Token | not |
Token ID | 407 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
.? | +0.638 |
verty | +0.542 |
numbered | +0.542 |
BLE | +0.536 |
ounty | +0.527 |
Neg logit contributions | |
xual | -0.649 |
fell | -0.621 |
Salman | -0.621 |
ctrl | -0.619 |
illin | -0.614 |
Token | affiliated |
Token ID | 18552 |
Feature activation | +5.82e+00 |
Pos logit contributions | |
xual | +0.330 |
Salman | +0.319 |
fell | +0.317 |
ctrl | +0.316 |
ente | +0.313 |
Neg logit contributions | |
.? | -0.331 |
verty | -0.283 |
numbered | -0.282 |
BLE | -0.279 |
ounty | -0.274 |
Token | with |
Token ID | 351 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
.? | +3.924 |
numbered | +3.203 |
BLE | +3.160 |
verty | +3.146 |
ounty | +3.125 |
Neg logit contributions | |
xual | -4.542 |
fell | -4.382 |
Salman | -4.345 |
ctrl | -4.337 |
illin | -4.321 |
Token | Sky |
Token ID | 5274 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
.? | +1.439 |
verty | +1.231 |
numbered | +1.222 |
BLE | +1.214 |
ounty | +1.199 |
Neg logit contributions | |
xual | -1.310 |
ctrl | -1.254 |
fell | -1.245 |
Salman | -1.241 |
illin | -1.234 |
Token | High |
Token ID | 3334 |
Feature activation | +8.76e+00 |
Pos logit contributions | |
.? | +2.573 |
verty | +2.173 |
BLE | +2.148 |
numbered | +2.141 |
ounty | +2.121 |
Neg logit contributions | |
xual | -2.345 |
Salman | -2.256 |
ctrl | -2.241 |
illin | -2.236 |
ente | -2.222 |
Token | Hol |
Token ID | 6479 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
.? | +5.325 |
verty | +4.109 |
ounty | +3.978 |
numbered | +3.921 |
BLE | +3.895 |
Neg logit contributions | |
xual | -7.204 |
ctrl | -7.175 |
Salman | -7.126 |
illin | -7.082 |
ente | -7.032 |
Token | istic |
Token ID | 2569 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
.? | +8.981 |
numbered | +7.049 |
ounty | +6.912 |
verty | +6.765 |
BLE | +6.742 |
Neg logit contributions | |
Collider | -12.602 |
Salman | -12.431 |
xual | -12.324 |
illin | -12.238 |
ctrl | -11.953 |
Token | but |
Token ID | 475 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
.? | +2.861 |
verty | +2.416 |
numbered | +2.394 |
BLE | +2.366 |
ounty | +2.342 |
Neg logit contributions | |
xual | -2.313 |
Salman | -2.227 |
ctrl | -2.225 |
illin | -2.222 |
fell | -2.197 |
Token | lost |
Token ID | 2626 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
xual | +0.259 |
Salman | +0.248 |
fell | +0.247 |
ctrl | +0.247 |
illin | +0.244 |
Neg logit contributions | |
.? | -0.296 |
verty | -0.255 |
numbered | -0.254 |
BLE | -0.251 |
ounty | -0.248 |
Token | power |
Token ID | 1176 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
xual | +0.442 |
Salman | +0.426 |
fell | +0.424 |
ctrl | +0.422 |
ente | +0.417 |
Neg logit contributions | |
.? | -0.463 |
verty | -0.398 |
numbered | -0.397 |
BLE | -0.392 |
ounty | -0.386 |
Token | and |
Token ID | 290 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
.? | +0.937 |
numbered | +0.805 |
verty | +0.801 |
BLE | +0.791 |
ounty | +0.779 |
Neg logit contributions | |
xual | -0.838 |
Salman | -0.803 |
ctrl | -0.799 |
fell | -0.796 |
ente | -0.790 |
Token | in |
Token ID | 287 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
.? | +3.604 |
numbered | +3.060 |
verty | +3.005 |
BLE | +2.984 |
ounty | +2.924 |
Neg logit contributions | |
xual | -3.392 |
ctrl | -3.218 |
illin | -3.205 |
fell | -3.204 |
ente | -3.201 |
Token | the |
Token ID | 262 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
xual | +0.198 |
Salman | +0.191 |
fell | +0.190 |
ctrl | +0.189 |
illin | +0.187 |
Neg logit contributions | |
.? | -0.212 |
verty | -0.182 |
numbered | -0.181 |
BLE | -0.179 |
ounty | -0.176 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
.? | +0.026 |
verty | +0.022 |
numbered | +0.022 |
BLE | +0.022 |
ounty | +0.021 |
Neg logit contributions | |
xual | -0.023 |
Salman | -0.022 |
fell | -0.022 |
ctrl | -0.022 |
illin | -0.022 |
Token | p |
Token ID | 279 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
.? | +3.092 |
verty | +2.696 |
numbered | +2.692 |
BLE | +2.661 |
ounty | +2.639 |
Neg logit contributions | |
xual | -2.203 |
ctrl | -2.100 |
Salman | -2.093 |
fell | -2.080 |
ente | -2.061 |
Token | . |
Token ID | 13 |
Feature activation | +7.44e+00 |
Pos logit contributions | |
.? | +4.987 |
BLE | +3.953 |
numbered | +3.922 |
ounty | +3.916 |
ANA | +3.830 |
Neg logit contributions | |
xual | -5.068 |
illin | -4.752 |
Collider | -4.749 |
Salman | -4.745 |
ctrl | -4.715 |
Token | m |
Token ID | 76 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
.? | +5.591 |
numbered | +4.619 |
BLE | +4.569 |
ANA | +4.431 |
ounty | +4.387 |
Neg logit contributions | |
xual | -5.312 |
Collider | -5.155 |
ailable | -5.069 |
Salman | -4.877 |
illin | -4.873 |
Token | . |
Token ID | 13 |
Feature activation | +8.01e+00 |
Pos logit contributions | |
.? | +9.794 |
BLE | +7.132 |
ounty | +7.129 |
numbered | +7.073 |
bleed | +7.025 |
Neg logit contributions | |
xual | -11.251 |
ailable | -10.608 |
ctrl | -10.574 |
Salman | -10.518 |
illin | -10.516 |
Token | ET |
Token ID | 12152 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
.? | +5.656 |
numbered | +4.786 |
BLE | +4.712 |
bleed | +4.694 |
verty | +4.602 |
Neg logit contributions | |
xual | -5.950 |
ailable | -5.661 |
ctrl | -5.588 |
illin | -5.526 |
ente | -5.496 |
Token | hour |
Token ID | 1711 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
.? | +3.368 |
numbered | +2.872 |
BLE | +2.816 |
verty | +2.794 |
ounty | +2.744 |
Neg logit contributions | |
xual | -3.374 |
ctrl | -3.192 |
Salman | -3.181 |
ailable | -3.165 |
illin | -3.151 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
