | -0.620 |
Token | 2 |
Token ID | 17 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Hunts | +0.415 |
Scand | +0.357 |
Engels | +0.356 |
Amateur | +0.353 |
Lat | +0.353 |
Neg logit contributions | |
inyl | -0.478 |
ricks | -0.432 |
Rah | -0.429 |
liner | -0.427 |
� | -0.422 |
Token | , |
Token ID | 11 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
inyl | +0.541 |
ricks | +0.484 |
Rah | +0.481 |
liner | +0.480 |
� | +0.475 |
Neg logit contributions | |
Hunts | -0.569 |
Engels | -0.496 |
Scand | -0.496 |
Amateur | -0.492 |
Lat | -0.491 |
Token | 4 |
Token ID | 19 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Hunts | +1.342 |
Scand | +1.149 |
Engels | +1.143 |
Lat | +1.139 |
Amateur | +1.135 |
Neg logit contributions | |
inyl | -1.628 |
ricks | -1.475 |
Rah | -1.463 |
liner | -1.458 |
� | -1.434 |
Token | ) |
Token ID | 8 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
Hunts | +0.711 |
Scand | +0.619 |
Engels | +0.617 |
Amateur | +0.613 |
Lat | +0.612 |
Neg logit contributions | |
inyl | -0.707 |
ricks | -0.638 |
Rah | -0.632 |
liner | -0.629 |
� | -0.618 |
Token | Mystery |
Token ID | 18208 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
Hunts | +0.644 |
Scand | +0.565 |
Engels | +0.563 |
Amateur | +0.561 |
Lat | +0.560 |
Neg logit contributions | |
inyl | -0.562 |
ricks | -0.499 |
Rah | -0.496 |
liner | -0.495 |
� | -0.482 |
Token | fellow |
Token ID | 5891 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
inyl | +5.186 |
� | +4.776 |
liner | +4.739 |
ricks | +4.709 |
Rah | +4.659 |
Neg logit contributions | |
Hunts | -5.656 |
Engels | -5.003 |
Lat | -4.946 |
Scand | -4.942 |
Amateur | -4.920 |
Token | � |
Token ID | 447 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
inyl | +2.620 |
� | +2.355 |
ricks | +2.350 |
liner | +2.343 |
Rah | +2.324 |
Neg logit contributions | |
Hunts | -2.948 |
Engels | -2.627 |
Scand | -2.596 |
Amateur | -2.586 |
Lat | -2.561 |
Token | � |
Token ID | 247 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Hunts | +0.472 |
Engels | +0.415 |
Scand | +0.415 |
Amateur | +0.412 |
Lat | +0.412 |
Neg logit contributions | |
inyl | -0.395 |
ricks | -0.351 |
Rah | -0.348 |
liner | -0.348 |
� | -0.343 |
Token | – |
Token ID | 784 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
inyl | +1.807 |
ricks | +1.624 |
liner | +1.614 |
Rah | +1.607 |
� | +1.605 |
Neg logit contributions | |
Hunts | -1.973 |
Engels | -1.734 |
Scand | -1.729 |
Amateur | -1.716 |
Lat | -1.704 |
Token | MR |
Token ID | 17242 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
Hunts | +0.114 |
Scand | +0.101 |
Engels | +0.100 |
Lat | +0.100 |
Amateur | +0.100 |
Neg logit contributions | |
inyl | -0.085 |
ricks | -0.074 |
Rah | -0.074 |
liner | -0.073 |
� | -0.072 |
Token | against |
Token ID | 1028 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Hunts | +1.086 |
Scand | +0.939 |
Engels | +0.936 |
Lat | +0.928 |
Amateur | +0.922 |
Neg logit contributions | |
inyl | -1.220 |
ricks | -1.105 |
Rah | -1.099 |
liner | -1.092 |
� | -1.078 |
Token | former |
Token ID | 1966 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
Hunts | +0.170 |
Scand | +0.148 |
Engels | +0.148 |
Lat | +0.147 |
Amateur | +0.147 |
Neg logit contributions | |
inyl | -0.166 |
ricks | -0.149 |
Rah | -0.148 |
liner | -0.148 |
� | -0.146 |
Token | President |
Token ID | 1992 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
inyl | +2.091 |
� | +1.893 |
ricks | +1.890 |
liner | +1.887 |
Rah | +1.879 |
Neg logit contributions | |
Hunts | -2.030 |
Engels | -1.789 |
Scand | -1.773 |
Amateur | -1.762 |
Lat | -1.724 |
Token | Barack |
Token ID | 8732 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
inyl | +0.544 |
ricks | +0.489 |
Rah | +0.485 |
liner | +0.484 |
� | +0.479 |
Neg logit contributions | |
Hunts | -0.535 |
Scand | -0.465 |
Engels | -0.464 |
Lat | -0.460 |
Amateur | -0.460 |
Token | Obama |
Token ID | 2486 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
inyl | +0.771 |
ricks | +0.671 |
Rah | +0.668 |
liner | +0.665 |
� | +0.657 |
Neg logit contributions | |
Hunts | -1.174 |
Scand | -1.048 |
Engels | -1.047 |
Amateur | -1.040 |
Lat | -1.037 |
Token | Barack |
Token ID | 8732 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
inyl | +0.957 |
ricks | +0.859 |
Rah | +0.853 |
liner | +0.852 |
� | +0.843 |
Neg logit contributions | |
Hunts | -0.978 |
Engels | -0.852 |
Scand | -0.851 |
Amateur | -0.844 |
Lat | -0.841 |
Token | Hussein |
Token ID | 22983 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
inyl | +4.137 |
Rah | +3.951 |
ricks | +3.736 |
� | +3.700 |
liner | +3.697 |
Neg logit contributions | |
Hunts | -6.643 |
Scand | -6.050 |
Amateur | -6.033 |
Engels | -5.857 |
Lat | -5.815 |
Token | Obama |
Token ID | 2486 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
inyl | +2.249 |
ricks | +1.963 |
Rah | +1.944 |
liner | +1.939 |
� | +1.914 |
Neg logit contributions | |
Hunts | -3.370 |
Scand | -3.004 |
Engels | -3.003 |
Amateur | -2.981 |
Lat | -2.977 |
Token | With |
Token ID | 3152 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
inyl | +2.042 |
Rah | +1.826 |
liner | +1.803 |
ricks | +1.791 |
� | +1.759 |
Neg logit contributions | |
Hunts | -3.047 |
Engels | -2.747 |
Scand | -2.743 |
Amateur | -2.717 |
Lat | -2.670 |
Token | low |
Token ID | 1877 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
inyl | +0.114 |
ricks | +0.103 |
liner | +0.103 |
Rah | +0.102 |
� | +0.101 |
Neg logit contributions | |
Hunts | -0.099 |
Amateur | -0.085 |
Lat | -0.085 |
Engels | -0.085 |
Scand | -0.084 |
Token | birth |
Token ID | 4082 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
inyl | +1.913 |
� | +1.730 |
liner | +1.701 |
Rah | +1.692 |
ricks | +1.683 |
Neg logit contributions | |
Hunts | -2.191 |
Scand | -1.923 |
Engels | -1.921 |
Amateur | -1.916 |
Lat | -1.877 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
inyl | +1.033 |
ricks | +0.934 |
liner | +0.929 |
Rah | +0.928 |
� | +0.921 |
Neg logit contributions | |
Hunts | -0.929 |
Scand | -0.802 |
Engels | -0.802 |
Amateur | -0.791 |
Lat | -0.790 |
Token | 88 |
Token ID | 3459 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
inyl | +0.163 |
ricks | +0.148 |
Rah | +0.148 |
liner | +0.148 |
� | +0.147 |
Neg logit contributions | |
Hunts | -0.129 |
Scand | -0.110 |
Engels | -0.110 |
Amateur | -0.109 |
Lat | -0.108 |
Token | million |
Token ID | 1510 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
inyl | +2.035 |
liner | +1.856 |
ricks | +1.849 |
� | +1.841 |
Rah | +1.835 |
Neg logit contributions | |
Hunts | -1.779 |
Engels | -1.540 |
Scand | -1.529 |
Amateur | -1.499 |
Lat | -1.495 |
Token | ( |
Token ID | 357 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
inyl | +0.751 |
ricks | +0.662 |
Rah | +0.657 |
liner | +0.655 |
� | +0.647 |
Neg logit contributions | |
Hunts | -0.989 |
Scand | -0.875 |
Engels | -0.875 |
Amateur | -0.868 |
Lat | -0.867 |
Token | 41 |
Token ID | 3901 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
inyl | +1.331 |
ricks | +1.229 |
Rah | +1.228 |
liner | +1.223 |
� | +1.208 |
Neg logit contributions | |
Hunts | -0.972 |
Engels | -0.825 |
Scand | -0.825 |
Amateur | -0.809 |
Lat | -0.804 |
Token | st |
Token ID | 301 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
inyl | +1.875 |
ricks | +1.729 |
liner | +1.723 |
� | +1.720 |
Rah | +1.710 |
Neg logit contributions | |
Hunts | -1.439 |
Scand | -1.234 |
Engels | -1.219 |
Amateur | -1.191 |
Lat | -1.183 |
Token | among |
Token ID | 1871 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
inyl | +4.818 |
� | +4.409 |
liner | +4.312 |
Rah | +4.275 |
ricks | +4.217 |
Neg logit contributions | |
Hunts | -5.931 |
Engels | -5.246 |
Scand | -5.200 |
Amateur | -5.188 |
Lat | -5.113 |
Token | all |
Token ID | 477 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
inyl | +2.922 |
ricks | +2.707 |
liner | +2.683 |
Rah | +2.666 |
� | +2.661 |
Neg logit contributions | |
Hunts | -2.897 |
Engels | -2.548 |
Amateur | -2.492 |
Scand | -2.490 |
Lat | -2.447 |
Token | edge |
Token ID | 5743 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
inyl | +1.388 |
ricks | +1.278 |
liner | +1.270 |
Rah | +1.267 |
� | +1.261 |
Neg logit contributions | |
Hunts | -0.987 |
Engels | -0.834 |
Scand | -0.826 |
Amateur | -0.823 |
Lat | -0.812 |
Token | r |
Token ID | 374 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
inyl | +1.023 |
ricks | +0.887 |
Rah | +0.879 |
liner | +0.876 |
� | +0.865 |
Neg logit contributions | |
Hunts | -1.890 |
Engels | -1.717 |
Amateur | -1.705 |
Scand | -1.693 |
Lat | -1.683 |
Token | us |
Token ID | 385 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Hunts | +1.087 |
Scand | +0.887 |
Engels | +0.887 |
Amateur | +0.874 |
Lat | +0.872 |
Neg logit contributions | |
inyl | -1.976 |
ricks | -1.820 |
Rah | -1.810 |
liner | -1.807 |
� | -1.794 |
Token | ] |
Token ID | 60 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
inyl | +3.392 |
� | +3.154 |
liner | +3.131 |
Rah | +3.118 |
ricks | +3.083 |
Neg logit contributions | |
Hunts | -1.965 |
Scand | -1.625 |
Engels | -1.607 |
Amateur | -1.577 |
Redmond | -1.534 |
Token | | |
Token ID | 930 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
Hunts | +1.475 |
Engels | +1.260 |
Lat | +1.255 |
Scand | +1.252 |
Amateur | +1.251 |
Neg logit contributions | |
inyl | -1.847 |
ricks | -1.681 |
Rah | -1.661 |
liner | -1.650 |
� | -1.617 |
Token | + |
Token ID | 1343 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
Hunts | +0.050 |
Scand | +0.045 |
Engels | +0.045 |
Amateur | +0.045 |
Lat | +0.045 |
Neg logit contributions | |
inyl | -0.021 |
ricks | -0.017 |
Rah | -0.017 |
liner | -0.017 |
� | -0.017 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
inyl | +4.434 |
Rah | +4.145 |
ricks | +4.071 |
� | +4.065 |
liner | +3.969 |
Neg logit contributions | |
Hunts | -4.759 |
Scand | -4.250 |
Engels | -4.138 |
Amateur | -4.096 |
Lat | -4.067 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
inyl | +0.767 |
� | +0.618 |
ricks | +0.612 |
Rah | +0.606 |
liner | +0.599 |
Neg logit contributions | |
Hunts | -2.250 |
Scand | -2.050 |
Engels | -2.044 |
Lat | -2.024 |
Amateur | -2.023 |
Token | + |
Token ID | 1343 |
Feature activation | -7.18e+00 |
Pos logit contributions | |
inyl | +1.109 |
� | +0.932 |
Rah | +0.906 |
liner | +0.904 |
ricks | +0.897 |
Neg logit contributions | |
Hunts | -3.041 |
Scand | -2.778 |
Engels | -2.764 |
Amateur | -2.740 |
Lat | -2.717 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
inyl | +5.105 |
Rah | +4.825 |
� | +4.729 |
ricks | +4.695 |
liner | +4.571 |
Neg logit contributions | |
Hunts | -5.716 |
Scand | -5.154 |
Engels | -4.989 |
Amateur | -4.949 |
Lat | -4.911 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
inyl | +0.781 |
� | +0.629 |
ricks | +0.620 |
Rah | +0.614 |
liner | +0.607 |
Neg logit contributions | |
Hunts | -2.323 |
Scand | -2.118 |
Engels | -2.113 |
Amateur | -2.089 |
Lat | -2.089 |
Token | < |
Token ID | 1279 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
inyl | +1.510 |
ricks | +1.360 |
liner | +1.349 |
Rah | +1.349 |
� | +1.343 |
Neg logit contributions | |
Hunts | -1.455 |
Engels | -1.264 |
Scand | -1.263 |
Amateur | -1.251 |
Lat | -1.245 |
Token | -- |
Token ID | 438 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Hunts | +0.254 |
Scand | +0.205 |
Engels | +0.204 |
Amateur | +0.201 |
Lat | +0.198 |
Neg logit contributions | |
inyl | -0.516 |
ricks | -0.477 |
Rah | -0.477 |
liner | -0.477 |
� | -0.474 |
Token | pop |
Token ID | 1461 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
Hunts | +1.375 |
Scand | +1.137 |
Engels | +1.129 |
Lat | +1.128 |
Amateur | +1.119 |
Neg logit contributions | |
inyl | -2.262 |
ricks | -2.075 |
Rah | -2.069 |
liner | -2.049 |
ciples | -2.019 |
Token | stealing |
Token ID | 16568 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Hunts | +1.202 |
Engels | +1.045 |
Scand | +1.044 |
Lat | +1.037 |
Amateur | +1.033 |
Neg logit contributions | |
inyl | -1.238 |
ricks | -1.118 |
Rah | -1.110 |
liner | -1.103 |
� | -1.093 |
Token | gas |
Token ID | 3623 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Hunts | +0.580 |
Scand | +0.507 |
Engels | +0.507 |
Amateur | +0.502 |
Lat | +0.501 |
Neg logit contributions | |
inyl | -0.546 |
ricks | -0.488 |
Rah | -0.485 |
liner | -0.484 |