.? | +0.667 |
numbered | +0.580 |
verty | +0.577 |
BLE | +0.570 |
ounty | +0.563 |
Neg logit contributions | |
xual | -0.537 |
Salman | -0.513 |
fell | -0.510 |
ctrl | -0.510 |
illin | -0.504 |
Token | and |
Token ID | 290 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
.? | +1.468 |
numbered | +1.259 |
verty | +1.255 |
BLE | +1.243 |
ounty | +1.218 |
Neg logit contributions | |
xual | -1.402 |
ctrl | -1.335 |
fell | -1.327 |
Salman | -1.325 |
illin | -1.320 |
Token | 1 |
Token ID | 352 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Salman | +2.593 |
xual | +2.583 |
fell | +2.563 |
ctrl | +2.520 |
Collider | +2.471 |
Neg logit contributions | |
.? | -3.547 |
verty | -3.202 |
numbered | -3.137 |
ounty | -3.120 |
BLE | -3.103 |
Token | , |
Token ID | 11 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
.? | +2.219 |
verty | +1.930 |
numbered | +1.917 |
BLE | +1.898 |
ounty | +1.877 |
Neg logit contributions | |
xual | -1.595 |
Salman | -1.513 |
illin | -1.511 |
fell | -1.505 |
ctrl | -1.502 |
Token | 9 |
Token ID | 860 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
xual | +1.161 |
Salman | +1.133 |
fell | +1.114 |
ctrl | +1.088 |
Collider | +1.071 |
Neg logit contributions | |
.? | -2.881 |
verty | -2.614 |
numbered | -2.598 |
BLE | -2.573 |
ounty | -2.553 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
.? | +2.709 |
numbered | +2.363 |
BLE | +2.354 |
verty | +2.351 |
ounty | +2.336 |
Neg logit contributions | |
xual | -1.673 |
ctrl | -1.566 |
Salman | -1.565 |
fell | -1.555 |
Collider | -1.548 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
.? | +6.861 |
BLE | +5.120 |
ounty | +5.091 |
numbered | +5.083 |
ANA | +5.032 |
Neg logit contributions | |
xual | -8.034 |
Collider | -7.591 |
illin | -7.560 |
ailable | -7.527 |
ente | -7.362 |
Token | m |
Token ID | 76 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
.? | +7.128 |
numbered | +5.866 |
BLE | +5.626 |
ANA | +5.531 |
ounty | +5.501 |
Neg logit contributions | |
xual | -7.892 |
Collider | -7.815 |
ailable | -7.455 |
illin | -7.259 |
Salman | -7.256 |
Token | . |
Token ID | 13 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
.? | +9.583 |
ounty | +7.164 |
verty | +7.088 |
BLE | +7.011 |
numbered | +6.830 |
Neg logit contributions | |
xual | -10.751 |
Salman | -10.171 |
Collider | -10.035 |
fell | -9.950 |
illin | -9.933 |
Token | PT |
Token ID | 19310 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
.? | +4.905 |
BLE | +4.059 |
numbered | +4.056 |
ounty | +4.048 |
verty | +4.030 |
Neg logit contributions | |
xual | -5.052 |
illin | -4.743 |
Salman | -4.736 |
ailable | -4.722 |
ente | -4.700 |
Token | . |
Token ID | 13 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
.? | +4.694 |
numbered | +3.898 |
BLE | +3.880 |
verty | +3.851 |
ounty | +3.796 |
Neg logit contributions | |
xual | -4.397 |
fell | -4.091 |
Salman | -4.088 |
Collider | -4.072 |
illin | -4.071 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
.? | +2.858 |
numbered | +2.445 |
verty | +2.421 |
BLE | +2.404 |
ounty | +2.373 |
Neg logit contributions | |
xual | -2.820 |
fell | -2.646 |
ente | -2.638 |
Salman | -2.638 |
ctrl | -2.631 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
.? | +1.674 |
numbered | +1.414 |
BLE | +1.407 |
verty | +1.370 |
ounty | +1.368 |
Neg logit contributions | |
xual | -1.564 |
Collider | -1.443 |
Salman | -1.433 |
illin | -1.432 |
ailable | -1.432 |
Token | . |
Token ID | 13 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
.? | +4.172 |
numbered | +3.554 |
BLE | +3.513 |
ounty | +3.410 |
verty | +3.401 |
Neg logit contributions | |
xual | -3.862 |
Salman | -3.703 |
ctrl | -3.659 |
illin | -3.656 |
ente | -3.612 |
Token | com |
Token ID | 785 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
xual | +1.257 |
fell | +1.230 |
Salman | +1.221 |
ctrl | +1.221 |
ente | +1.207 |
Neg logit contributions | |
.? | -1.399 |
verty | -1.220 |
numbered | -1.201 |
BLE | -1.180 |
ounty | -1.175 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -4.32e+00 |
Pos logit contributions | |
.? | +3.855 |
numbered | +3.331 |
BLE | +3.267 |
verty | +3.238 |
ANA | +3.155 |
Neg logit contributions | |
xual | -3.763 |
ctrl | -3.601 |
Salman | -3.600 |
illin | -3.571 |
ente | -3.509 |
Token | 92 |
Token ID | 5892 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
fell | +2.174 |
xual | +2.163 |
ctrl | +2.135 |
Salman | +2.117 |
illin | +2.112 |
Neg logit contributions | |
.? | -4.001 |
verty | -3.585 |
numbered | -3.541 |
BLE | -3.492 |
ounty | -3.471 |
Token | ] |
Token ID | 60 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
xual | +0.358 |
Salman | +0.346 |
fell | +0.345 |
ctrl | +0.344 |
illin | +0.340 |
Neg logit contributions | |
.? | -0.294 |
verty | -0.247 |
numbered | -0.247 |
BLE | -0.243 |
ounty | -0.238 |
Token | SB |
Token ID | 18056 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
.? | +1.374 |
numbered | +1.176 |
verty | +1.171 |
BLE | +1.162 |
ounty | +1.137 |
Neg logit contributions | |
xual | -1.328 |
ctrl | -1.268 |
Salman | -1.266 |
fell | -1.260 |
illin | -1.250 |
Token | Nation |
Token ID | 8741 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
.? | +5.661 |
ANA | +4.561 |
BLE | +4.435 |
ounty | +4.338 |
verty | +3.870 |
Neg logit contributions | |
xual | -13.540 |
Salman | -12.929 |
fell | -12.744 |
ctrl | -12.594 |
illin | -12.502 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
.? | +4.258 |
numbered | +3.615 |
BLE | +3.592 |
verty | +3.498 |
ounty | +3.452 |
Neg logit contributions | |
xual | -4.326 |
Salman | -4.174 |
ctrl | -4.153 |
illin | -4.088 |
ente | -4.071 |
Token | 93 |
Token ID | 6052 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
xual | +2.215 |
fell | +2.202 |
ctrl | +2.182 |
att | +2.146 |
Salman | +2.120 |
Neg logit contributions | |
.? | -5.929 |
verty | -5.389 |
numbered | -5.326 |
BLE | -5.250 |
ounty | -5.225 |
Token | ] |
Token ID | 60 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
xual | +2.187 |
Salman | +2.129 |
fell | +2.119 |
ctrl | +2.105 |
Collider | +2.088 |
Neg logit contributions | |
.? | -1.976 |
numbered | -1.677 |
verty | -1.674 |
BLE | -1.634 |
ounty | -1.608 |
Token | and |
Token ID | 290 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
.? | +1.770 |
numbered | +1.512 |
verty | +1.505 |
BLE | +1.495 |
ounty | +1.459 |
Neg logit contributions | |
xual | -1.751 |
ctrl | -1.674 |
Salman | -1.667 |
fell | -1.661 |
illin | -1.649 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
xual | +0.428 |
Salman | +0.411 |
fell | +0.409 |
ctrl | +0.407 |
illin | +0.403 |
Neg logit contributions | |
.? | -0.540 |
verty | -0.470 |
numbered | -0.469 |
BLE | -0.464 |
ounty | -0.457 |
Token | Charlotte |
Token ID | 14685 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
xual | +0.819 |
Salman | +0.796 |
fell | +0.788 |
ctrl | +0.785 |
ente | +0.778 |
Neg logit contributions | |
.? | -1.017 |
verty | -0.887 |
numbered | -0.884 |
BLE | -0.874 |
ounty | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
.? | +2.118 |
verty | +1.805 |
numbered | +1.804 |
BLE | +1.793 |
ounty | +1.770 |
Neg logit contributions | |
xual | -1.790 |
ctrl | -1.698 |
fell | -1.690 |
Salman | -1.682 |
illin | -1.680 |
Token |
|
Token ID | 198 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
Salman | +1.977 |
xual | +1.976 |
fell | +1.934 |
ctrl | +1.910 |
Collider | +1.906 |
Neg logit contributions | |
.? | -2.859 |
verty | -2.544 |
numbered | -2.517 |
BLE | -2.481 |
ounty | -2.467 |
Token |
|
Token ID | 198 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Salman | +2.358 |
fell | +2.355 |
ctrl | +2.305 |
xual | +2.295 |
att | +2.270 |
Neg logit contributions | |
.? | -3.738 |
verty | -3.446 |
numbered | -3.332 |
BLE | -3.286 |
ounty | -3.278 |
Token | Mother |
Token ID | 31398 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
fell | +1.279 |
xual | +1.278 |
Salman | +1.277 |
ctrl | +1.272 |
att | +1.254 |
Neg logit contributions | |
.? | -1.886 |
verty | -1.681 |
numbered | -1.660 |
ounty | -1.625 |
BLE | -1.622 |
Token | s |
Token ID | 82 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
.? | +7.310 |
BLE | +6.307 |
numbered | +5.926 |
verty | +5.689 |
ANA | +5.673 |
Neg logit contributions | |
xual | -11.920 |
ctrl | -11.315 |
illin | -11.209 |
fell | -11.098 |
Salman | -10.926 |
Token | of |
Token ID | 286 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
.? | +3.047 |
numbered | +2.613 |
BLE | +2.588 |
verty | +2.571 |
ounty | +2.500 |
Neg logit contributions | |
xual | -2.884 |
ctrl | -2.710 |
fell | -2.698 |
Salman | -2.683 |
illin | -2.656 |
Token | the |
Token ID | 262 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
xual | +0.604 |
Salman | +0.587 |
fell | +0.584 |
ctrl | +0.581 |
illin | +0.575 |
Neg logit contributions | |
.? | -0.596 |
verty | -0.507 |
numbered | -0.506 |
BLE | -0.499 |
ounty | -0.492 |
Token | Movement |
Token ID | 15477 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
xual | +0.166 |
Salman | +0.161 |
fell | +0.160 |
ctrl | +0.160 |
illin | +0.158 |
Neg logit contributions | |
.? | -0.159 |
verty | -0.135 |
numbered | -0.135 |
BLE | -0.133 |
ounty | -0.131 |
Token | , |
Token ID | 11 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
.? | +0.312 |
numbered | +0.269 |
verty | +0.268 |
BLE | +0.265 |
ounty | +0.260 |
Neg logit contributions | |
xual | -0.278 |
Salman | -0.266 |
fell | -0.266 |
ctrl | -0.265 |
illin | -0.263 |
Token | ... |
Token ID | 2644 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
.? | +1.395 |
numbered | +1.196 |
verty | +1.192 |
BLE | +1.181 |
ounty | +1.163 |
Neg logit contributions | |
xual | -1.175 |
Salman | -1.124 |
ctrl | -1.118 |
fell | -1.117 |
illin | -1.105 |
Token | at |
Token ID | 379 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
.? | +1.417 |
numbered | +1.218 |
verty | +1.210 |
BLE | +1.204 |
ounty | +1.177 |
Neg logit contributions | |
xual | -1.265 |
Salman | -1.215 |
fell | -1.207 |
ctrl | -1.207 |
illin | -1.195 |
Token | 4 |
Token ID | 604 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
.? | +0.461 |
numbered | +0.395 |
verty | +0.395 |
BLE | +0.391 |
ounty | +0.384 |
Neg logit contributions | |
xual | -0.421 |
Salman | -0.401 |
ctrl | -0.400 |
fell | -0.400 |
illin | -0.397 |
Token | a |
Token ID | 257 |
Feature activation | +8.71e+00 |
Pos logit contributions | |
.? | +4.486 |
numbered | +3.842 |
BLE | +3.827 |
verty | +3.785 |
ounty | +3.760 |
Neg logit contributions | |
xual | -3.414 |
fell | -3.261 |
Collider | -3.251 |
Salman | -3.233 |
ctrl | -3.204 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
.? | +6.248 |
numbered | +4.724 |
BLE | +4.717 |
ounty | +4.654 |
ANA | +4.619 |
Neg logit contributions | |
xual | -6.637 |
ailable | -6.378 |
illin | -6.287 |
Collider | -6.203 |
ente | -6.148 |
Token | m |
Token ID | 76 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
.? | +7.954 |
numbered | +6.476 |
BLE | +6.146 |
ounty | +6.048 |
ANA | +5.999 |
Neg logit contributions | |
xual | -9.021 |
Collider | -8.884 |
ailable | -8.674 |
Salman | -8.304 |
illin | -8.178 |
Token | . |
Token ID | 13 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
.? | +9.844 |
ounty | +6.941 |
BLE | +6.908 |