� | -0.479 |
Token | meant |
Token ID | 4001 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
Hunts | +1.548 |
Scand | +1.333 |
Lat | +1.331 |
Engels | +1.330 |
Amateur | +1.309 |
Neg logit contributions | |
inyl | -1.753 |
ricks | -1.581 |
Rah | -1.577 |
liner | -1.550 |
� | -1.542 |
Token | for |
Token ID | 329 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
inyl | +1.458 |
ricks | +1.311 |
liner | +1.308 |
Rah | +1.297 |
� | +1.286 |
Neg logit contributions | |
Hunts | -1.466 |
Engels | -1.277 |
Scand | -1.277 |
Amateur | -1.268 |
Lat | -1.255 |
Token | Europe |
Token ID | 2031 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Hunts | +0.226 |
Engels | +0.196 |
Scand | +0.196 |
Amateur | +0.194 |
Lat | +0.193 |
Neg logit contributions | |
inyl | -0.226 |
ricks | -0.203 |
liner | -0.202 |
Rah | -0.202 |
� | -0.200 |
Token | Russian |
Token ID | 3394 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
inyl | +0.993 |
ricks | +0.890 |
liner | +0.889 |
Rah | +0.882 |
� | +0.882 |
Neg logit contributions | |
Hunts | -1.036 |
Scand | -0.907 |
Engels | -0.905 |
Amateur | -0.895 |
Lat | -0.893 |
Token | state |
Token ID | 1181 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
inyl | +4.853 |
liner | +4.476 |
� | +4.406 |
ricks | +4.300 |
Rah | +4.263 |
Neg logit contributions | |
Hunts | -5.482 |
Scand | -4.981 |
Engels | -4.844 |
Amateur | -4.829 |
Redmond | -4.763 |
Token | energy |
Token ID | 2568 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
inyl | +0.084 |
ricks | +0.076 |
liner | +0.075 |
Rah | +0.075 |
� | +0.075 |
Neg logit contributions | |
Hunts | -0.075 |
Scand | -0.065 |
Engels | -0.065 |
Amateur | -0.064 |
Lat | -0.064 |
Token | company |
Token ID | 1664 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
inyl | +0.347 |
ricks | +0.309 |
liner | +0.307 |
Rah | +0.304 |
� | +0.303 |
Neg logit contributions | |
Hunts | -0.416 |
Engels | -0.366 |
Scand | -0.366 |
Amateur | -0.365 |
Lat | -0.360 |
Token | Gaz |
Token ID | 21347 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
inyl | +1.007 |
liner | +0.915 |
ricks | +0.913 |
� | +0.907 |
Rah | +0.905 |
Neg logit contributions | |
Hunts | -0.821 |
Engels | -0.706 |
Amateur | -0.703 |
Scand | -0.703 |
Lat | -0.686 |
Token | prom |
Token ID | 16963 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Hunts | +0.405 |
Engels | +0.340 |
Scand | +0.340 |
Amateur | +0.337 |
Lat | +0.330 |
Neg logit contributions | |
inyl | -0.610 |
ricks | -0.557 |
liner | -0.557 |
Rah | -0.554 |
� | -0.554 |
Token | "] |
Token ID | 8973 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Hunts | +0.741 |
Scand | +0.654 |
Engels | +0.653 |
Lat | +0.648 |
Amateur | +0.647 |
Neg logit contributions | |
inyl | -0.602 |
ricks | -0.535 |
Rah | -0.529 |
liner | -0.526 |
� | -0.521 |
Token | | |
Token ID | 930 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Hunts | +2.536 |
Scand | +2.193 |
Lat | +2.190 |
Engels | +2.173 |
Amateur | +2.171 |
Neg logit contributions | |
inyl | -2.756 |
ricks | -2.513 |
Rah | -2.469 |
liner | -2.437 |
� | -2.406 |
Token | + |
Token ID | 1343 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
inyl | +0.236 |
ricks | +0.197 |
Rah | +0.194 |
liner | +0.194 |
� | +0.190 |
Neg logit contributions | |
Hunts | -0.537 |
Scand | -0.487 |
Engels | -0.487 |
Amateur | -0.484 |
Lat | -0.483 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
inyl | +4.084 |
Rah | +3.814 |
ricks | +3.751 |
� | +3.726 |
liner | +3.656 |
Neg logit contributions | |
Hunts | -4.307 |
Scand | -3.836 |
Engels | -3.745 |
Amateur | -3.695 |
Lat | -3.676 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
inyl | +0.712 |
� | +0.571 |
ricks | +0.571 |
Rah | +0.566 |
liner | +0.559 |
Neg logit contributions | |
Hunts | -2.047 |
Scand | -1.866 |
Engels | -1.860 |
Amateur | -1.843 |
Lat | -1.841 |
Token | + |
Token ID | 1343 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
inyl | +1.178 |
� | +1.003 |
Rah | +0.980 |
liner | +0.974 |
ricks | +0.973 |
Neg logit contributions | |
Hunts | -2.825 |
Scand | -2.571 |
Engels | -2.561 |
Amateur | -2.539 |
Lat | -2.516 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
inyl | +4.971 |
Rah | +4.709 |
� | +4.601 |
ricks | +4.585 |
liner | +4.447 |
Neg logit contributions | |
Hunts | -5.604 |
Scand | -5.062 |
Engels | -4.897 |
Amateur | -4.852 |
Lat | -4.818 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
inyl | +0.762 |
� | +0.613 |
ricks | +0.608 |
Rah | +0.601 |
liner | +0.594 |
Neg logit contributions | |
Hunts | -2.249 |
Scand | -2.053 |
Engels | -2.046 |
Amateur | -2.025 |
Lat | -2.023 |
Token | | |
Token ID | 930 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
inyl | +0.951 |
ricks | +0.857 |
Rah | +0.851 |
liner | +0.850 |
� | +0.841 |
Neg logit contributions | |
Hunts | -0.888 |
Scand | -0.768 |
Engels | -0.768 |
Amateur | -0.760 |
Lat | -0.759 |
Token | ... |
Token ID | 2644 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
Hunts | +1.187 |
Scand | +0.921 |
Lat | +0.908 |
Engels | +0.907 |
Amateur | +0.892 |
Neg logit contributions | |
inyl | -2.897 |
ricks | -2.693 |
Rah | -2.681 |
liner | -2.661 |
� | -2.624 |
Token | | |
Token ID | 930 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Hunts | +2.116 |
Lat | +1.802 |
Engels | +1.797 |
Scand | +1.789 |
Amateur | +1.788 |
Neg logit contributions | |
inyl | -2.740 |
ricks | -2.504 |
Rah | -2.464 |
liner | -2.450 |
ciples | -2.407 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Hunts | +0.095 |
Scand | +0.081 |
Engels | +0.081 |
Amateur | +0.080 |
Lat | +0.080 |
Neg logit contributions | |
inyl | -0.123 |
ricks | -0.112 |
Rah | -0.111 |
liner | -0.111 |
� | -0.110 |
Token | | |
Token ID | 930 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
Hunts | +1.377 |
Scand | +1.181 |
Engels | +1.170 |
Lat | +1.168 |
Amateur | +1.160 |
Neg logit contributions | |
inyl | -1.743 |
ricks | -1.591 |
Rah | -1.572 |
liner | -1.557 |
� | -1.535 |
Token | + |
Token ID | 1343 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Hunts | +0.051 |
Engels | +0.044 |
Scand | +0.044 |
Amateur | +0.043 |
Lat | +0.043 |
Neg logit contributions | |
inyl | -0.061 |
ricks | -0.055 |
Rah | -0.055 |
liner | -0.055 |
� | -0.055 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
inyl | +2.573 |
Rah | +2.355 |
ricks | +2.351 |
liner | +2.321 |
� | +2.312 |
Neg logit contributions | |
Hunts | -2.370 |
Scand | -2.049 |
Engels | -2.048 |
Amateur | -2.031 |
Lat | -2.009 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Hunts | +1.157 |
Scand | +1.051 |
Engels | +1.050 |
Amateur | +1.044 |
Lat | +1.043 |
Neg logit contributions | |
inyl | -0.477 |
ricks | -0.394 |
Rah | -0.388 |
liner | -0.387 |
� | -0.380 |
Token | + |
Token ID | 1343 |
Feature activation | -6.99e+00 |
Pos logit contributions | |
inyl | +0.895 |
ricks | +0.796 |
liner | +0.793 |
Rah | +0.792 |
� | +0.786 |
Neg logit contributions | |
Hunts | -1.032 |
Engels | -0.908 |
Scand | -0.906 |
Amateur | -0.899 |
Lat | -0.894 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
inyl | +5.109 |
Rah | +4.747 |
ricks | +4.722 |
� | +4.621 |
liner | +4.559 |
Neg logit contributions | |
Hunts | -5.423 |
Engels | -4.783 |
Scand | -4.775 |
Amateur | -4.689 |
Lat | -4.670 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
inyl | +0.562 |
ricks | +0.453 |
� | +0.446 |
liner | +0.446 |
Rah | +0.445 |
Neg logit contributions | |
Hunts | -1.541 |
Engels | -1.404 |
Scand | -1.404 |
Amateur | -1.388 |
Lat | -1.386 |
Token | < |
Token ID | 1279 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
inyl | +2.185 |
liner | +1.964 |
� | +1.958 |
ricks | +1.957 |
Rah | +1.950 |
Neg logit contributions | |
Hunts | -2.221 |
Engels | -1.940 |
Scand | -1.931 |
Amateur | -1.915 |
Lat | -1.894 |
Token | -- |
Token ID | 438 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
inyl | +1.551 |
liner | +1.430 |
ricks | +1.427 |
Rah | +1.424 |
� | +1.414 |
Neg logit contributions | |
Hunts | -0.865 |
Engels | -0.710 |
Scand | -0.707 |
Amateur | -0.703 |
Lat | -0.690 |
Token | Start |
Token ID | 7253 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
inyl | +0.885 |
ricks | +0.794 |
liner | +0.791 |
Rah | +0.789 |
� | +0.785 |
Neg logit contributions | |
Hunts | -0.866 |
Engels | -0.753 |
Scand | -0.750 |
Amateur | -0.745 |
Lat | -0.740 |
Token | ] |
Token ID | 60 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
inyl | +2.618 |
� | +2.426 |
liner | +2.416 |
Rah | +2.404 |
ricks | +2.387 |
Neg logit contributions | |
Hunts | -1.466 |
Scand | -1.205 |
Engels | -1.198 |
Amateur | -1.170 |
Redmond | -1.139 |
Token | | |
Token ID | 930 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
Hunts | +1.866 |
Lat | +1.592 |
Engels | +1.590 |
Amateur | +1.586 |
Scand | +1.580 |
Neg logit contributions | |
inyl | -2.366 |
ricks | -2.155 |
Rah | -2.127 |
liner | -2.111 |
ciples | -2.075 |
Token | + |
Token ID | 1343 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
Hunts | +0.719 |
Scand | +0.649 |
Engels | +0.647 |
Lat | +0.645 |
Amateur | +0.644 |
Neg logit contributions | |
inyl | -0.348 |
ricks | -0.295 |
Rah | -0.291 |
liner | -0.289 |
� | -0.281 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inyl | +4.242 |
Rah | +3.967 |
ricks | +3.901 |
� | +3.882 |
liner | +3.796 |
Neg logit contributions | |
Hunts | -4.532 |
Scand | -4.047 |
Engels | -3.938 |
Amateur | -3.906 |
Lat | -3.867 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
inyl | +0.727 |
� | +0.583 |
ricks | +0.581 |
Rah | +0.576 |
liner | +0.571 |
Neg logit contributions | |
Hunts | -2.080 |
Scand | -1.896 |
Engels | -1.891 |
Amateur | -1.872 |
Lat | -1.869 |
Token | + |
Token ID | 1343 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
inyl | +0.911 |
� | +0.761 |
ricks | +0.750 |
Rah | +0.749 |
liner | +0.746 |
Neg logit contributions | |
Hunts | -2.220 |
Scand | -2.019 |
Engels | -2.019 |
Amateur | -1.999 |
Lat | -1.981 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
inyl | +4.955 |
Rah | +4.683 |
� | +4.576 |
ricks | +4.569 |
liner | +4.435 |
Neg logit contributions | |
Hunts | -5.570 |
Scand | -5.028 |
Engels | -4.868 |
Amateur | -4.831 |
Lat | -4.783 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
inyl | +0.555 |
� | +0.445 |
ricks | +0.445 |
Rah | +0.439 |
liner | +0.436 |
Neg logit contributions | |
Hunts | -1.560 |
Scand | -1.422 |
Engels | -1.420 |
Amateur | -1.405 |
Lat | -1.402 |
Token | < |
Token ID | 1279 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
inyl | +1.170 |
ricks | +1.053 |
Rah | +1.046 |
liner | +1.045 |
� | +1.037 |
Neg logit contributions | |
Hunts | -1.116 |
Engels | -0.967 |
Scand | -0.967 |
Amateur | -0.958 |
Lat | -0.955 |
Token | -- |
Token ID | 438 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
Hunts | +0.341 |
Scand | +0.275 |
Engels | +0.274 |
Amateur | +0.270 |
Lat | +0.266 |
Neg logit contributions | |
inyl | -0.695 |
ricks | -0.642 |
liner | -0.642 |
Rah | -0.642 |
� | -0.637 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
Hunts | +1.170 |
Scand | +1.006 |
Engels | +1.001 |
Lat | +1.000 |
Amateur | +0.988 |
Neg logit contributions | |
inyl | -1.364 |
ricks | -1.240 |
Rah | -1.235 |
liner | -1.219 |
ciples | -1.196 |
Token | . |
Token ID | 13 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Hunts | +0.105 |
Scand | +0.091 |
Engels | +0.091 |
Amateur | +0.090 |
Lat | +0.090 |
Neg logit contributions | |
inyl | -0.121 |
ricks | -0.110 |
Rah | -0.109 |
liner | -0.109 |
� | -0.108 |
Token | 78 |
Token ID | 3695 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
inyl | +0.351 |
ricks | +0.319 |
Rah | +0.318 |
liner | +0.317 |
� | +0.315 |
Neg logit contributions | |
Hunts | -0.271 |
Engels | -0.230 |
Scand | -0.230 |
Amateur | -0.227 |
Lat | -0.227 |
Token | million |
Token ID | 1510 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
inyl | +1.912 |
ricks | +1.741 |
liner | +1.734 |
Rah | +1.731 |
� | +1.722 |
Neg logit contributions | |
Hunts | -1.602 |
Engels | -1.374 |
Scand | -1.371 |
Amateur | -1.349 |
Lat | -1.348 |
Token | ( |
Token ID | 357 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
inyl | +0.609 |
ricks | +0.538 |
Rah | +0.533 |
liner | +0.533 |
� | +0.528 |
Neg logit contributions | |
Hunts | -0.800 |
Engels | -0.709 |
Scand | -0.708 |
Amateur | -0.702 |
Lat | -0.701 |
Token | 24 |