ANA | +6.828 |
bleed | +6.806 |
Neg logit contributions | |
xual | -10.008 |
fell | -9.737 |
Collider | -9.672 |
Salman | -9.520 |
illin | -9.515 |
Token | ... |
Token ID | 2644 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
.? | +5.047 |
numbered | +4.137 |
BLE | +4.058 |
verty | +4.050 |
bleed | +3.997 |
Neg logit contributions | |
xual | -4.807 |
ailable | -4.636 |
fell | -4.623 |
ctrl | -4.602 |
Salman | -4.562 |
Token | after |
Token ID | 706 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
.? | +1.710 |
numbered | +1.461 |
verty | +1.450 |
BLE | +1.441 |
ounty | +1.412 |
Neg logit contributions | |
xual | -1.566 |
Salman | -1.500 |
ctrl | -1.495 |
fell | -1.493 |
illin | -1.476 |
Token | a |
Token ID | 257 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
xual | +1.387 |
Salman | +1.343 |
fell | +1.336 |
ctrl | +1.324 |
ente | +1.318 |
Neg logit contributions | |
.? | -1.507 |
verty | -1.307 |
numbered | -1.304 |
BLE | -1.281 |
ounty | -1.266 |
Token | prim |
Token ID | 2684 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
xual | +0.187 |
Salman | +0.180 |
fell | +0.179 |
ctrl | +0.179 |
illin | +0.177 |
Neg logit contributions | |
.? | -0.193 |
verty | -0.164 |
numbered | -0.164 |
BLE | -0.162 |
ounty | -0.159 |
Token | local |
Token ID | 1957 |
Feature activation | +8.93e+00 |
Pos logit contributions | |
.? | +0.871 |
verty | +0.753 |
numbered | +0.753 |
BLE | +0.744 |
ounty | +0.733 |
Neg logit contributions | |
xual | -0.736 |
Salman | -0.705 |
fell | -0.703 |
ctrl | -0.701 |
illin | -0.693 |
Token | public |
Token ID | 1171 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
.? | +6.184 |
verty | +5.167 |
numbered | +5.141 |
ounty | +5.045 |
BLE | +5.036 |
Neg logit contributions | |
xual | -6.867 |
ailable | -6.289 |
Salman | -6.227 |
fell | -6.218 |
ctrl | -6.198 |
Token | - |
Token ID | 12 |
Feature activation | +4.59e+00 |
Pos logit contributions | |
.? | +3.420 |
numbered | +2.880 |
verty | +2.875 |
BLE | +2.830 |
ounty | +2.777 |
Neg logit contributions | |
xual | -3.866 |
Salman | -3.652 |
ente | -3.647 |
fell | -3.645 |
illin | -3.643 |
Token | radio |
Token ID | 37004 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
.? | +3.886 |
numbered | +3.428 |
verty | +3.387 |
BLE | +3.345 |
ounty | +3.301 |
Neg logit contributions | |
xual | -2.817 |
Salman | -2.684 |
Collider | -2.629 |
illin | -2.621 |
fell | -2.619 |
Token | affiliate |
Token ID | 17375 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
.? | +4.224 |
numbered | +3.327 |
verty | +3.233 |
BLE | +3.198 |
ounty | +3.181 |
Neg logit contributions | |
xual | -7.299 |
illin | -6.968 |
ctrl | -6.924 |
fell | -6.875 |
ailable | -6.846 |
Token | KP |
Token ID | 45814 |
Feature activation | +1.37e+01 |
Pos logit contributions | |
.? | +5.474 |
numbered | +4.600 |
BLE | +4.583 |
verty | +4.574 |
ANA | +4.491 |
Neg logit contributions | |
xual | -5.380 |
ctrl | -5.004 |
ailable | -4.993 |
fell | -4.980 |
illin | -4.969 |
Token | CC |
Token ID | 4093 |
Feature activation | +8.21e+00 |
Pos logit contributions | |
.? | +8.335 |
ANA | +7.196 |
BLE | +6.669 |
UGE | +6.601 |
ounty | +6.581 |
Neg logit contributions | |
xual | -11.011 |
fell | -10.266 |
ailable | -10.062 |
Salman | -9.996 |
ctrl | -9.903 |
Token | studios |
Token ID | 20747 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
.? | +6.070 |
numbered | +5.034 |
ANA | +4.948 |
BLE | +4.946 |
verty | +4.938 |
Neg logit contributions | |
xual | -5.963 |
ailable | -5.594 |
ctrl | -5.586 |
fell | -5.565 |
Salman | -5.471 |
Token | September |
Token ID | 2693 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
.? | +0.304 |
verty | +0.263 |
numbered | +0.263 |
BLE | +0.260 |
ounty | +0.256 |
Neg logit contributions | |
xual | -0.258 |
Salman | -0.247 |
fell | -0.246 |
ctrl | -0.245 |
illin | -0.243 |
Token | 29 |
Token ID | 2808 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
xual | +1.069 |
Salman | +1.046 |
fell | +1.040 |
ctrl | +1.026 |
ente | +1.014 |
Neg logit contributions | |
.? | -1.380 |
verty | -1.215 |
numbered | -1.206 |
BLE | -1.195 |
ounty | -1.185 |
Token | , |
Token ID | 11 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
.? | +2.987 |
numbered | +2.579 |
BLE | +2.531 |
verty | +2.521 |
ounty | +2.475 |
Neg logit contributions | |
xual | -2.409 |
ailable | -2.252 |
illin | -2.237 |
Collider | -2.221 |
ctrl | -2.218 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
.? | +1.797 |
numbered | +1.555 |
verty | +1.545 |
BLE | +1.541 |
ounty | +1.530 |
Neg logit contributions | |
xual | -1.237 |
Salman | -1.179 |
Collider | -1.171 |
fell | -1.157 |
ctrl | -1.155 |
Token | O |
Token ID | 46 |
Feature activation | +9.20e+00 |
Pos logit contributions | |
.? | +3.146 |
numbered | +2.672 |
verty | +2.666 |
BLE | +2.658 |
ANA | +2.600 |
Neg logit contributions | |
xual | -3.183 |
ctrl | -3.045 |
fell | -3.041 |
Salman | -3.025 |
Collider | -3.022 |
Token | . |
Token ID | 13 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
.? | +6.653 |
BLE | +5.373 |
ounty | +5.285 |
verty | +5.276 |
numbered | +5.221 |
Neg logit contributions | |
xual | -6.544 |
Collider | -6.412 |
ctrl | -6.319 |
illin | -6.255 |
fell | -6.233 |
Token | R |
Token ID | 49 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
.? | +4.770 |
numbered | +4.073 |
BLE | +4.073 |
verty | +4.055 |
ANA | +3.972 |
Neg logit contributions | |
xual | -4.681 |
ctrl | -4.456 |
Collider | -4.446 |
illin | -4.387 |
fell | -4.382 |
Token | . |
Token ID | 13 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
.? | +7.348 |
BLE | +5.833 |
ounty | +5.779 |
verty | +5.760 |
ANA | +5.739 |
Neg logit contributions | |
xual | -7.311 |
Collider | -7.047 |
ctrl | -7.017 |
illin | -6.894 |
fell | -6.847 |
Token | S |
Token ID | 50 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
.? | +4.245 |
BLE | +3.607 |
numbered | +3.576 |
verty | +3.553 |
ANA | +3.506 |
Neg logit contributions | |
xual | -4.307 |
ctrl | -4.156 |
Collider | -4.142 |
illin | -4.118 |
Salman | -4.095 |
Token | . |
Token ID | 13 |
Feature activation | +7.20e+00 |
Pos logit contributions | |
.? | +9.459 |
BLE | +7.459 |
ANA | +7.400 |
ounty | +7.384 |
verty | +7.265 |
Neg logit contributions | |
xual | -9.166 |
Collider | -9.099 |
ctrl | -8.931 |
illin | -8.810 |
Salman | -8.662 |
Token | A |
Token ID | 32 |
Feature activation | +1.28e+01 |
Pos logit contributions | |
.? | +5.235 |
BLE | +4.486 |
numbered | +4.462 |
verty | +4.404 |
ANA | +4.395 |
Neg logit contributions | |
xual | -4.984 |
Collider | -4.798 |
ctrl | -4.794 |
illin | -4.779 |
Salman | -4.741 |
Token | . |
Token ID | 13 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
.? | +8.985 |
BLE | +7.143 |
ounty | +7.009 |
verty | +6.934 |
ANA | +6.931 |
Neg logit contributions | |
Collider | -8.762 |
xual | -8.738 |
ctrl | -8.596 |
illin | -8.495 |
ailable | -8.319 |
Token | I |
Token ID | 40 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
.? | +5.270 |
BLE | +4.532 |
numbered | +4.487 |
verty | +4.427 |
ANA | +4.421 |
Neg logit contributions | |
xual | -5.040 |
Collider | -4.859 |
ctrl | -4.843 |
illin | -4.825 |
Salman | -4.771 |
Token | . |
Token ID | 13 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
.? | +4.787 |
BLE | +4.009 |
numbered | +3.960 |
ounty | +3.934 |
verty | +3.924 |
Neg logit contributions | |
xual | -4.305 |
Collider | -4.228 |
ctrl | -4.182 |
illin | -4.166 |
Salman | -4.156 |
Token | in |
Token ID | 287 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
.? | +0.100 |
verty | +0.086 |
numbered | +0.086 |
BLE | +0.085 |
ounty | +0.083 |
Neg logit contributions | |
xual | -0.091 |
Salman | -0.088 |
fell | -0.087 |
ctrl | -0.087 |
illin | -0.086 |
Token | My |
Token ID | 2011 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
.? | +0.187 |
verty | +0.160 |
numbered | +0.160 |
BLE | +0.158 |
ounty | +0.156 |
Neg logit contributions | |
xual | -0.177 |
Salman | -0.170 |
fell | -0.169 |
ctrl | -0.169 |
illin | -0.167 |
Token | h |
Token ID | 71 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
xual | +1.633 |
fell | +1.572 |
Salman | +1.568 |
ctrl | +1.566 |
ente | +1.539 |
Neg logit contributions | |
.? | -2.029 |
verty | -1.761 |
numbered | -1.757 |
BLE | -1.735 |
ounty | -1.717 |
Token | re |
Token ID | 260 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
.? | +2.408 |
verty | +2.077 |
numbered | +2.062 |
BLE | +2.026 |
ounty | +2.016 |
Neg logit contributions | |
xual | -2.094 |
Salman | -1.972 |
ctrl | -1.953 |
Collider | -1.952 |
fell | -1.945 |
Token | et |
Token ID | 2123 |
Feature activation | +7.87e+00 |
Pos logit contributions | |
.? | +2.380 |
verty | +2.057 |
numbered | +2.046 |
BLE | +2.036 |
ounty | +1.983 |
Neg logit contributions | |
xual | -2.088 |
Salman | -2.003 |
ctrl | -1.987 |
ente | -1.982 |
illin | -1.970 |
Token | al |
Token ID | 435 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
.? | +4.869 |
numbered | +3.716 |
verty | +3.696 |
bleed | +3.556 |
BLE | +3.526 |
Neg logit contributions | |
xual | -6.703 |
ailable | -6.307 |
ctrl | -6.277 |
Collider | -6.264 |
ente | -6.244 |
Token | . |
Token ID | 13 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
.? | +9.214 |
verty | +6.972 |
ounty | +6.953 |
numbered | +6.930 |
BLE | +6.885 |
Neg logit contributions | |
xual | -9.480 |
Collider | -9.397 |
ctrl | -9.287 |
illin | -9.272 |
fell | -9.271 |
Token | ( |
Token ID | 357 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
.? | +4.203 |
numbered | +3.645 |
verty | +3.595 |
BLE | +3.574 |
ounty | +3.502 |
Neg logit contributions | |
xual | -3.433 |
ctrl | -3.320 |
illin | -3.307 |
fell | -3.300 |
ente | -3.298 |
Token | 1998 |
Token ID | 21113 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
.? | +2.033 |
numbered | +1.797 |
verty | +1.776 |
BLE | +1.774 |
ounty | +1.731 |
Neg logit contributions | |
xual | -1.367 |
Salman | -1.284 |
ctrl | -1.271 |
illin | -1.270 |
Collider | -1.267 |
Token | ) |
Token ID | 8 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
.? | +3.251 |
numbered | +2.863 |
verty | +2.846 |
BLE | +2.846 |
ounty | +2.780 |
Neg logit contributions | |
xual | -2.090 |
Salman | -1.966 |
illin | -1.966 |
ctrl | -1.954 |
ente | -1.949 |
Token | and |
Token ID | 290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
.? | +3.786 |
numbered | +3.258 |
BLE | +3.207 |
verty | +3.201 |
ounty | +3.131 |
Neg logit contributions | |
xual | -3.353 |
illin | -3.216 |
ctrl | -3.204 |
Salman | -3.202 |
ente | -3.187 |
Token | Sporting |
Token ID | 31790 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
.? | +1.282 |
numbered | +1.096 |
verty | +1.094 |
BLE | +1.082 |
ounty | +1.060 |
Neg logit contributions | |
xual | -1.270 |
Salman | -1.215 |
ctrl | -1.214 |
fell | -1.210 |
illin | -1.199 |
Token | News |
Token ID | 3000 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
.? | +7.108 |
BLE | +6.222 |
numbered | +6.141 |
ANA | +5.958 |
verty | +5.829 |
Neg logit contributions | |
xual | -7.892 |
ente | -7.436 |
Salman | -7.407 |
illin | -7.375 |
fell | -7.317 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
.? | +3.262 |
numbered | +2.764 |
verty | +2.752 |
BLE | +2.746 |
ANA | +2.649 |
Neg logit contributions | |
xual | -3.272 |
Salman | -3.172 |