Token ID | 1731 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
inyl | +2.325 |
Rah | +2.159 |
ricks | +2.148 |
liner | +2.143 |
� | +2.117 |
Neg logit contributions | |
Hunts | -1.784 |
Engels | -1.522 |
Scand | -1.519 |
Amateur | -1.492 |
Lat | -1.474 |
Token | th |
Token ID | 400 |
Feature activation | -6.97e+00 |
Pos logit contributions | |
inyl | +1.617 |
ricks | +1.467 |
liner | +1.459 |
� | +1.451 |
Rah | +1.441 |
Neg logit contributions | |
Hunts | -1.912 |
Scand | -1.690 |
Engels | -1.681 |
Amateur | -1.649 |
Lat | -1.643 |
Token | among |
Token ID | 1871 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
inyl | +4.802 |
� | +4.314 |
liner | +4.301 |
ricks | +4.261 |
Rah | +4.241 |
Neg logit contributions | |
Hunts | -5.695 |
Engels | -5.000 |
Scand | -4.979 |
Amateur | -4.946 |
Lat | -4.845 |
Token | guards |
Token ID | 10942 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
inyl | +2.895 |
ricks | +2.627 |
liner | +2.572 |
� | +2.555 |
Rah | +2.547 |
Neg logit contributions | |
Hunts | -4.458 |
Engels | -4.033 |
Scand | -3.963 |
Amateur | -3.958 |
Lat | -3.897 |
Token | ) |
Token ID | 8 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
inyl | +2.261 |
liner | +2.009 |
ricks | +2.009 |
� | +1.998 |
Rah | +1.992 |
Neg logit contributions | |
Hunts | -2.577 |
Engels | -2.262 |
Scand | -2.254 |
Amateur | -2.229 |
Lat | -2.219 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
Hunts | +0.311 |
Scand | +0.275 |
Engels | +0.274 |
Amateur | +0.273 |
Lat | +0.272 |
Neg logit contributions | |
inyl | -0.233 |
ricks | -0.205 |
Rah | -0.203 |
liner | -0.202 |
� | -0.198 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
inyl | +1.011 |
ricks | +0.882 |
Rah | +0.882 |
� | +0.880 |
liner | +0.880 |
Neg logit contributions | |
Hunts | -1.544 |
Scand | -1.383 |
Engels | -1.378 |
Amateur | -1.365 |
Lat | -1.354 |
Token | afraid |
Token ID | 7787 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
Hunts | +0.243 |
Scand | +0.211 |
Engels | +0.211 |
Amateur | +0.209 |
Lat | +0.209 |
Neg logit contributions | |
inyl | -0.240 |
ricks | -0.216 |
Rah | -0.214 |
liner | -0.214 |
� | -0.212 |
Token | to |
Token ID | 284 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
inyl | +0.319 |
ricks | +0.285 |
Rah | +0.282 |
liner | +0.282 |
� | +0.278 |
Neg logit contributions | |
Hunts | -0.332 |
Scand | -0.289 |
Engels | -0.289 |
Lat | -0.286 |
Amateur | -0.285 |
Token | express |
Token ID | 4911 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
inyl | +1.133 |
ricks | +1.012 |
Rah | +1.003 |
liner | +1.003 |
� | +0.994 |
Neg logit contributions | |
Hunts | -1.235 |
Scand | -1.082 |
Engels | -1.081 |
Amateur | -1.074 |
Lat | -1.069 |
Token | opinions |
Token ID | 9317 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
inyl | +1.072 |
ricks | +0.968 |
Rah | +0.964 |
liner | +0.961 |
� | +0.959 |
Neg logit contributions | |
Hunts | -0.966 |
Scand | -0.837 |
Engels | -0.835 |
Amateur | -0.833 |
Lat | -0.818 |
Token | differing |
Token ID | 28742 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inyl | +0.859 |
ricks | +0.768 |
liner | +0.763 |
Rah | +0.762 |
� | +0.757 |
Neg logit contributions | |
Hunts | -0.929 |
Scand | -0.814 |
Engels | -0.813 |
Amateur | -0.808 |
Lat | -0.804 |
Token | from |
Token ID | 422 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
inyl | +1.464 |
ricks | +1.319 |
Rah | +1.316 |
liner | +1.312 |
� | +1.307 |
Neg logit contributions | |
Hunts | -1.334 |
Scand | -1.157 |
Engels | -1.156 |
Amateur | -1.147 |
Lat | -1.140 |
Token | those |
Token ID | 883 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
inyl | +5.006 |
Rah | +4.571 |
� | +4.549 |
ricks | +4.548 |
liner | +4.434 |
Neg logit contributions | |
Hunts | -5.224 |
Amateur | -4.725 |
Scand | -4.676 |
Lat | -4.630 |
Engels | -4.615 |
Token | of |
Token ID | 286 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
inyl | +2.795 |
Rah | +2.515 |
ricks | +2.511 |
liner | +2.503 |
� | +2.500 |
Neg logit contributions | |
Hunts | -2.919 |
Amateur | -2.597 |
Scand | -2.580 |
Engels | -2.565 |
Lat | -2.561 |
Token | Democratic |
Token ID | 4390 |
Feature activation | +5.40e-02 |
Pos logit contributions | |
inyl | +2.751 |
Rah | +2.493 |
ricks | +2.486 |
� | +2.465 |
liner | +2.459 |
Neg logit contributions | |
Hunts | -2.753 |
Amateur | -2.431 |
Scand | -2.426 |
Engels | -2.420 |
Lat | -2.381 |
Token | leaders |
Token ID | 2766 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
Hunts | +0.039 |
Scand | +0.034 |
Engels | +0.034 |
Amateur | +0.034 |
Lat | +0.034 |
Neg logit contributions | |
inyl | -0.044 |
ricks | -0.040 |
Rah | -0.040 |
liner | -0.040 |
� | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Hunts | +0.599 |
Scand | +0.516 |
Engels | +0.515 |
Lat | +0.511 |
Amateur | +0.508 |
Neg logit contributions | |
inyl | -0.645 |
ricks | -0.581 |
Rah | -0.576 |
liner | -0.574 |
� | -0.566 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Hunts | +0.532 |
Scand | +0.409 |
Engels | +0.405 |
Lat | +0.400 |
Amateur | +0.397 |
Neg logit contributions | |
inyl | -1.384 |
ricks | -1.288 |
Rah | -1.281 |
liner | -1.275 |
� | -1.264 |
Token | | |
Token ID | 930 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Hunts | +1.809 |
Lat | +1.540 |
Engels | +1.539 |
Scand | +1.532 |
Amateur | +1.531 |
Neg logit contributions | |
inyl | -2.345 |
ricks | -2.140 |
Rah | -2.106 |
liner | -2.095 |
ciples | -2.058 |
Token | + |
Token ID | 1343 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
inyl | +1.034 |
ricks | +0.850 |
Rah | +0.840 |
liner | +0.837 |
� | +0.834 |
Neg logit contributions | |
Hunts | -2.560 |
Engels | -2.332 |
Scand | -2.327 |
Amateur | -2.314 |
Lat | -2.306 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
inyl | +3.436 |
Rah | +3.179 |
ricks | +3.140 |
� | +3.114 |
liner | +3.072 |
Neg logit contributions | |
Hunts | -3.428 |
Scand | -3.032 |
Engels | -2.976 |
Amateur | -2.936 |
Lat | -2.925 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Hunts | +0.333 |
Scand | +0.302 |
Engels | +0.302 |
Amateur | +0.300 |
Lat | +0.300 |
Neg logit contributions | |
inyl | -0.132 |
ricks | -0.108 |
Rah | -0.106 |
liner | -0.106 |
� | -0.105 |
Token | + |
Token ID | 1343 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
inyl | +0.915 |
� | +0.761 |
Rah | +0.752 |
ricks | +0.748 |
liner | +0.746 |
Neg logit contributions | |
Hunts | -2.331 |
Scand | -2.124 |
Engels | -2.122 |
Amateur | -2.102 |
Lat | -2.088 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
inyl | +4.953 |
Rah | +4.684 |
� | +4.564 |
ricks | +4.556 |
liner | +4.423 |
Neg logit contributions | |
Hunts | -5.536 |
Scand | -4.981 |
Engels | -4.846 |
Amateur | -4.778 |
Lat | -4.757 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
inyl | +0.679 |
� | +0.543 |
ricks | +0.542 |
Rah | +0.535 |
liner | +0.529 |
Neg logit contributions | |
Hunts | -1.975 |
Scand | -1.800 |
Engels | -1.798 |
Lat | -1.778 |
Amateur | -1.776 |
Token | < |
Token ID | 1279 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
inyl | +2.129 |
ricks | +1.914 |
liner | +1.902 |
Rah | +1.898 |
� | +1.898 |
Neg logit contributions | |
Hunts | -2.104 |
Engels | -1.833 |
Scand | -1.830 |
Amateur | -1.814 |
Lat | -1.802 |
Token | -- |
Token ID | 438 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
inyl | +0.570 |
liner | +0.529 |
Rah | +0.529 |
ricks | +0.527 |
� | +0.526 |
Neg logit contributions | |
Hunts | -0.295 |
Scand | -0.241 |
Engels | -0.239 |
Amateur | -0.235 |
Lat | -0.231 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
Hunts | +0.191 |
Scand | +0.163 |
Engels | +0.162 |
Amateur | +0.161 |
Lat | +0.161 |
Neg logit contributions | |
inyl | -0.242 |
ricks | -0.220 |
Rah | -0.219 |
liner | -0.218 |
� | -0.216 |
Token | stack |
Token ID | 8931 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Hunts | +2.171 |
Scand | +1.900 |
Engels | +1.885 |
Lat | +1.883 |
Amateur | +1.862 |
Neg logit contributions | |
inyl | -2.175 |
ricks | -1.958 |
Rah | -1.947 |
liner | -1.920 |
ciples | -1.890 |
Token | pointer |
Token ID | 17562 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
inyl | +1.334 |
liner | +1.177 |
ricks | +1.172 |
� | +1.165 |
Rah | +1.165 |
Neg logit contributions | |
Hunts | -1.802 |
Scand | -1.601 |
Engels | -1.591 |
Amateur | -1.580 |
Lat | -1.567 |
Token | + |
Token ID | 1343 |
Feature activation | -3.87e+00 |
Pos logit contributions | |
inyl | +1.592 |
� | +1.379 |
liner | +1.326 |
ricks | +1.309 |
Rah | +1.298 |
Neg logit contributions | |
Hunts | -4.047 |
Engels | -3.700 |
Scand | -3.689 |
Amateur | -3.651 |
Lat | -3.624 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
inyl | +3.049 |
Rah | +2.787 |
ricks | +2.777 |
� | +2.750 |
liner | +2.733 |
Neg logit contributions | |
Hunts | -2.918 |
Scand | -2.557 |
Engels | -2.528 |
Lat | -2.490 |
Amateur | -2.489 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
inyl | +0.720 |
ricks | +0.578 |
� | +0.575 |
Rah | +0.568 |
liner | +0.568 |
Neg logit contributions | |
Hunts | -2.051 |
Scand | -1.866 |
Engels | -1.864 |
Amateur | -1.845 |
Lat | -1.844 |
Token | + |
Token ID | 1343 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
inyl | +0.832 |
ricks | +0.741 |
Rah | +0.740 |
� | +0.739 |
liner | +0.739 |
Neg logit contributions | |
Hunts | -0.947 |
Scand | -0.832 |
Engels | -0.830 |
Amateur | -0.821 |
Lat | -0.817 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
inyl | +4.945 |
Rah | +4.650 |
ricks | +4.578 |
� | +4.550 |
liner | +4.433 |
Neg logit contributions | |
Hunts | -5.531 |
Scand | -4.964 |
Engels | -4.831 |
Amateur | -4.769 |
Lat | -4.757 |
Token | --+ |
Token ID | 44785 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
inyl | +0.922 |
� | +0.742 |
ricks | +0.735 |
Rah | +0.723 |
liner | +0.720 |
Neg logit contributions | |
Hunts | -2.783 |
Scand | -2.536 |
Engels | -2.530 |
Amateur | -2.504 |
Lat | -2.499 |
Token | < |
Token ID | 1279 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Hunts | +0.381 |
Engels | +0.327 |
Scand | +0.327 |
Amateur | +0.324 |
Lat | +0.324 |
Neg logit contributions | |
inyl | -0.441 |
ricks | -0.399 |
Rah | -0.396 |
liner | -0.395 |
� | -0.391 |
Token | -- |
Token ID | 438 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Hunts | +0.948 |
Engels | +0.751 |
Scand | +0.751 |
Amateur | +0.739 |
Lat | +0.737 |
Neg logit contributions | |
inyl | -2.075 |
ricks | -1.921 |
Rah | -1.911 |
liner | -1.908 |
� | -1.894 |
Token | pop |
Token ID | 1461 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Hunts | +1.448 |
Scand | +1.248 |
Engels | +1.239 |
Lat | +1.232 |
Amateur | +1.225 |
Neg logit contributions | |
inyl | -1.722 |
ricks | -1.560 |
Rah | -1.554 |
liner | -1.540 |
� | -1.518 |
Token | ] |
Token ID | 60 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
inyl | +3.062 |
� | +2.847 |
liner | +2.831 |
Rah | +2.814 |
ricks | +2.791 |
Neg logit contributions | |
Hunts | -1.751 |
Scand | -1.446 |
Engels | -1.429 |
Amateur | -1.399 |
Redmond | -1.365 |
Token | | |
Token ID | 930 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Hunts | +1.843 |
Engels | +1.572 |
Lat | +1.571 |
Amateur | +1.565 |
Scand | +1.561 |
Neg logit contributions | |
inyl | -2.336 |
ricks | -2.128 |
Rah | -2.102 |
liner | -2.086 |
ciples | -2.048 |
Token | + |
Token ID | 1343 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
Hunts | +1.024 |
Scand | +0.925 |
Engels | +0.923 |
Lat | +0.919 |
Amateur | +0.917 |
Neg logit contributions | |
inyl | -0.485 |
ricks | -0.410 |
Rah | -0.405 |
liner | -0.402 |
� | -0.391 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inyl | +4.142 |
Rah | +3.869 |
ricks | +3.805 |
� | +3.786 |
liner | +3.708 |
Neg logit contributions | |
Hunts | -4.398 |
Scand | -3.923 |
Engels | -3.819 |
Amateur | -3.787 |
Lat | -3.752 |
Token | --+ |
Token ID | 44785 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
inyl | +0.722 |
� | +0.580 |
ricks | +0.577 |
Rah | +0.571 |
liner | +0.565 |
Neg logit contributions | |
Hunts | -2.086 |
Scand | -1.902 |
Engels | -1.895 |
Amateur | -1.878 |
Lat | -1.876 |
Token | + |
Token ID | 1343 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
inyl | +0.905 |
� | +0.760 |
Rah | +0.746 |
ricks | +0.745 |
liner | +0.744 |
Neg logit contributions | |
Hunts | -2.254 |
Scand | -2.053 |
Engels | -2.045 |
Amateur | -2.029 |
Lat | -2.014 |
Token | -------------------- |
Token ID | 19351 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
inyl | +4.840 |
Rah | +4.569 |
� | +4.461 |
ricks | +4.450 |
liner | +4.331 |
Neg logit contributions | |
Hunts | -5.386 |
Scand | -4.849 |
Engels | -4.697 |
Amateur | -4.665 |
Lat | -4.621 |
Token | --+ |
Token ID | 44785 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
inyl | +0.616 |
� | +0.495 |
ricks | +0.493 |
Rah | +0.487 |
liner | +0.483 |
Neg logit contributions | |
Hunts | -1.764 |
Scand | -1.609 |
Engels | -1.605 |
Amateur | -1.588 |
Lat | -1.586 |
Token | < |
Token ID | 1279 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
inyl | +0.837 |
ricks | +0.754 |
Rah | +0.749 |
liner | +0.748 |
� | +0.741 |
Neg logit contributions | |
Hunts | -0.785 |
Scand | -0.679 |
Engels | -0.679 |
Amateur | -0.673 |
Lat | -0.671 |
Token | -- |
Token ID | 438 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Hunts | +0.320 |
Scand | +0.258 |
Engels | +0.257 |
Amateur | +0.253 |
Lat | +0.249 |
Neg logit contributions | |
inyl | -0.649 |
ricks | -0.600 |
liner | -0.600 |
Rah | -0.600 |
� | -0.596 |
Token | Special |
Token ID | 6093 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
Hunts | +1.228 |
Scand | +1.003 |
Engels | +0.998 |
Lat | +0.997 |
Amateur | +0.980 |
Neg logit contributions | |
inyl | -2.236 |
ricks | -2.070 |
Rah | -2.062 |
liner | -2.037 |
ciples | -2.007 |
Token | im |
Token ID | 545 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Hunts | +3.329 |
Lat | +2.820 |
Scand | +2.784 |
Amateur | +2.746 |
Engels | +2.728 |
Neg logit contributions | |
inyl | -4.851 |
ricks | -4.586 |
Rah | -4.520 |
liner | -4.424 |
ciples | -4.377 |
Token | read |
Token ID | 961 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Hunts | +0.999 |
Engels | +0.862 |
Scand | +0.862 |
Lat | +0.857 |
Amateur | +0.855 |
Neg logit contributions | |
inyl | -1.052 |
ricks | -0.948 |
Rah | -0.948 |
liner | -0.939 |
� | -0.928 |
Token | ( |
Token ID | 357 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Hunts | +1.396 |
Engels | +1.231 |
Lat | +1.230 |
Scand | +1.227 |
Amateur | +1.224 |
Neg logit contributions | |
inyl | -1.175 |
ricks | -1.044 |
Rah | -1.024 |
liner | -1.019 |
ciples | -0.997 |
Token | image |
Token ID | 2939 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
Hunts | +1.178 |
Engels | +0.988 |
Lat | +0.982 |
Scand | +0.982 |
Amateur | +0.980 |
Neg logit contributions | |
inyl | -1.798 |
ricks | -1.659 |
Rah | -1.644 |
liner | -1.635 |
� | -1.603 |
Token | Path |
Token ID | 15235 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
inyl | +0.303 |
Rah | +0.263 |
ricks | +0.263 |
� | +0.261 |
liner | +0.261 |
Neg logit contributions | |
Hunts | -0.482 |
Scand | -0.432 |
Engels | -0.431 |
Amateur | -0.428 |
Lat | -0.426 |
Token | ) |
Token ID | 1267 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
inyl | +0.932 |
ricks | +0.810 |
Rah | +0.807 |
liner | +0.803 |
� | +0.801 |
Neg logit contributions | |
Hunts | -1.447 |
Scand | -1.291 |
Engels | -1.291 |
Amateur | -1.281 |
Lat | -1.275 |
Token | image |
Token ID | 2939 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Hunts | +2.771 |
Lat | +2.329 |
Amateur | +2.281 |
Scand | +2.276 |
Engels | +2.269 |
Neg logit contributions | |
inyl | -4.769 |
ricks | -4.464 |
Rah | -4.373 |
liner | -4.366 |
ciples | -4.301 |
Token | = |
Token ID | 796 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
inyl | +0.952 |
� | +0.826 |
Rah | +0.822 |
liner | +0.811 |
ricks | +0.811 |
Neg logit contributions | |
Hunts | -1.727 |
Scand | -1.559 |
Engels | -1.557 |
Amateur | -1.543 |
Lat | -1.528 |
Token | im |
Token ID | 545 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Hunts | +1.421 |
Scand | +1.209 |
Engels | +1.205 |
Lat | +1.197 |
Amateur | +1.195 |
Neg logit contributions | |
inyl | -1.848 |
ricks | -1.691 |
Rah | -1.677 |
liner | -1.669 |
� | -1.634 |
Token | utils |
Token ID | 26791 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Hunts | +2.399 |
Engels | +2.009 |
Scand | +1.955 |
Amateur | +1.944 |
Lat | +1.943 |
Neg logit contributions | |
inyl | -3.812 |
Rah | -3.544 |
ricks | -3.452 |
liner | -3.442 |
Jinn | -3.402 |
Token | . |
Token ID | 764 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
Hunts | +1.169 |
Engels | +1.008 |
Lat | +1.005 |
Scand | +1.005 |
Amateur | +0.999 |
Neg logit contributions | |
inyl | -1.281 |
ricks | -1.156 |
Rah | -1.141 |
liner | -1.138 |
� | -1.106 |
Token | takeover |
Token ID | 27011 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
inyl | +0.519 |
ricks | +0.468 |
liner | +0.466 |
Rah | +0.465 |
� | +0.461 |
Neg logit contributions | |
Hunts | -0.507 |
Scand | -0.439 |
Engels | -0.435 |
Amateur | -0.435 |
Lat | -0.431 |
Token | of |
Token ID | 286 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
inyl | +0.479 |
ricks | +0.432 |
Rah | +0.429 |
liner | +0.428 |
� | +0.424 |
Neg logit contributions | |
Hunts | -0.463 |
Scand | -0.401 |
Engels | -0.401 |
Amateur | -0.398 |
Lat | -0.396 |
Token | V |
Token ID | 569 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
inyl | +1.207 |
ricks | +1.075 |
liner | +1.071 |
Rah | +1.069 |
� | +1.067 |
Neg logit contributions | |
Hunts | -1.363 |
Scand | -1.190 |
Amateur | -1.188 |
Engels | -1.187 |
Lat | -1.170 |
Token | enez |
Token ID | 11437 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
inyl | +0.340 |
ricks | +0.307 |
liner | +0.303 |
Rah | +0.302 |
� | +0.302 |
Neg logit contributions | |
Hunts | -0.314 |
Engels | -0.269 |
Scand | -0.269 |
Amateur | -0.268 |
Lat | -0.261 |
Token | ue |
Token ID | 518 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Hunts | +0.535 |
Scand | +0.475 |
Engels | +0.473 |
Lat | +0.471 |
Amateur | +0.468 |
Neg logit contributions | |
inyl | -0.413 |
ricks | -0.366 |
Rah | -0.363 |
liner | -0.361 |
� | -0.357 |
Token | ... |
Token ID | 986 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
inyl | +1.256 |
ricks | +1.127 |
liner | +1.122 |
Rah | +1.121 |
� | +1.117 |
Neg logit contributions | |
Hunts | -1.222 |
Scand | -1.061 |
Engels | -1.059 |
Amateur | -1.048 |
Lat | -1.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Hunts | +5.104 |
Scand | +4.484 |
Lat | +4.452 |
Engels | +4.442 |
Amateur | +4.383 |
Neg logit contributions | |
inyl | -4.256 |
ricks | -3.817 |
liner | -3.739 |
Rah | -3.719 |
ciples | -3.641 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Hunts | +1.042 |
Engels | +0.923 |
Scand | +0.921 |
Lat | +0.920 |
Amateur | +0.917 |
Neg logit contributions | |
inyl | -0.780 |
ricks | -0.687 |
Rah | -0.676 |
liner | -0.675 |
� | -0.661 |
Token | From |
Token ID | 4863 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Hunts | +2.310 |
Engels | +2.016 |
Scand | +2.014 |
Lat | +2.007 |
Amateur | +2.000 |
Neg logit contributions | |
inyl | -2.149 |
ricks | -1.902 |
liner | -1.882 |
Rah | -1.867 |
� | -1.865 |
Token | Vox |
Token ID | 28035 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
inyl | +0.136 |
ricks | +0.120 |
Rah | +0.119 |
liner | +0.119 |
� | +0.118 |
Neg logit contributions | |
Hunts | -0.170 |
Scand | -0.150 |
Engels | -0.150 |
Amateur | -0.148 |
Lat | -0.148 |
Token | : |
Token ID | 25 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Hunts | +1.196 |
Scand | +1.045 |
Engels | +1.044 |
Lat | +1.040 |
Amateur | +1.036 |
Neg logit contributions | |
inyl | -1.073 |
ricks | -0.957 |
Rah | -0.947 |
liner | -0.946 |
� | -0.933 |
Token | 15 |
Token ID | 1315 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
inyl | +0.236 |
ricks | +0.213 |
Rah | +0.212 |
liner | +0.212 |
� | +0.211 |
Neg logit contributions | |
Hunts | -0.210 |
Engels | -0.181 |
Scand | -0.181 |
Amateur | -0.179 |
Lat | -0.177 |
Token | } |
Token ID | 92 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
inyl | +0.614 |
ricks | +0.559 |
Rah | +0.558 |
liner | +0.556 |
� | +0.555 |
Neg logit contributions | |
Hunts | -0.453 |
Scand | -0.387 |
Engels | -0.384 |
Amateur | -0.377 |
Lat | -0.374 |
Token | -> |
Token ID | 4613 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Hunts | +1.031 |
Engels | +0.876 |
Scand | +0.876 |
Amateur | +0.867 |
Lat | +0.866 |
Neg logit contributions | |
inyl | -1.327 |
ricks | -1.207 |
Rah | -1.199 |
liner | -1.197 |
� | -1.184 |
Token | " |
Token ID | 366 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Hunts | +2.315 |
Lat | +2.039 |
Engels | +2.039 |
Scand | +2.035 |
Amateur | +2.031 |
Neg logit contributions | |
inyl | -1.835 |
ricks | -1.628 |
Rah | -1.602 |
liner | -1.596 |
� | -1.559 |
Token | S |
Token ID | 50 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Hunts | +0.135 |
Engels | +0.116 |
Scand | +0.116 |
Amateur | +0.115 |
Lat | +0.115 |
Neg logit contributions | |
inyl | -0.147 |
ricks | -0.133 |
Rah | -0.132 |
liner | -0.132 |
� | -0.130 |
Token | ", |
Token ID | 1600 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
inyl | +1.743 |
ricks | +1.532 |
Rah | +1.521 |
liner | +1.519 |
� | +1.503 |
Neg logit contributions | |
Hunts | -2.295 |
Scand | -2.041 |
Engels | -2.041 |
Amateur | -2.018 |
Lat | -2.010 |
Token | { |
Token ID | 1391 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
Hunts | +3.435 |
Scand | +2.938 |
Lat | +2.937 |
Amateur | +2.904 |
Engels | +2.884 |
Neg logit contributions | |
inyl | -4.018 |
ricks | -3.659 |
Rah | -3.636 |
liner | -3.613 |
� | -3.544 |
Token | 10 |
Token ID | 940 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
Hunts | +3.212 |
Scand | +2.757 |
Lat | +2.729 |
Amateur | +2.698 |
Engels | +2.697 |
Neg logit contributions | |
inyl | -4.220 |
ricks | -3.835 |
liner | -3.750 |
Rah | -3.741 |
� | -3.725 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
inyl | +1.551 |
Rah | +1.391 |
� | +1.391 |
liner | +1.384 |
ricks | +1.375 |
Neg logit contributions | |
Hunts | -1.784 |
Scand | -1.581 |
Engels | -1.574 |
Amateur | -1.541 |
Lat | -1.525 |
Token | 15 |
Token ID | 1315 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
Hunts | +0.120 |
Scand | +0.103 |
Engels | +0.103 |
Amateur | +0.102 |
Lat | +0.101 |
Neg logit contributions | |
inyl | -0.144 |
ricks | -0.130 |
Rah | -0.129 |
liner | -0.129 |
� | -0.128 |
Token | } |
Token ID | 92 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
inyl | +0.242 |
ricks | +0.221 |
Rah | +0.221 |
liner | +0.220 |
� | +0.219 |
Neg logit contributions | |
Hunts | -0.177 |
Scand | -0.151 |
Engels | -0.150 |
Amateur | -0.147 |
Lat | -0.146 |
Token | B |
Token ID | 33 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Hunts | +0.741 |
Scand | +0.646 |
Engels | +0.644 |
Amateur | +0.642 |
Lat | +0.641 |
Neg logit contributions | |
inyl | -0.714 |
ricks | -0.639 |
Rah | -0.633 |
liner | -0.633 |
� | -0.625 |
Token | ionic |
Token ID | 26523 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
inyl | +0.845 |
ricks | +0.762 |
liner | +0.747 |
Rah | +0.746 |
� | +0.742 |
Neg logit contributions | |
Hunts | -0.908 |
Scand | -0.799 |
Engels | -0.796 |
Amateur | -0.787 |
Lat | -0.784 |
Token | Commando |
Token ID | 47150 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Hunts | +0.609 |
Scand | +0.516 |
Engels | +0.516 |
Amateur | +0.511 |
Lat | +0.510 |
Neg logit contributions | |
inyl | -0.805 |
ricks | -0.732 |
Rah | -0.728 |
liner | -0.726 |
� | -0.720 |
Token | Rear |
Token ID | 30144 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
inyl | +0.174 |
ricks | +0.156 |
Rah | +0.155 |
liner | +0.155 |
� | +0.154 |
Neg logit contributions | |
Hunts | -0.178 |
Engels | -0.156 |
Scand | -0.156 |
Amateur | -0.154 |
Lat | -0.154 |
Token | med |
Token ID | 1150 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
inyl | +0.674 |
liner | +0.620 |
ricks | +0.619 |
Rah | +0.617 |
� | +0.610 |
Neg logit contributions | |
Hunts | -0.454 |
Engels | -0.384 |
Scand | -0.381 |
Amateur | -0.373 |
Lat | -0.373 |
Token | [/ |
Token ID | 13412 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
Hunts | +0.592 |
Scand | +0.512 |
Engels | +0.511 |
Amateur | +0.508 |
Lat | +0.508 |
Neg logit contributions | |
inyl | -0.607 |
ricks | -0.543 |
Rah | -0.541 |
liner | -0.539 |
� | -0.533 |
Token | b |
Token ID | 65 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Hunts | +3.696 |
Lat | +3.170 |
Amateur | +3.158 |
Scand | +3.155 |
Engels | +3.149 |
Neg logit contributions | |