ctrl | -3.128 |
illin | -3.109 |
ente | -3.100 |
Token | 99 |
Token ID | 2079 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ctrl | +3.926 |
xual | +3.880 |
att | +3.860 |
fell | +3.827 |
ente | +3.734 |
Neg logit contributions | |
.? | -5.380 |
verty | -4.788 |
numbered | -4.663 |
BLE | -4.591 |
ounty | -4.527 |
Token | ] |
Token ID | 60 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
xual | +1.249 |
Salman | +1.212 |
fell | +1.210 |
ctrl | +1.205 |
ente | +1.191 |
Neg logit contributions | |
.? | -1.089 |
verty | -0.917 |
numbered | -0.916 |
BLE | -0.900 |
ounty | -0.885 |
Token | SB |
Token ID | 18056 |
Feature activation | +1.35e+01 |
Pos logit contributions | |
.? | +2.061 |
numbered | +1.763 |
verty | +1.755 |
BLE | +1.741 |
ounty | +1.699 |
Neg logit contributions | |
xual | -2.034 |
ctrl | -1.942 |
Salman | -1.935 |
fell | -1.930 |
ente | -1.914 |
Token | Nation |
Token ID | 8741 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
.? | +5.294 |
ANA | +4.075 |
BLE | +3.965 |
ounty | +3.894 |
verty | +3.690 |
Neg logit contributions | |
xual | -13.468 |
Salman | -12.826 |
ctrl | -12.613 |
illin | -12.561 |
fell | -12.550 |
Token | ,[ |
Token ID | 17414 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
.? | +3.249 |
numbered | +2.763 |
BLE | +2.749 |
verty | +2.742 |
ounty | +2.640 |
Neg logit contributions | |
xual | -3.449 |
Salman | -3.317 |
ctrl | -3.280 |
illin | -3.259 |
ente | -3.258 |
Token | 93 |
Token ID | 6052 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ctrl | +4.586 |
fell | +4.576 |
xual | +4.512 |
att | +4.506 |
illin | +4.489 |
Neg logit contributions | |
.? | -3.692 |
verty | -3.158 |
numbered | -3.077 |
BLE | -2.966 |
bleed | -2.947 |
Token | ] |
Token ID | 60 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
xual | +1.515 |
Salman | +1.463 |
fell | +1.459 |
ctrl | +1.455 |
illin | +1.440 |
Neg logit contributions | |
.? | -1.394 |
numbered | -1.183 |
verty | -1.182 |
BLE | -1.161 |
ounty | -1.142 |
Token | Sports |
Token ID | 7092 |
Feature activation | +8.19e+00 |
Pos logit contributions | |
.? | +1.178 |
numbered | +1.005 |
verty | +1.005 |
BLE | +0.993 |
ounty | +0.973 |
Neg logit contributions | |
xual | -1.175 |
Salman | -1.126 |
ctrl | -1.124 |
fell | -1.121 |
illin | -1.111 |
Token | at |
Token ID | 379 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
xual | +2.500 |
Salman | +2.404 |
fell | +2.385 |
att | +2.374 |
ctrl | +2.366 |
Neg logit contributions | |
.? | -4.128 |
verty | -3.677 |
numbered | -3.647 |
BLE | -3.635 |
ounty | -3.580 |
Token | a |
Token ID | 257 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
.? | +1.544 |
numbered | +1.313 |
verty | +1.301 |
BLE | +1.290 |
ounty | +1.276 |
Neg logit contributions | |
xual | -1.516 |
illin | -1.435 |
fell | -1.431 |
Salman | -1.429 |
ctrl | -1.422 |
Token | 90 |
Token ID | 4101 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
.? | +1.365 |
verty | +1.157 |
numbered | +1.146 |
BLE | +1.136 |
ounty | +1.114 |
Neg logit contributions | |
xual | -1.454 |
illin | -1.381 |
ctrl | -1.380 |
fell | -1.379 |
Salman | -1.379 |
Token | F |
Token ID | 376 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
.? | +1.782 |
numbered | +1.476 |
verty | +1.464 |
BLE | +1.456 |
ounty | +1.416 |
Neg logit contributions | |
xual | -2.238 |
illin | -2.139 |
Salman | -2.133 |
ctrl | -2.126 |
fell | -2.121 |
Token | OV |
Token ID | 8874 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
xual | +2.292 |
fell | +2.265 |
ctrl | +2.255 |
Salman | +2.253 |
ente | +2.225 |
Neg logit contributions | |
.? | -1.875 |
verty | -1.600 |
numbered | -1.597 |
BLE | -1.547 |
ounty | -1.531 |
Token | even |
Token ID | 772 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
.? | +4.242 |
numbered | +3.367 |
verty | +3.273 |
bleed | +3.201 |
BLE | +3.175 |
Neg logit contributions | |
xual | -8.331 |
illin | -8.124 |
ctrl | -8.106 |
fell | -8.012 |
Salman | -7.959 |
Token | double |
Token ID | 4274 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
.? | +4.379 |
numbered | +3.096 |
bleed | +2.923 |
BLE | +2.921 |
circle | +2.623 |
Neg logit contributions | |
xual | -14.402 |
illin | -13.992 |
ailable | -13.886 |
olitan | -13.559 |
Salman | -13.556 |
Token | or |
Token ID | 393 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
.? | +5.443 |
numbered | +4.465 |
bleed | +4.235 |
BLE | +4.214 |
ounty | +4.078 |
Neg logit contributions | |
xual | -8.316 |
ailable | -8.038 |
illin | -7.916 |
Salman | -7.910 |
ente | -7.770 |
Token | 4 |
Token ID | 604 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
.? | +6.530 |
numbered | +5.213 |
BLE | +4.898 |
bleed | +4.865 |
repl | +4.683 |
Neg logit contributions | |
xual | -10.859 |
illin | -10.519 |
Salman | -10.244 |
ente | -10.117 |
ailable | -10.071 |
Token | x |
Token ID | 87 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
.? | +5.436 |
BLE | +4.342 |
numbered | +4.293 |
ANA | +3.976 |
verty | +3.847 |
Neg logit contributions | |
xual | -9.329 |
Salman | -8.980 |
illin | -8.978 |
ailable | -8.862 |
Collider | -8.807 |
Token | 1080 |
Token ID | 17729 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
.? | +3.080 |
verty | +2.618 |
numbered | +2.612 |
BLE | +2.586 |
ounty | +2.558 |
Neg logit contributions | |
xual | -3.108 |
Salman | -2.955 |
illin | -2.953 |
ente | -2.946 |
ctrl | -2.937 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
xual | +0.647 |
Salman | +0.625 |
fell | +0.624 |
ctrl | +0.620 |
ente | +0.613 |
Neg logit contributions | |
.? | -0.736 |
numbered | -0.634 |
verty | -0.634 |
BLE | -0.628 |
ounty | -0.617 |
Token | that |
Token ID | 326 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
xual | +2.762 |
Salman | +2.754 |
fell | +2.703 |
ctrl | +2.683 |
ente | +2.647 |
Neg logit contributions | |
.? | -3.602 |
numbered | -3.142 |
verty | -3.139 |
BLE | -3.101 |
ounty | -3.056 |
Token | Merry |
Token ID | 39001 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
.? | +0.497 |
verty | +0.428 |
numbered | +0.427 |
BLE | +0.421 |
ounty | +0.416 |
Neg logit contributions | |
xual | -0.444 |
ctrl | -0.422 |
Salman | -0.422 |
fell | -0.421 |
ente | -0.417 |
Token | and |
Token ID | 290 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
.? | +0.028 |
verty | +0.024 |
numbered | +0.024 |
BLE | +0.024 |
ounty | +0.024 |
Neg logit contributions | |
xual | -0.026 |
Salman | -0.024 |
ctrl | -0.024 |
fell | -0.024 |
illin | -0.024 |
Token | P |
Token ID | 350 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
.? | +2.064 |
verty | +1.758 |
numbered | +1.747 |
BLE | +1.720 |
ounty | +1.696 |
Neg logit contributions | |
xual | -2.101 |
ctrl | -1.987 |
fell | -1.972 |
illin | -1.963 |
Collider | -1.963 |
Token | ipp |
Token ID | 3974 |
Feature activation | +1.34e+01 |
Pos logit contributions | |
.? | +0.427 |
verty | +0.380 |
numbered | +0.379 |
BLE | +0.375 |
ounty | +0.373 |
Neg logit contributions | |
xual | -0.206 |
Salman | -0.192 |
fell | -0.191 |
Collider | -0.190 |
ctrl | -0.190 |
Token | in |
Token ID | 259 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
.? | +6.488 |
numbered | +5.005 |
ounty | +4.699 |
verty | +4.305 |
BLE | +4.301 |
Neg logit contributions | |
xual | -12.310 |
Collider | -12.087 |
ailable | -11.665 |
Salman | -11.381 |
ctrl | -10.944 |
Token | are |
Token ID | 389 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
.? | +1.631 |
numbered | +1.399 |
verty | +1.397 |
BLE | +1.365 |
ounty | +1.358 |
Neg logit contributions | |
xual | -1.571 |
ctrl | -1.494 |
Salman | -1.484 |
ente | -1.475 |
Collider | -1.474 |
Token | safe |
Token ID | 3338 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
.? | +1.184 |
numbered | +1.015 |
verty | +1.011 |
BLE | +0.999 |
ounty | +0.981 |
Neg logit contributions | |
xual | -1.143 |
ctrl | -1.080 |
Salman | -1.077 |
fell | -1.076 |
Collider | -1.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
xual | +1.239 |
Salman | +1.197 |
fell | +1.192 |
ctrl | +1.184 |
illin | +1.170 |
Neg logit contributions | |
.? | -1.587 |
verty | -1.384 |
numbered | -1.384 |
BLE | -1.370 |
ounty | -1.351 |
Token | Together |
Token ID | 17083 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
.? | +2.057 |
numbered | +1.770 |
verty | +1.747 |
BLE | +1.742 |
ANA | +1.707 |
Neg logit contributions | |
xual | -1.898 |
ctrl | -1.769 |
ente | -1.753 |
ailable | -1.751 |
illin | -1.734 |
Token | rim |
Token ID | 3036 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
.? | +2.793 |
verty | +2.351 |
numbered | +2.321 |
BLE | +2.275 |
ounty | +2.248 |
Neg logit contributions | |
xual | -3.399 |
Salman | -3.276 |
ctrl | -3.244 |
Collider | -3.226 |
ente | -3.203 |
Token | . |
Token ID | 13 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
xual | +0.938 |
Salman | +0.899 |
fell | +0.899 |
ctrl | +0.892 |
ente | +0.883 |
Neg logit contributions | |
.? | -1.163 |
verty | -1.010 |
numbered | -1.009 |
BLE | -0.997 |
ounty | -0.983 |
Token | Merry |
Token ID | 39001 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
.? | +3.024 |
numbered | +2.604 |
verty | +2.558 |
BLE | +2.548 |
ANA | +2.497 |
Neg logit contributions | |
xual | -2.951 |
ctrl | -2.750 |
ente | -2.735 |
ailable | -2.730 |
illin | -2.681 |
Token | and |
Token ID | 290 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
.? | +2.048 |
verty | +1.758 |
numbered | +1.745 |
BLE | +1.727 |
ounty | +1.686 |
Neg logit contributions | |
xual | -1.945 |
ctrl | -1.855 |
illin | -1.842 |
ailable | -1.834 |
Collider | -1.833 |
Token | P |
Token ID | 350 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
.? | +2.008 |
verty | +1.733 |
numbered | +1.719 |
BLE | +1.689 |
ounty | +1.671 |
Neg logit contributions | |
xual | -1.980 |
ctrl | -1.880 |
fell | -1.874 |
Salman | -1.864 |
Collider | -1.862 |
Token | ipp |
Token ID | 3974 |
Feature activation | +1.33e+01 |
Pos logit contributions | |
xual | +0.319 |
Salman | +0.300 |
fell | +0.298 |
ctrl | +0.297 |
illin | +0.292 |
Neg logit contributions | |
.? | -0.703 |
verty | -0.628 |
numbered | -0.627 |
BLE | -0.622 |
ounty | -0.615 |
Token | in |
Token ID | 259 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
.? | +6.442 |
numbered | +5.045 |
ounty | +4.732 |
BLE | +4.374 |
verty | +4.336 |
Neg logit contributions | |
xual | -12.153 |
Collider | -11.938 |
ailable | -11.518 |
Salman | -11.262 |
ctrl | -10.802 |
Token | escape |
Token ID | 6654 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
.? | +3.320 |
numbered | +2.820 |
verty | +2.777 |
bleed | +2.748 |
BLE | +2.723 |
Neg logit contributions | |
xual | -3.731 |
ctrl | -3.526 |
Collider | -3.505 |
Salman | -3.492 |
ailable | -3.486 |
Token | into |
Token ID | 656 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
xual | +2.898 |
Salman | +2.895 |
fell | +2.829 |
ctrl | +2.808 |
illin | +2.768 |
Neg logit contributions | |
.? | -3.902 |
verty | -3.449 |
numbered | -3.439 |
BLE | -3.402 |
ounty | -3.354 |
Token | Fang |
Token ID | 24468 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
.? | +1.076 |
verty | +0.928 |
numbered | +0.926 |
BLE | +0.913 |
ounty | +0.903 |
Neg logit contributions | |
xual | -0.965 |
ctrl | -0.917 |
Salman | -0.916 |
fell | -0.914 |
illin | -0.906 |
Token | orn |