inyl | -4.325 |
ricks | -3.934 |
Rah | -3.856 |
� | -3.807 |
ciples | -3.798 |
Token | ][/ |
Token ID | 44926 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
inyl | +1.570 |
ricks | +1.444 |
Rah | +1.435 |
liner | +1.434 |
� | +1.427 |
Neg logit contributions | |
Hunts | -0.963 |
Scand | -0.805 |
Engels | -0.798 |
Amateur | -0.786 |
Lat | -0.781 |
Token | color |
Token ID | 8043 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
Hunts | +2.503 |
Lat | +2.125 |
Engels | +2.107 |
Scand | +2.106 |
Amateur | +2.101 |
Neg logit contributions | |
inyl | -3.373 |
ricks | -3.079 |
Rah | -3.046 |
� | -3.005 |
liner | -2.997 |
Token | ] |
Token ID | 60 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
inyl | +0.327 |
ricks | +0.302 |
Rah | +0.300 |
liner | +0.300 |
� | +0.298 |
Neg logit contributions | |
Hunts | -0.173 |
Scand | -0.141 |
Engels | -0.141 |
Amateur | -0.139 |
Lat | -0.138 |
Token | - |
Token ID | 532 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Hunts | +0.716 |
Scand | +0.627 |
Engels | +0.625 |
Amateur | +0.624 |
Lat | +0.621 |
Neg logit contributions | |
inyl | -0.637 |
ricks | -0.569 |
Rah | -0.562 |
liner | -0.561 |
� | -0.553 |
Token | this |
Token ID | 428 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
inyl | +0.738 |
ricks | +0.661 |
liner | +0.657 |
Rah | +0.656 |
� | +0.654 |
Neg logit contributions | |
Hunts | -0.746 |
Engels | -0.652 |
Scand | -0.651 |
Amateur | -0.643 |
Lat | -0.641 |
Token | shootout |
Token ID | 34995 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Hunts | +0.175 |
Engels | +0.152 |
Scand | +0.151 |
Amateur | +0.150 |
Lat | +0.150 |
Neg logit contributions | |
inyl | -0.184 |
ricks | -0.165 |
Rah | -0.164 |
liner | -0.164 |
� | -0.163 |
Token | from |
Token ID | 422 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
inyl | +0.930 |
ricks | +0.836 |
Rah | +0.830 |
liner | +0.829 |
� | +0.823 |
Neg logit contributions | |
Hunts | -0.911 |
Engels | -0.792 |
Scand | -0.791 |
Amateur | -0.784 |
Lat | -0.782 |
Token | Y |
Token ID | 575 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
inyl | +0.077 |
ricks | +0.069 |
Rah | +0.068 |
liner | +0.068 |
� | +0.067 |
Neg logit contributions | |
Hunts | -0.082 |
Scand | -0.072 |
Engels | -0.072 |
Amateur | -0.071 |
Lat | -0.071 |
Token | oy |
Token ID | 726 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
inyl | +0.541 |
ricks | +0.477 |
Rah | +0.473 |
liner | +0.472 |
� | +0.466 |
Neg logit contributions | |
Hunts | -0.719 |
Scand | -0.636 |
Engels | -0.636 |
Amateur | -0.631 |
Lat | -0.630 |
Token | ore |
Token ID | 382 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Hunts | +3.014 |
Amateur | +2.672 |
Scand | +2.662 |
Lat | +2.650 |
Engels | +2.639 |
Neg logit contributions | |
inyl | -2.187 |
ricks | -1.948 |
Rah | -1.945 |
liner | -1.914 |
� | -1.892 |
Token | creation |
Token ID | 38793 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
Hunts | +3.630 |
Amateur | +3.043 |
Scand | +2.995 |
Lat | +2.991 |
Engels | +2.978 |
Neg logit contributions | |
inyl | -5.091 |
Rah | -4.631 |
ricks | -4.607 |
liner | -4.528 |
� | -4.463 |
Token | , |
Token ID | 11 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Hunts | +0.374 |
Scand | +0.323 |
Engels | +0.322 |
Lat | +0.321 |
Amateur | +0.321 |
Neg logit contributions | |
inyl | -0.388 |
ricks | -0.348 |
Rah | -0.347 |
liner | -0.345 |
� | -0.339 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
inyl | +0.021 |
ricks | +0.018 |
Rah | +0.018 |
liner | +0.018 |
� | +0.018 |
Neg logit contributions | |
Hunts | -0.021 |
Scand | -0.018 |
Engels | -0.018 |
Amateur | -0.018 |
Lat | -0.018 |
Token | I |
Token ID | 314 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
inyl | +0.777 |
ricks | +0.696 |
� | +0.691 |
Rah | +0.691 |
liner | +0.691 |
Neg logit contributions | |
Hunts | -0.839 |
Engels | -0.737 |
Scand | -0.736 |
Amateur | -0.729 |
Lat | -0.724 |
Token | purchased |
Token ID | 8155 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
inyl | +0.743 |
ricks | +0.669 |
� | +0.666 |
Rah | +0.663 |
liner | +0.661 |
Neg logit contributions | |
Hunts | -0.804 |
Engels | -0.709 |
Scand | -0.708 |
Amateur | -0.699 |
Lat | -0.694 |
Token | the |
Token ID | 262 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
Hunts | +1.441 |
Lat | +1.266 |
Engels | +1.264 |
Scand | +1.257 |
Amateur | +1.240 |
Neg logit contributions | |
inyl | -1.371 |
Rah | -1.215 |
ricks | -1.212 |
liner | -1.212 |
ciples | -1.190 |
Token | monument |
Token ID | 17757 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Hunts | +0.245 |
Engels | +0.214 |
Scand | +0.213 |
Lat | +0.212 |
Amateur | +0.212 |
Neg logit contributions | |
inyl | -0.232 |
ricks | -0.207 |
Rah | -0.206 |
liner | -0.205 |
� | -0.202 |
Token | until |
Token ID | 1566 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Hunts | +1.485 |
Engels | +1.291 |
Scand | +1.281 |
Lat | +1.279 |
Amateur | +1.269 |
Neg logit contributions | |
inyl | -1.514 |
Rah | -1.351 |
ricks | -1.348 |
liner | -1.335 |
� | -1.311 |
Token | the |
Token ID | 262 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Hunts | +0.615 |
Scand | +0.539 |
Engels | +0.539 |
Lat | +0.536 |
Amateur | +0.534 |
Neg logit contributions | |
inyl | -0.561 |
ricks | -0.500 |
Rah | -0.496 |
liner | -0.493 |
� | -0.486 |
Token | graffiti |
Token ID | 28530 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Hunts | +0.945 |
Scand | +0.821 |
Engels | +0.820 |
Lat | +0.814 |
Amateur | +0.813 |
Neg logit contributions | |
inyl | -0.965 |
ricks | -0.867 |
Rah | -0.862 |
liner | -0.857 |
� | -0.848 |
Token | was |
Token ID | 373 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
Hunts | +0.544 |
Scand | +0.467 |
Engels | +0.467 |
Amateur | +0.462 |
Lat | +0.461 |
Neg logit contributions | |
inyl | -0.642 |
ricks | -0.582 |
Rah | -0.578 |
liner | -0.577 |
� | -0.571 |
Token | removed |
Token ID | 4615 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
Hunts | +0.472 |
Scand | +0.409 |
Engels | +0.409 |
Amateur | +0.405 |
Lat | +0.405 |
Neg logit contributions | |
inyl | -0.488 |
ricks | -0.440 |
Rah | -0.436 |
liner | -0.436 |
� | -0.430 |
Token | . |
Token ID | 13 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
inyl | +0.472 |
ricks | +0.426 |
Rah | +0.422 |
liner | +0.422 |
� | +0.419 |
Neg logit contributions | |
Hunts | -0.443 |
Scand | -0.384 |
Engels | -0.383 |
Amateur | -0.380 |
Lat | -0.379 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Hunts | +0.498 |
Engels | +0.441 |
Amateur | +0.441 |
Scand | +0.441 |
Lat | +0.439 |
Neg logit contributions | |
inyl | -0.382 |
ricks | -0.337 |
liner | -0.331 |
Rah | -0.331 |
� | -0.324 |
Token |
|
Token ID | 198 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
Hunts | +1.137 |
Engels | +1.006 |
Lat | +1.006 |
Amateur | +1.001 |
Scand | +1.000 |
Neg logit contributions | |
inyl | -0.876 |
ricks | -0.773 |
liner | -0.758 |
Rah | -0.756 |
� | -0.738 |
Token | The |
Token ID | 464 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
Hunts | +0.822 |
Scand | +0.726 |
Engels | +0.726 |
Amateur | +0.723 |
Lat | +0.721 |
Neg logit contributions | |
inyl | -0.656 |
ricks | -0.578 |
liner | -0.571 |
Rah | -0.569 |
� | -0.566 |
Token | in |
Token ID | 287 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
inyl | +1.127 |
ricks | +1.007 |
Rah | +1.002 |
liner | +1.000 |
� | +0.995 |
Neg logit contributions | |
Hunts | -1.227 |
Engels | -1.076 |
Scand | -1.072 |
Amateur | -1.067 |
Lat | -1.064 |
Token | 2004 |
Token ID | 5472 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
inyl | +0.151 |
ricks | +0.135 |
liner | +0.134 |
Rah | +0.134 |
� | +0.132 |
Neg logit contributions | |
Hunts | -0.175 |
Engels | -0.154 |
Scand | -0.154 |
Amateur | -0.153 |
Lat | -0.152 |
Token |
|
Token ID | 198 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
inyl | +0.115 |
ricks | +0.102 |
Rah | +0.101 |
liner | +0.101 |
� | +0.100 |
Neg logit contributions | |
Hunts | -0.131 |
Scand | -0.115 |
Engels | -0.115 |
Amateur | -0.114 |
Lat | -0.114 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
Hunts | +0.677 |
Engels | +0.600 |
Scand | +0.599 |
Lat | +0.597 |
Amateur | +0.596 |
Neg logit contributions | |
inyl | -0.502 |
ricks | -0.442 |
Rah | -0.435 |
liner | -0.434 |
� | -0.426 |
Token | 5 |
Token ID | 20 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Hunts | +0.145 |
Engels | +0.125 |
Scand | +0.125 |
Amateur | +0.124 |
Lat | +0.124 |
Neg logit contributions | |
inyl | -0.151 |
ricks | -0.136 |
Rah | -0.135 |
liner | -0.135 |
� | -0.133 |
Token | million |
Token ID | 1510 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
inyl | +0.827 |
ricks | +0.746 |
Rah | +0.742 |
liner | +0.740 |
� | +0.738 |
Neg logit contributions | |
Hunts | -0.751 |
Engels | -0.648 |
Scand | -0.648 |
Amateur | -0.642 |
Lat | -0.639 |
Token | Estimated |
Token ID | 47737 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Hunts | +2.164 |
Scand | +1.881 |
Engels | +1.870 |
Amateur | +1.861 |
Lat | +1.857 |
Neg logit contributions | |
inyl | -2.243 |
ricks | -2.035 |
Rah | -2.004 |
liner | -1.998 |
� | -1.952 |
Token | number |
Token ID | 1271 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Hunts | +1.543 |
Scand | +1.340 |
Engels | +1.335 |
Lat | +1.327 |
Amateur | +1.325 |
Neg logit contributions | |
inyl | -1.620 |
ricks | -1.472 |
Rah | -1.454 |
liner | -1.445 |
� | -1.425 |
Token | of |
Token ID | 286 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
Hunts | +1.679 |
Scand | +1.448 |
Engels | +1.442 |
Lat | +1.436 |
Amateur | +1.432 |
Neg logit contributions | |
inyl | -1.888 |
ricks | -1.712 |
Rah | -1.691 |
liner | -1.685 |
� | -1.653 |
Token | Buddh |
Token ID | 20921 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Hunts | +0.815 |
Scand | +0.718 |
Engels | +0.716 |
Amateur | +0.711 |
Lat | +0.711 |
Neg logit contributions | |
inyl | -0.689 |
ricks | -0.612 |
Rah | -0.607 |
liner | -0.606 |
� | -0.596 |
Token | ists |
Token ID | 1023 |
Feature activation | +5.83e-01 |
Pos logit contributions | |
inyl | +1.113 |
ricks | +0.993 |
liner | +0.982 |
Rah | +0.978 |
� | +0.970 |
Neg logit contributions | |
Hunts | -1.278 |
Scand | -1.123 |
Engels | -1.120 |
Amateur | -1.113 |
Lat | -1.106 |
Token | lines |
Token ID | 6615 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
inyl | +0.776 |
ricks | +0.667 |
liner | +0.660 |
Rah | +0.660 |
� | +0.647 |
Neg logit contributions | |
Hunts | -1.374 |
Scand | -1.235 |
Engels | -1.234 |
Amateur | -1.226 |
Lat | -1.223 |
Token | ) |
Token ID | 8 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
inyl | +1.153 |
ricks | +1.035 |
Rah | +1.034 |
liner | +1.031 |
� | +1.022 |
Neg logit contributions | |
Hunts | -1.149 |
Scand | -1.002 |
Engels | -1.001 |
Amateur | -0.990 |
Lat | -0.985 |
Token | September |
Token ID | 2693 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Hunts | +1.646 |
Engels | +1.451 |
Scand | +1.447 |
Lat | +1.447 |
Amateur | +1.443 |
Neg logit contributions | |
inyl | -1.198 |
ricks | -1.051 |
Rah | -1.039 |
liner | -1.035 |
ciples | -1.004 |
Token | 26 |
Token ID | 2608 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
inyl | +1.837 |
� | +1.685 |
Rah | +1.678 |
liner | +1.673 |
ricks | +1.670 |
Neg logit contributions | |
Hunts | -1.504 |
Scand | -1.298 |
Engels | -1.295 |
Amateur | -1.257 |
Lat | -1.251 |
Token | , |
Token ID | 11 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
inyl | +0.785 |
Rah | +0.704 |
� | +0.703 |
ricks | +0.703 |
liner | +0.703 |
Neg logit contributions | |
Hunts | -0.853 |
Scand | -0.749 |
Engels | -0.745 |
Amateur | -0.737 |
Lat | -0.730 |
Token | 2016 |
Token ID | 1584 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
inyl | +0.465 |
ricks | +0.408 |
Rah | +0.407 |
liner | +0.405 |
� | +0.403 |
Neg logit contributions | |
Hunts | -0.640 |
Scand | -0.568 |
Engels | -0.567 |
Amateur | -0.562 |
Lat | -0.559 |
Token |
|
Token ID | 198 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Hunts | +2.272 |
Engels | +2.000 |
Scand | +1.998 |
Lat | +1.988 |
Amateur | +1.985 |
Neg logit contributions | |
inyl | -1.804 |
ricks | -1.590 |
Rah | -1.573 |
liner | -1.567 |
ciples | -1.517 |
Token |
|
Token ID | 198 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
Hunts | +0.152 |
Engels | +0.135 |
Scand | +0.135 |
Amateur | +0.134 |
Lat | +0.133 |
Neg logit contributions | |
inyl | -0.108 |
ricks | -0.095 |
Rah | -0.094 |
liner | -0.094 |
� | -0.092 |
Token | G |
Token ID | 38 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Hunts | +0.402 |
Scand | +0.352 |
Engels | +0.352 |
Amateur | +0.349 |
Lat | +0.348 |
Neg logit contributions | |
inyl | -0.361 |
ricks | -0.323 |
Rah | -0.322 |
liner | -0.320 |
� | -0.317 |
Token | otte |
Token ID | 11404 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Hunts | +1.400 |
Engels | +1.249 |
Scand | +1.245 |
Lat | +1.239 |
Amateur | +1.238 |
Neg logit contributions | |
inyl | -0.851 |
ricks | -0.737 |
Rah | -0.733 |
liner | -0.730 |
� | -0.720 |
Token | h |
Token ID | 71 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
Hunts | +0.972 |
Engels | +0.842 |
Scand | +0.838 |
Amateur | +0.835 |
Lat | +0.834 |
Neg logit contributions | |
inyl | -0.999 |
ricks | -0.896 |
Rah | -0.889 |
liner | -0.886 |
� | -0.878 |
Token | � |
Token ID | 564 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
inyl | +0.438 |
ricks | +0.387 |
Rah | +0.384 |
liner | +0.383 |
� | +0.379 |
Neg logit contributions | |
Hunts | -0.560 |
Engels | -0.495 |
Scand | -0.495 |
Amateur | -0.491 |
Lat | -0.490 |
Token | � |
Token ID | 250 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
inyl | +1.003 |
ricks | +0.867 |
Rah | +0.862 |
liner | +0.859 |
� | +0.858 |
Neg logit contributions | |
Hunts | -1.594 |
Engels | -1.435 |
Scand | -1.432 |
Amateur | -1.415 |
Lat | -1.409 |
Token | Is |
Token ID | 3792 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
inyl | +0.546 |
ricks | +0.484 |
Rah | +0.481 |
liner | +0.479 |
� | +0.474 |
Neg logit contributions | |
Hunts | -0.665 |
Engels | -0.586 |
Scand | -0.586 |
Amateur | -0.581 |
Lat | -0.580 |
Token | it |
Token ID | 340 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inyl | +0.197 |
ricks | +0.177 |
Rah | +0.175 |
liner | +0.175 |
� | +0.173 |
Neg logit contributions | |
Hunts | -0.207 |
Scand | -0.181 |
Engels | -0.181 |
Amateur | -0.179 |
Lat | -0.179 |
Token | okay |
Token ID | 8788 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
inyl | +1.344 |
ricks | +1.200 |
Rah | +1.189 |
liner | +1.189 |
� | +1.182 |
Neg logit contributions | |
Hunts | -1.460 |
Engels | -1.278 |
Scand | -1.277 |
Amateur | -1.267 |
Lat | -1.261 |
Token | if |
Token ID | 611 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
Hunts | +0.420 |
Engels | +0.366 |
Scand | +0.366 |
Lat | +0.364 |
Amateur | +0.362 |
Neg logit contributions | |
inyl | -0.392 |
ricks | -0.353 |
Rah | -0.350 |
liner | -0.349 |
� | -0.341 |
Token | I |
Token ID | 314 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
Hunts | +1.169 |
Engels | +1.015 |
Scand | +1.013 |
Lat | +1.012 |
Amateur | +1.003 |
Neg logit contributions | |
inyl | -1.177 |
ricks | -1.063 |
Rah | -1.054 |
liner | -1.051 |
� | -1.026 |
Token | hug |
Token ID | 16225 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Hunts | +0.225 |
Scand | +0.196 |
Engels | +0.196 |
Amateur | +0.194 |
Lat | +0.194 |
Neg logit contributions | |
inyl | -0.212 |
ricks | -0.190 |
Rah | -0.189 |
liner | -0.188 |
� | -0.186 |
Token | you |
Token ID | 345 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
inyl | +0.351 |
ricks | +0.318 |
Rah | +0.316 |
liner | +0.316 |
� | +0.313 |
Neg logit contributions | |
Hunts | -0.301 |
Scand | -0.258 |
Engels | -0.258 |
Amateur | -0.256 |
Lat | -0.255 |
Token | ? |
Token ID | 30 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Hunts | +1.214 |
Scand | +1.043 |
Engels | +1.042 |
Lat | +1.042 |
Amateur | +1.035 |
Neg logit contributions | |
inyl | -1.289 |
ricks | -1.162 |
Rah | -1.158 |
liner | -1.143 |
ciples | -1.120 |
Token | � |
Token ID | 447 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
Hunts | +0.977 |
Scand | +0.847 |
Lat | +0.840 |
Engels | +0.839 |
Amateur | +0.834 |
Neg logit contributions | |
inyl | -0.977 |
ricks | -0.882 |
Rah | -0.874 |
liner | -0.871 |
� | -0.849 |
Token | journalists |
Token ID | 9046 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
Hunts | +1.029 |
Engels | +0.893 |
Scand | +0.892 |
Lat | +0.886 |
Amateur | +0.880 |
Neg logit contributions | |
inyl | -1.064 |
ricks | -0.951 |
liner | -0.943 |
Rah | -0.941 |
� | -0.925 |
Token | , |
Token ID | 11 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
inyl | +0.021 |
ricks | +0.019 |
Rah | +0.019 |
liner | +0.019 |
� | +0.018 |
Neg logit contributions | |
Hunts | -0.021 |
Scand | -0.018 |
Engels | -0.018 |
Amateur | -0.018 |
Lat | -0.018 |
Token | calling |
Token ID | 4585 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
Hunts | +0.276 |
Engels | +0.241 |
Scand | +0.240 |
Amateur | +0.238 |
Lat | +0.238 |
Neg logit contributions | |
inyl | -0.267 |
ricks | -0.239 |
Rah | -0.238 |
liner | -0.237 |
� | -0.234 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Hunts | +0.684 |
Scand | +0.587 |
Engels | +0.586 |
Lat | +0.581 |
Amateur | +0.580 |
Neg logit contributions | |
inyl | -0.815 |
ricks | -0.737 |
Rah | -0.731 |
liner | -0.731 |
� | -0.722 |
Token | media |
Token ID | 2056 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
inyl | +1.020 |
ricks | +0.923 |
liner | +0.918 |
Rah | +0.918 |
� | +0.915 |
Neg logit contributions | |
Hunts | -0.900 |
Engels | -0.778 |
Scand | -0.775 |
Amateur | -0.768 |
Lat | -0.764 |
Token | a |
Token ID | 257 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
inyl | +1.182 |
ricks | +1.054 |
Rah | +1.047 |
liner | +1.044 |
� | +1.034 |
Neg logit contributions | |
Hunts | -1.336 |
Scand | -1.173 |
Engels | -1.172 |
Amateur | -1.162 |
Lat | -1.159 |
Token | � |
Token ID | 564 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
Hunts | +1.068 |
Scand | +0.931 |
Engels | +0.928 |
Lat | +0.926 |
Amateur | +0.923 |
Neg logit contributions | |
inyl | -0.943 |
ricks | -0.838 |
Rah | -0.833 |
liner | -0.831 |
� | -0.818 |
Token | � |
Token ID | 250 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Hunts | +0.032 |
Scand | +0.028 |
Engels | +0.028 |
Amateur | +0.028 |
Lat | +0.028 |
Neg logit contributions | |
inyl | -0.025 |
ricks | -0.022 |
Rah | -0.022 |
liner | -0.022 |
� | -0.022 |
Token | b |
Token ID | 65 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Hunts | +1.306 |
Amateur | +1.141 |
Engels | +1.141 |
Scand | +1.140 |
Lat | +1.133 |
Neg logit contributions | |
inyl | -1.144 |
ricks | -1.010 |
liner | -1.006 |
Rah | -1.003 |
� | -0.999 |
Token | unch |
Token ID | 3316 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Hunts | +0.399 |
Engels | +0.354 |
Scand | +0.353 |
Amateur | +0.350 |
Lat | +0.350 |
Neg logit contributions | |
inyl | -0.301 |
ricks | -0.264 |
Rah | -0.264 |
liner | -0.263 |
� | -0.259 |
Token | of |
Token ID | 286 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
inyl | +0.545 |
ricks | +0.490 |
Rah | +0.487 |
liner | +0.486 |
� | +0.480 |
Neg logit contributions | |
Hunts | -0.520 |
Scand | -0.450 |
Engels | -0.450 |
Amateur | -0.446 |
Lat | -0.445 |
Token | Committee |
Token ID | 4606 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
inyl | +1.028 |
liner | +0.902 |
ricks | +0.900 |
Rah | +0.896 |
� | +0.894 |
Neg logit contributions | |
Hunts | -1.457 |
Scand | -1.306 |
Engels | -1.301 |
Amateur | -1.295 |
Lat | -1.284 |
Token | rolled |
Token ID | 11686 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Hunts | +0.679 |
Scand | +0.591 |
Engels | +0.591 |
Lat | +0.586 |
Amateur | +0.585 |
Neg logit contributions | |
inyl | -0.659 |
ricks | -0.592 |
Rah | -0.588 |
liner | -0.585 |
� | -0.578 |
Token | out |
Token ID | 503 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
inyl | +0.732 |
ricks | +0.658 |
Rah | +0.654 |
liner | +0.651 |
� | +0.648 |
Neg logit contributions | |
Hunts | -0.785 |
Scand | -0.691 |
Engels | -0.686 |
Amateur | -0.683 |
Lat | -0.678 |
Token | a |
Token ID | 257 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
Hunts | +0.822 |
Scand | +0.716 |
Engels | +0.715 |
Amateur | +0.708 |
Lat | +0.706 |
Neg logit contributions | |
inyl | -0.821 |
ricks | -0.738 |
Rah | -0.733 |
liner | -0.731 |
� | -0.724 |
Token | television |
Token ID | 5581 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Hunts | +0.179 |
Scand | +0.157 |
Engels | +0.156 |
Amateur | +0.155 |
Lat | +0.153 |
Neg logit contributions | |
inyl | -0.181 |
ricks | -0.162 |
Rah | -0.161 |
liner | -0.161 |
� | -0.160 |
Token | ad |
Token ID | 512 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Hunts | +1.707 |
Engels | +1.470 |
Scand | +1.466 |
Lat | +1.458 |
Amateur | +1.458 |
Neg logit contributions | |
inyl | -1.844 |
ricks | -1.673 |
Rah | -1.654 |
liner | -1.648 |
� | -1.631 |
Token | Thursday |
Token ID | 3635 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
Hunts | +0.276 |
Engels | +0.241 |
Scand | +0.241 |
Amateur | +0.238 |
Lat | +0.238 |
Neg logit contributions | |
inyl | -0.268 |
ricks | -0.240 |
Rah | -0.239 |
liner | -0.238 |
� | -0.236 |
Token | raising |
Token ID | 8620 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
inyl | +0.008 |
ricks | +0.007 |
Rah | +0.007 |
liner | +0.007 |
� | +0.007 |
Neg logit contributions | |
Hunts | -0.008 |
Scand | -0.007 |
Engels | -0.007 |
Amateur | -0.007 |
Lat | -0.007 |
Token | questions |
Token ID | 2683 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
inyl | +0.267 |
ricks | +0.238 |
Rah | +0.235 |
liner | +0.235 |
� | +0.233 |
Neg logit contributions | |
Hunts | -0.316 |
Scand | -0.279 |
Engels | -0.278 |
Amateur | -0.276 |
Lat | -0.275 |
Token | about |
Token ID | 546 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Hunts | +0.212 |
Scand | +0.185 |
Engels | +0.185 |
Amateur | +0.183 |
Lat | +0.183 |
Neg logit contributions | |
inyl | -0.207 |
ricks | -0.186 |
Rah | -0.184 |
liner | -0.184 |
� | -0.182 |
Token | the |
Token ID | 262 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
inyl | +0.389 |
ricks | +0.348 |
Rah | +0.346 |
liner | +0.345 |
� | +0.342 |
Neg logit contributions | |
Hunts | -0.412 |
Engels | -0.361 |
Scand | -0.361 |
Amateur | -0.358 |
Lat | -0.356 |
Token | stop |
Token ID | 2245 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
inyl | +0.138 |
ricks | +0.123 |
Rah | +0.123 |
liner | +0.122 |
� | +0.120 |
Neg logit contributions | |
Hunts | -0.143 |
Scand | -0.124 |
Engels | -0.124 |
Lat | -0.123 |
Amateur | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
inyl | +1.066 |
ricks | +0.957 |
liner | +0.948 |
Rah | +0.948 |
� | +0.942 |
Neg logit contributions | |
Hunts | -1.098 |
Scand | -0.959 |
Engels | -0.957 |
Amateur | -0.949 |
Lat | -0.947 |
Token | So |
Token ID | 1406 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
inyl | +0.140 |
ricks | +0.125 |
Rah | +0.124 |
liner | +0.123 |
� | +0.122 |
Neg logit contributions | |
Hunts | -0.168 |
Engels | -0.148 |
Scand | -0.148 |
Amateur | -0.146 |
Lat | -0.146 |
Token | much |
Token ID | 881 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Hunts | +1.599 |
Scand | +1.394 |
Engels | +1.392 |
Lat | +1.386 |
Amateur | +1.384 |
Neg logit contributions | |
inyl | -1.478 |
ricks | -1.320 |
Rah | -1.313 |
liner | -1.311 |
� | -1.282 |
Token | so |
Token ID | 523 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Hunts | +0.789 |
Engels | +0.676 |
Scand | +0.676 |
Lat | +0.671 |
Amateur | +0.670 |
Neg logit contributions | |
inyl | -0.911 |
ricks | -0.824 |
Rah | -0.819 |
liner | -0.817 |
� | -0.806 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
Hunts | +0.994 |
Scand | +0.857 |
Engels | +0.855 |
Lat | +0.849 |
Amateur | +0.848 |
Neg logit contributions | |
inyl | -1.016 |
ricks | -0.913 |
Rah | -0.909 |
liner | -0.905 |
� | -0.885 |
Token | that |
Token ID | 326 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Hunts | +0.223 |
Scand | +0.194 |
Engels | +0.194 |
Amateur | +0.192 |
Lat | +0.192 |
Neg logit contributions | |
inyl | -0.218 |
ricks | -0.196 |
Rah | -0.194 |
liner | -0.194 |
� | -0.191 |
Token | we |
Token ID | 356 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Hunts | +0.927 |
Scand | +0.810 |
Engels | +0.808 |
Amateur | +0.803 |
Lat | +0.803 |
Neg logit contributions | |
inyl | -0.852 |
ricks | -0.762 |
Rah | -0.756 |
liner | -0.754 |
� | -0.742 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Hunts | +1.682 |
Scand | +1.452 |
Lat | +1.445 |
Engels | +1.443 |
Amateur | +1.437 |
Neg logit contributions | |
inyl | -1.734 |
ricks | -1.559 |
Rah | -1.556 |
liner | -1.545 |
ciples | -1.505 |
Token | � |
Token ID | 447 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
Hunts | +1.333 |
Lat | +1.149 |
Scand | +1.148 |
Engels | +1.148 |
Amateur | +1.145 |
Neg logit contributions | |
inyl | -1.356 |
ricks | -1.223 |
Rah | -1.200 |
liner | -1.198 |
� | -1.171 |
Token | � |
Token ID | 247 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
inyl | +0.191 |
ricks | +0.169 |
Rah | +0.168 |
liner | +0.167 |
� | +0.166 |
Neg logit contributions | |
Hunts | -0.250 |
Scand | -0.222 |
Engels | -0.222 |
Amateur | -0.220 |
Lat | -0.219 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
inyl | +1.706 |
liner | +1.533 |
Rah | +1.531 |
ricks | +1.530 |
� | +1.526 |
Neg logit contributions | |
Hunts | -1.719 |
Scand | -1.504 |
Engels | -1.498 |
Amateur | -1.485 |
Lat | -1.474 |
Token | which |
Token ID | 543 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
inyl | +0.885 |
ricks | +0.793 |
Rah | +0.788 |
liner | +0.786 |
� | +0.779 |
Neg logit contributions | |
Hunts | -0.923 |
Scand | -0.806 |
Engels | -0.805 |
Amateur | -0.798 |
Lat | -0.796 |
Token | was |
Token ID | 373 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
inyl | +0.868 |
ricks | +0.779 |
Rah | +0.777 |
liner | +0.775 |
� | +0.772 |
Neg logit contributions | |
Hunts | -0.877 |
Scand | -0.767 |
Engels | -0.763 |
Amateur | -0.759 |
Lat | -0.752 |
Token | presented |
Token ID | 5545 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Hunts | +1.558 |
Engels | +1.358 |
Scand | +1.351 |
Lat | +1.349 |
Amateur | +1.339 |
Neg logit contributions | |
inyl | -1.532 |
ricks | -1.378 |
Rah | -1.365 |
liner | -1.361 |
� | -1.329 |
Token | at |
Token ID | 379 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
Hunts | +1.736 |
Lat | +1.493 |
Engels | +1.491 |
Scand | +1.488 |
Amateur | +1.480 |
Neg logit contributions | |
inyl | -1.906 |
ricks | -1.720 |
Rah | -1.708 |
liner | -1.693 |
� | -1.657 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
inyl | +0.082 |
ricks | +0.074 |
Rah | +0.073 |
liner | +0.073 |
� | +0.072 |
Neg logit contributions | |
Hunts | -0.091 |
Scand | -0.080 |
Engels | -0.080 |
Amateur | -0.079 |
Lat | -0.079 |
Token | Promise |
Token ID | 34920 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
inyl | +0.295 |
ricks | +0.264 |
Rah | +0.263 |
liner | +0.262 |
� | +0.260 |
Neg logit contributions | |
Hunts | -0.305 |
Engels | -0.266 |
Scand | -0.266 |
Amateur | -0.264 |
Lat | -0.263 |
Token | of |
Token ID | 286 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
inyl | +0.667 |
Rah | +0.599 |
liner | +0.599 |
ricks | +0.595 |
� | +0.595 |
Neg logit contributions | |
Hunts | -0.677 |
Engels | -0.595 |
Scand | -0.592 |
Amateur | -0.587 |
Lat | -0.582 |
Token | the |
Token ID | 262 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
inyl | +1.569 |
ricks | +1.405 |
Rah | +1.402 |
liner | +1.395 |
� | +1.390 |
Neg logit contributions | |
Hunts | -1.592 |
Engels | -1.393 |
Scand | -1.390 |
Amateur | -1.372 |
Lat | -1.367 |
Token | Peace |
Token ID | 12689 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
inyl | +1.631 |
Rah | +1.475 |
ricks | +1.471 |
� | +1.469 |
liner | +1.463 |
Neg logit contributions | |
Hunts | -1.517 |
Engels | -1.326 |
Scand | -1.322 |
Amateur | -1.301 |
Lat | -1.292 |
Token | Corps |
Token ID | 12778 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
inyl | +1.129 |
ricks | +1.008 |
liner | +1.008 |
Rah | +1.007 |
� | +1.002 |
Neg logit contributions | |
Hunts | -1.169 |
Engels | -1.026 |
Scand | -1.025 |
Amateur | -1.013 |
Lat | -1.008 |
Token | their |
Token ID | 511 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
inyl | +0.162 |
ricks | +0.145 |
Rah | +0.144 |
liner | +0.144 |
� | +0.143 |
Neg logit contributions | |
Hunts | -0.165 |
Scand | -0.144 |
Engels | -0.144 |
Amateur | -0.143 |
Lat | -0.142 |
Token | parents |
Token ID | 3397 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
inyl | +0.677 |
ricks | +0.615 |
Rah | +0.614 |
� | +0.612 |
liner | +0.611 |
Neg logit contributions | |
Hunts | -0.522 |
Engels | -0.445 |
Scand | -0.445 |
Amateur | -0.442 |
Lat | -0.435 |
Token | for |
Token ID | 329 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
inyl | +0.781 |
ricks | +0.699 |
Rah | +0.695 |
liner | +0.694 |
� | +0.689 |
Neg logit contributions | |
Hunts | -0.821 |
Scand | -0.718 |
Engels | -0.716 |
Amateur | -0.712 |
Lat | -0.708 |
Token | exposing |
Token ID | 21294 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
inyl | +0.078 |
ricks | +0.070 |
Rah | +0.070 |
liner | +0.069 |
� | +0.069 |
Neg logit contributions | |
Hunts | -0.084 |
Engels | -0.074 |
Scand | -0.074 |
Amateur | -0.073 |
Lat | -0.073 |
Token | their |
Token ID | 511 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Hunts | +0.186 |
Scand | +0.164 |
Engels | +0.164 |
Amateur | +0.162 |
Lat | +0.162 |
Neg logit contributions | |
inyl | -0.159 |
ricks | -0.141 |
Rah | -0.140 |
liner | -0.140 |
� | -0.138 |
Token | child |
Token ID | 1200 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
inyl | +1.361 |
ricks | +1.224 |
liner | +1.218 |
� | +1.215 |
Rah | +1.215 |
Neg logit contributions | |
Hunts | -1.336 |
Engels | -1.168 |
Scand | -1.164 |
Amateur | -1.152 |
Lat | -1.142 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
inyl | +0.024 |
ricks | +0.021 |
Rah | +0.021 |
liner | +0.021 |
� | +0.021 |
Neg logit contributions | |
Hunts | -0.026 |
Engels | -0.022 |
Scand | -0.022 |
Amateur | -0.022 |
Lat | -0.022 |
Token | prof |
Token ID | 1534 |
Feature activation | -8.61e-02 |
Pos logit contributions | |
Hunts | +1.016 |
Scand | +0.884 |
Engels | +0.884 |
Amateur | +0.876 |
Lat | +0.874 |
Neg logit contributions | |
inyl | -1.009 |
ricks | -0.907 |
Rah | -0.900 |
liner | -0.898 |
� | -0.889 |
Token | anity |
Token ID | 19689 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
inyl | +0.078 |
ricks | +0.071 |
liner | +0.070 |
Rah | +0.070 |
� | +0.070 |
Neg logit contributions | |
Hunts | -0.056 |
Scand | -0.047 |
Engels | -0.047 |
Amateur | -0.047 |
Lat | -0.046 |
Token | ." |
Token ID | 526 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
inyl | +1.319 |
ricks | +1.180 |
liner | +1.171 |
Rah | +1.165 |
� | +1.163 |
Neg logit contributions | |
Hunts | -1.483 |
Scand | -1.304 |
Engels | -1.303 |
Amateur | -1.300 |
Lat | -1.286 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
inyl | +1.069 |
ricks | +0.938 |
Rah | +0.931 |
liner | +0.928 |
� | +0.920 |
Neg logit contributions | |
Hunts | -1.503 |
Engels | -1.336 |
Scand | -1.336 |
Amateur | -1.325 |
Lat | -1.324 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
inyl | +0.924 |
Rah | +0.807 |
ricks | +0.806 |
liner | +0.804 |
� | +0.802 |
Neg logit contributions | |
Hunts | -1.401 |
Scand | -1.255 |
Engels | -1.250 |
Amateur | -1.238 |
Lat | -1.229 |
Token | " |
Token ID | 1 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
inyl | +1.094 |
Rah | +0.988 |
ricks | +0.976 |
liner | +0.967 |
� | +0.951 |
Neg logit contributions | |
Hunts | -1.539 |
Engels | -1.376 |
Scand | -1.364 |
Amateur | -1.349 |
Lat | -1.347 |
Token | I |
Token ID | 40 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
inyl | +0.277 |
ricks | +0.245 |
Rah | +0.244 |
liner | +0.243 |
� | +0.240 |
Neg logit contributions | |
Hunts | -0.364 |
Engels | -0.323 |
Scand | -0.322 |
Amateur | -0.319 |
Lat | -0.319 |
Token | think |
Token ID | 892 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
inyl | +0.979 |
ricks | +0.885 |
liner | +0.878 |
� | +0.876 |
Rah | +0.874 |
Neg logit contributions | |
Hunts | -0.988 |
Engels | -0.866 |
Scand | -0.865 |
Amateur | -0.851 |
Lat | -0.847 |
Token | my |
Token ID | 616 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Hunts | +0.232 |
Scand | +0.203 |
Engels | +0.203 |
Amateur | +0.201 |
Lat | +0.201 |
Neg logit contributions | |
inyl | -0.214 |
ricks | -0.192 |
Rah | -0.190 |
liner | -0.190 |
� | -0.188 |
Token | story |
Token ID | 1621 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
inyl | +0.424 |
ricks | +0.382 |
Rah | +0.379 |
liner | +0.379 |
� | +0.378 |
Neg logit contributions | |
Hunts | -0.420 |
Engels | -0.366 |
Scand | -0.363 |
Amateur | -0.360 |
Lat | -0.358 |
Token | 's |
Token ID | 338 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Hunts | +0.071 |
Scand | +0.062 |
Engels | +0.062 |
Lat | +0.061 |
Amateur | +0.061 |
Neg logit contributions | |
inyl | -0.073 |
ricks | -0.065 |
Rah | -0.065 |
liner | -0.064 |
� | -0.064 |
Token | one |
Token ID | 530 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
Hunts | +0.149 |
Engels | +0.130 |
Scand | +0.130 |
Amateur | +0.129 |
Lat | +0.129 |
Neg logit contributions | |
inyl | -0.142 |
ricks | -0.127 |
Rah | -0.126 |
liner | -0.126 |
� | -0.125 |
Token | of |
Token ID | 286 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Hunts | +0.762 |
Engels | +0.662 |
Scand | +0.662 |
Amateur | +0.656 |
Lat | +0.654 |
Neg logit contributions | |
inyl | -0.772 |
ricks | -0.695 |
Rah | -0.690 |
liner | -0.690 |
� | -0.683 |
Token | persever |
Token ID | 45712 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
Hunts | +1.411 |
Scand | +1.226 |
Engels | +1.220 |
Lat | +1.213 |
Amateur | +1.213 |
Neg logit contributions | |
inyl | -1.455 |
ricks | -1.308 |
Rah | -1.301 |
liner | -1.295 |
� | -1.277 |
Token | ance |
Token ID | 590 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Hunts | +0.699 |
Engels | +0.616 |
Scand | +0.615 |
Amateur | +0.612 |
Lat | +0.612 |
Neg logit contributions | |
inyl | -0.552 |
ricks | -0.488 |
Rah | -0.486 |
liner | -0.484 |
� | -0.477 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Hunts | +0.668 |
Engels | +0.582 |
Scand | +0.581 |
Lat | +0.577 |
Amateur | +0.576 |
Neg logit contributions | |
inyl | -0.638 |
ricks | -0.572 |
Rah | -0.569 |
liner | -0.565 |
� | -0.559 |
Token | of |
Token ID | 286 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
Hunts | +0.826 |
Engels | +0.712 |
Scand | +0.708 |
Lat | +0.704 |
Amateur | +0.703 |
Neg logit contributions | |
inyl | -0.906 |
ricks | -0.821 |
Rah | -0.817 |
liner | -0.809 |
� | -0.801 |
Token | Loving |
Token ID | 39202 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
inyl | +1.772 |
ricks | +1.577 |
liner | +1.574 |
� | +1.571 |
Rah | +1.566 |
Neg logit contributions | |
Hunts | -1.830 |
Scand | -1.611 |
Engels | -1.603 |
Amateur | -1.592 |
Lat | -1.575 |
Token | v |
Token ID | 410 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Hunts | +0.875 |
Scand | +0.769 |
Engels | +0.769 |
Amateur | +0.762 |
Lat | +0.760 |
Neg logit contributions | |
inyl | -0.750 |
ricks | -0.667 |
Rah | -0.662 |
liner | -0.661 |
� | -0.654 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
inyl | +1.007 |
� | +0.909 |
Rah | +0.907 |
liner | +0.905 |
ricks | +0.897 |
Neg logit contributions | |
Hunts | -1.013 |
Scand | -0.895 |
Engels | -0.882 |
Amateur | -0.875 |
Lat | -0.863 |
Token | Virginia |
Token ID | 6025 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
inyl | +1.298 |
� | +1.187 |
Rah | +1.185 |
liner | +1.180 |
ricks | +1.162 |
Neg logit contributions | |
Hunts | -1.187 |
Scand | -1.044 |
Engels | -1.030 |
Amateur | -1.020 |
Lat | -1.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
inyl | +3.106 |
liner | +2.791 |
ricks | +2.780 |
� | +2.775 |
Rah | +2.729 |
Neg logit contributions | |
Hunts | -3.263 |
Scand | -2.894 |
Engels | -2.856 |
Amateur | -2.844 |
Lat | -2.793 |
Token | which |
Token ID | 543 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
inyl | +1.116 |
ricks | +1.003 |
liner | +0.993 |
Rah | +0.990 |
� | +0.988 |
Neg logit contributions | |
Hunts | -1.212 |
Scand | -1.066 |
Engels | -1.059 |
Amateur | -1.056 |
Lat | -1.046 |
Token | declared |
Token ID | 6875 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
inyl | +0.797 |
ricks | +0.712 |
liner | +0.708 |
� | +0.708 |
Rah | +0.706 |
Neg logit contributions | |
Hunts | -0.806 |
Scand | -0.707 |
Amateur | -0.701 |
Engels | -0.700 |
Lat | -0.690 |
Token | all |
Token ID | 477 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
inyl | +0.325 |
ricks | +0.291 |
liner | +0.290 |
Rah | +0.289 |
� | +0.289 |
Neg logit contributions | |
Hunts | -0.318 |
Scand | -0.278 |
Engels | -0.276 |
Amateur | -0.274 |
Lat | -0.272 |
Token | state |
Token ID | 1181 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
inyl | +3.007 |
ricks | +2.735 |
� | +2.729 |
liner | +2.683 |
Rah | +2.672 |
Neg logit contributions | |
Hunts | -2.654 |
Scand | -2.343 |
Engels | -2.294 |
Amateur | -2.270 |
Corsair | -2.227 |
Token | { |
Token ID | 1391 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
inyl | +0.684 |
ricks | +0.619 |
Rah | +0.614 |
liner | +0.613 |
� | +0.607 |
Neg logit contributions | |
Hunts | -0.601 |
Scand | -0.517 |
Engels | -0.517 |
Amateur | -0.512 |
Lat | -0.512 |
Token | ( |
Token ID | 7 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Hunts | +0.779 |
Engels | +0.679 |
Scand | +0.678 |
Lat | +0.674 |
Amateur | +0.674 |
Neg logit contributions | |
inyl | -0.752 |
ricks | -0.674 |
liner | -0.665 |
Rah | -0.664 |
� | -0.657 |
Token | 132 |
Token ID | 19924 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Hunts | +0.793 |
Scand | +0.682 |
Engels | +0.682 |
Amateur | +0.675 |
Lat | +0.674 |
Neg logit contributions | |
inyl | -0.916 |
ricks | -0.829 |
Rah | -0.823 |
liner | -0.822 |
� | -0.813 |
Token | s |
Token ID | 82 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
inyl | +1.674 |
ricks | +1.533 |
Rah | +1.521 |
� | +1.519 |
liner | +1.517 |
Neg logit contributions | |
Hunts | -1.457 |
Scand | -1.257 |
Engels | -1.253 |
Amateur | -1.232 |
Lat | -1.229 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
inyl | +1.549 |
� | +1.332 |
ricks | +1.331 |
Rah | +1.325 |
liner | +1.323 |
Neg logit contributions | |
Hunts | -2.661 |
Scand | -2.408 |
Engels | -2.381 |
Amateur | -2.354 |
Lat | -2.340 |
Token | B |
Token ID | 347 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
inyl | +1.729 |
Rah | +1.520 |
ricks | +1.516 |
� | +1.512 |
liner | +1.501 |
Neg logit contributions | |
Hunts | -2.375 |
Engels | -2.108 |
Scand | -2.098 |
Amateur | -2.090 |
Lat | -2.067 |
Token | d |
Token ID | 67 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
inyl | +3.083 |
ricks | +2.796 |
Rah | +2.750 |
liner | +2.729 |
� | +2.715 |
Neg logit contributions | |
Hunts | -3.671 |
Scand | -3.230 |
Engels | -3.225 |
Amateur | -3.204 |
Lat | -3.143 |
Token | 7 |
Token ID | 22 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
Hunts | +0.376 |
Scand | +0.321 |
Engels | +0.321 |
Amateur | +0.318 |
Lat | +0.316 |
Neg logit contributions | |
inyl | -0.451 |
ricks | -0.409 |
Rah | -0.406 |
liner | -0.405 |
� | -0.402 |
Token | { |
Token ID | 1391 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
inyl | +0.122 |
ricks | +0.109 |
Rah | +0.109 |
liner | +0.109 |
� | +0.109 |
Neg logit contributions | |
Hunts | -0.112 |
Engels | -0.097 |
Scand | -0.097 |
Amateur | -0.096 |
Lat | -0.095 |
Token | ( |
Token ID | 7 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
Hunts | +0.497 |
Engels | +0.434 |
Scand | +0.434 |
Amateur | +0.431 |
Lat | +0.430 |
Neg logit contributions | |
inyl | -0.467 |
ricks | -0.418 |
Rah | -0.414 |
liner | -0.413 |
� | -0.409 |
Token | 507 |
Token ID | 35378 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
inyl | +0.052 |
ricks | +0.047 |
Rah | +0.046 |
liner | +0.046 |
� | +0.046 |
Neg logit contributions | |
Hunts | -0.045 |
Scand | -0.039 |
Engels | -0.039 |
Amateur | -0.038 |
Lat | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
inyl | +1.488 |
� | +1.332 |
ricks | +1.331 |
liner | +1.326 |
Rah | +1.319 |
Neg logit contributions | |
Hunts | -1.503 |
Engels | -1.306 |
Scand | -1.302 |
Amateur | -1.298 |
Lat | -1.271 |
Token | 5 |
Token ID | 642 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
Hunts | +0.106 |
Engels | +0.091 |
Scand | +0.091 |
Amateur | +0.091 |
Lat | +0.089 |
Neg logit contributions | |
inyl | -0.117 |
ricks | -0.105 |
Rah | -0.105 |
liner | -0.105 |
� | -0.105 |
Token | )) |
Token ID | 4008 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
inyl | +0.702 |
ricks | +0.630 |
liner | +0.627 |
� | +0.627 |
Rah | +0.626 |
Neg logit contributions | |
Hunts | -0.650 |
Engels | -0.561 |
Scand | -0.560 |
Amateur | -0.556 |
Lat | -0.548 |
Token | sq |
Token ID | 19862 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
Hunts | +1.041 |
Scand | +0.905 |
Engels | +0.903 |
Lat | +0.897 |
Amateur | +0.895 |
Neg logit contributions | |
inyl | -1.068 |
ricks | -0.961 |
Rah | -0.954 |
liner | -0.952 |
� | -0.939 |
Token | K |
Token ID | 42 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
inyl | +2.647 |
Rah | +2.383 |
ricks | +2.370 |
liner | +2.351 |
� | +2.299 |
Neg logit contributions | |
Hunts | -3.148 |
Engels | -2.768 |
Scand | -2.755 |
Amateur | -2.729 |
Lat | -2.675 |
Token | ernel |
Token ID | 7948 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
inyl | +1.488 |
ricks | +1.348 |
Rah | +1.336 |
liner | +1.331 |
� | +1.319 |
Neg logit contributions | |
Hunts | -1.265 |
Scand | -1.090 |
Engels | -1.085 |
Amateur | -1.070 |
Lat | -1.061 |
Token | = |
Token ID | 796 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
inyl | +2.724 |
Rah | +2.427 |
ricks | +2.394 |
liner | +2.392 |
� | +2.382 |
Neg logit contributions | |
Hunts | -3.853 |
Engels | -3.424 |
Scand | -3.416 |
Amateur | -3.385 |
Redmond | -3.301 |
Token | c |
Token ID | 269 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
Hunts | +1.076 |
Scand | +0.963 |
Engels | +0.958 |
Lat | +0.957 |
Amateur | +0.952 |
Neg logit contributions | |
inyl | -0.704 |
ricks | -0.616 |
Rah | -0.608 |
liner | -0.607 |
� | -0.592 |
Token | v |
Token ID | 85 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Hunts | +1.918 |
Engels | +1.696 |
Scand | +1.690 |
Lat | +1.685 |
Amateur | +1.683 |
Neg logit contributions | |
inyl | -1.509 |
ricks | -1.336 |
Rah | -1.333 |
liner | -1.313 |
� | -1.306 |
Token | 2 |
Token ID | 17 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Hunts | +0.157 |
Engels | +0.136 |
Scand | +0.136 |
Amateur | +0.135 |
Lat | +0.134 |
Neg logit contributions | |
inyl | -0.157 |
ricks | -0.141 |
liner | -0.140 |
Rah | -0.140 |
� | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Hunts | +0.841 |
Engels | +0.725 |
Scand | +0.725 |
Amateur | +0.718 |
Lat | +0.717 |
Neg logit contributions | |
inyl | -0.940 |
ricks | -0.849 |
Rah | -0.843 |
liner | -0.842 |
� | -0.834 |
Token | ( |
Token ID | 7 |
Feature activation | -6.81e-02 |
Pos logit contributions | |
Hunts | +1.480 |
Engels | +1.285 |
Lat | +1.284 |
Scand | +1.282 |
Amateur | +1.278 |
Neg logit contributions | |
inyl | -1.499 |
ricks | -1.347 |
liner | -1.321 |
Rah | -1.315 |
� | -1.305 |
Token | 115 |
Token ID | 15363 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
inyl | +0.058 |
ricks | +0.053 |
Rah | +0.052 |
liner | +0.052 |
� | +0.052 |
Neg logit contributions | |
Hunts | -0.047 |
Scand | -0.041 |
Engels | -0.041 |
Amateur | -0.040 |
Lat | -0.040 |
Token | s |
Token ID | 82 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
inyl | +1.535 |
ricks | +1.408 |
Rah | +1.392 |
liner | +1.389 |
� | +1.386 |
Neg logit contributions | |
Hunts | -1.312 |
Scand | -1.129 |
Engels | -1.122 |
Amateur | -1.109 |
Lat | -1.100 |
Token | )} |
Token ID | 38165 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
inyl | +1.364 |
ricks | +1.175 |
� | +1.173 |
Rah | +1.166 |
liner | +1.164 |
Neg logit contributions | |
Hunts | -2.349 |
Scand | -2.126 |
Engels | -2.100 |
Amateur | -2.080 |
Lat | -2.068 |
Token | 5 |
Token ID | 642 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
inyl | +1.369 |
ricks | +1.207 |
Rah | +1.198 |
liner | +1.194 |
� | +1.182 |
Neg logit contributions | |
Hunts | -1.812 |
Scand | -1.605 |
Engels | -1.605 |
Amateur | -1.592 |
Lat | -1.588 |
Token | . |
Token ID | 13 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
inyl | +2.661 |
� | +2.441 |
liner | +2.405 |
Rah | +2.402 |
ricks | +2.360 |
Neg logit contributions | |
Hunts | -2.970 |
Scand | -2.633 |
Engels | -2.597 |
Amateur | -2.555 |
Redmond | -2.510 |
Token | O |
Token ID | 440 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
inyl | +2.900 |
� | +2.590 |
Rah | +2.560 |
ricks | +2.540 |
liner | +2.525 |
Neg logit contributions | |
Hunts | -4.027 |
Engels | -3.563 |
Amateur | -3.548 |
Scand | -3.546 |
Lat | -3.478 |
Token | - |
Token ID | 12 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
inyl | +1.798 |
ricks | +1.622 |
liner | +1.614 |
Rah | +1.611 |
� | +1.598 |
Neg logit contributions | |
Hunts | -1.673 |
Engels | -1.449 |
Scand | -1.444 |
Amateur | -1.435 |
Lat | -1.420 |
Token | O |
Token ID | 46 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
inyl | +0.643 |
ricks | +0.557 |
Rah | +0.555 |
liner | +0.553 |
� | +0.543 |
Neg logit contributions | |
Hunts | -1.049 |
Engels | -0.939 |
Scand | -0.938 |
Amateur | -0.928 |
Lat | -0.925 |
Token | { |
Token ID | 1391 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
Hunts | +0.189 |
Scand | +0.164 |
Engels | +0.164 |
Lat | +0.162 |
Amateur | +0.162 |
Neg logit contributions | |
inyl | -0.202 |
ricks | -0.182 |
Rah | -0.181 |
liner | -0.180 |
� | -0.178 |
Token | ( |
Token ID | 7 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
Hunts | +0.192 |
Scand | +0.168 |
Engels | +0.168 |
Amateur | +0.167 |
Lat | +0.166 |
Neg logit contributions | |
inyl | -0.180 |
ricks | -0.161 |
Rah | -0.160 |
liner | -0.159 |
� | -0.158 |
Token | rahim |
Token ID | 26922 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Hunts | +2.774 |
Lat | +2.460 |
Scand | +2.459 |
Engels | +2.458 |
Amateur | +2.453 |
Neg logit contributions | |
inyl | -1.807 |
ricks | -1.562 |
Rah | -1.556 |
liner | -1.539 |
� | -1.525 |
Token | , |
Token ID | 11 |
Feature activation | -8.65e-01 |
Pos logit contributions | |
Hunts | +0.181 |
Scand | +0.158 |
Engels | +0.157 |
Lat | +0.156 |
Amateur | +0.156 |
Neg logit contributions | |
inyl | -0.176 |
ricks | -0.158 |
Rah | -0.157 |
liner | -0.157 |
� | -0.155 |
Token | r |
Token ID | 374 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
inyl | +0.650 |
ricks | +0.582 |
Rah | +0.578 |
liner | +0.577 |
� | +0.571 |
Neg logit contributions | |
Hunts | -0.691 |
Engels | -0.604 |
Scand | -0.604 |
Amateur | -0.599 |
Lat | -0.597 |
Token | ai |
Token ID | 1872 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
inyl | +0.327 |
ricks | +0.292 |
Rah | +0.290 |
liner | +0.289 |
� | +0.287 |
Neg logit contributions | |
Hunts | -0.361 |
Scand | -0.316 |
Engels | -0.316 |
Amateur | -0.314 |
Lat | -0.313 |
Token | han |
Token ID | 7637 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
inyl | +1.020 |
ricks | +0.914 |
Rah | +0.911 |
liner | +0.908 |
� | +0.898 |
Neg logit contributions | |
Hunts | -1.040 |
Scand | -0.907 |
Engels | -0.906 |
Amateur | -0.896 |
Lat | -0.895 |
Token | must |
Token ID | 1276 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
inyl | +1.424 |
ricks | +1.276 |
Rah | +1.273 |
liner | +1.266 |
� | +1.257 |
Neg logit contributions | |
Hunts | -1.471 |
Scand | -1.288 |
Engels | -1.284 |
Amateur | -1.270 |
Lat | -1.261 |
Token | afa |
Token ID | 28485 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
inyl | +3.285 |
� | +2.938 |
ricks | +2.903 |
Rah | +2.846 |
liner | +2.801 |
Neg logit contributions | |
Hunts | -3.901 |
Scand | -3.444 |
Engels | -3.421 |
Lat | -3.379 |
Amateur | -3.349 |
Token | k |
Token ID | 479 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
inyl | +0.812 |
ricks | +0.727 |
Rah | +0.723 |
liner | +0.719 |
� | +0.717 |
Neg logit contributions | |
Hunts | -0.877 |
Scand | -0.768 |
Engels | -0.767 |
Amateur | -0.760 |
Lat | -0.756 |
Token | am |
Token ID | 321 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
inyl | +1.399 |
ricks | +1.253 |
liner | +1.248 |
Rah | +1.244 |
� | +1.236 |
Neg logit contributions | |
Hunts | -1.382 |
Scand | -1.217 |
Engels | -1.208 |
Amateur | -1.184 |
Lat | -1.174 |
Token | al |
Token ID | 282 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
inyl | +1.676 |
ricks | +1.476 |
liner | +1.470 |
� | +1.465 |
Rah | +1.464 |
Neg logit contributions | |
Hunts | -2.094 |
Scand | -1.867 |
Engels | -1.862 |
Amateur | -1.825 |
Lat | -1.810 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
inyl | +0.955 |
ricks | +0.856 |
Rah | +0.850 |
liner | +0.848 |
� | +0.841 |
Neg logit contributions | |
Hunts | -0.995 |
Engels | -0.870 |
Scand | -0.869 |
Amateur | -0.861 |
Lat | -0.858 |