Token ID | 1211 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
xual | +1.290 |
fell | +1.255 |
Salman | +1.247 |
ctrl | +1.234 |
ente | +1.228 |
Neg logit contributions | |
.? | -1.554 |
numbered | -1.347 |
verty | -1.345 |
BLE | -1.338 |
ounty | -1.305 |
Token | Rest |
Token ID | 8324 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
.? | +0.351 |
verty | +0.297 |
numbered | +0.297 |
BLE | +0.293 |
ounty | +0.287 |
Neg logit contributions | |
xual | -0.380 |
Salman | -0.366 |
fell | -0.365 |
ctrl | -0.363 |
illin | -0.361 |
Token | art |
Token ID | 433 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
xual | +0.277 |
Salman | +0.265 |
fell | +0.264 |
ctrl | +0.264 |
ente | +0.260 |
Neg logit contributions | |
.? | -0.368 |
numbered | -0.321 |
verty | -0.321 |
BLE | -0.317 |
ounty | -0.313 |
Token | Network |
Token ID | 7311 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
.? | +2.007 |
verty | +1.708 |
numbered | +1.707 |
BLE | +1.699 |
ounty | +1.646 |
Neg logit contributions | |
xual | -1.809 |
fell | -1.731 |
Salman | -1.730 |
illin | -1.719 |
ctrl | -1.713 |
Token | Manager |
Token ID | 9142 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
xual | +0.662 |
Salman | +0.641 |
ctrl | +0.640 |
fell | +0.639 |
Collider | +0.627 |
Neg logit contributions | |
.? | -0.792 |
verty | -0.689 |
numbered | -0.687 |
BLE | -0.679 |
ounty | -0.673 |
Token | at |
Token ID | 379 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
.? | +0.259 |
verty | +0.225 |
numbered | +0.225 |
BLE | +0.222 |
ounty | +0.219 |
Neg logit contributions | |
xual | -0.207 |
Salman | -0.198 |
fell | -0.197 |
ctrl | -0.196 |
illin | -0.194 |
Token | boot |
Token ID | 6297 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
.? | +0.411 |
verty | +0.351 |
numbered | +0.350 |
BLE | +0.345 |
ounty | +0.339 |
Neg logit contributions | |
xual | -0.413 |
Salman | -0.396 |
fell | -0.395 |
ctrl | -0.394 |
illin | -0.392 |
Token | up |
Token ID | 510 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
.? | +8.456 |
verty | +6.575 |
numbered | +6.556 |
ANA | +6.324 |
bleed | +6.322 |
Neg logit contributions | |
xual | -10.179 |
Collider | -9.431 |
fell | -9.420 |
illin | -9.357 |
Salman | -9.267 |
Token |
|
Token ID | 198 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
.? | +3.037 |
numbered | +2.536 |
verty | +2.522 |
BLE | +2.496 |
ounty | +2.445 |
Neg logit contributions | |
xual | -2.871 |
fell | -2.756 |
Salman | -2.739 |
Collider | -2.718 |
illin | -2.711 |
Token |
|
Token ID | 198 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
.? | +2.825 |
numbered | +2.351 |
BLE | +2.333 |
ANA | +2.253 |
ounty | +2.242 |
Neg logit contributions | |
xual | -2.932 |
Collider | -2.684 |
ailable | -2.677 |
illin | -2.659 |
ente | -2.630 |
Token | So |
Token ID | 2396 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
.? | +2.603 |
numbered | +2.205 |
BLE | +2.196 |
verty | +2.191 |
ANA | +2.143 |
Neg logit contributions | |
xual | -2.763 |
Salman | -2.598 |
Collider | -2.579 |
illin | -2.552 |
fell | -2.526 |
Token | your |
Token ID | 534 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
.? | +4.015 |
verty | +3.389 |
numbered | +3.334 |
BLE | +3.333 |
ANA | +3.239 |
Neg logit contributions | |
xual | -3.908 |
fell | -3.710 |
illin | -3.708 |
Salman | -3.702 |
Collider | -3.645 |
Token | of |
Token ID | 286 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
.? | +0.713 |
numbered | +0.614 |
verty | +0.613 |
BLE | +0.606 |
ounty | +0.598 |
Neg logit contributions | |
xual | -0.593 |
Salman | -0.565 |
fell | -0.563 |
ctrl | -0.563 |
illin | -0.558 |
Token | H |
Token ID | 367 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
xual | +2.237 |
Salman | +2.228 |
fell | +2.175 |
ctrl | +2.172 |
Collider | +2.149 |
Neg logit contributions | |
.? | -2.670 |
numbered | -2.314 |
verty | -2.306 |
BLE | -2.288 |
ounty | -2.245 |
Token | . |
Token ID | 13 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
.? | +1.451 |
verty | +1.254 |
numbered | +1.243 |
BLE | +1.230 |
ounty | +1.219 |
Neg logit contributions | |
xual | -1.152 |
Salman | -1.093 |
fell | -1.085 |
ctrl | -1.083 |
Collider | -1.080 |
Token | M |
Token ID | 44 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
.? | +0.923 |
numbered | +0.774 |
verty | +0.771 |
BLE | +0.766 |
ounty | +0.746 |
Neg logit contributions | |
xual | -1.081 |
ctrl | -1.036 |
fell | -1.034 |
Salman | -1.034 |
ente | -1.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
.? | +7.143 |
BLE | +5.371 |
ounty | +5.317 |
ANA | +5.275 |
numbered | +5.196 |
Neg logit contributions | |
xual | -7.837 |
ailable | -7.211 |
Collider | -7.110 |
ctrl | -7.110 |
illin | -7.069 |
Token | S |
Token ID | 50 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
.? | +0.877 |
verty | +0.752 |
numbered | +0.751 |
BLE | +0.743 |
ounty | +0.731 |
Neg logit contributions | |
xual | -0.791 |
fell | -0.753 |
ctrl | -0.752 |
Salman | -0.751 |
illin | -0.743 |
Token | . |
Token ID | 13 |
Feature activation | +6.95e+00 |
Pos logit contributions | |
.? | +9.380 |
ounty | +7.070 |
verty | +6.873 |
BLE | +6.752 |
numbered | +6.670 |
Neg logit contributions | |
xual | -9.560 |
Collider | -9.245 |
fell | -9.211 |
ctrl | -9.175 |
ailable | -8.984 |
Token | Surprise |
Token ID | 47893 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
.? | +5.362 |
numbered | +4.557 |
verty | +4.509 |
BLE | +4.504 |
ounty | +4.492 |
Neg logit contributions | |
xual | -4.675 |
fell | -4.460 |
ctrl | -4.437 |
ailable | -4.335 |
illin | -4.323 |
Token | , |
Token ID | 11 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
.? | +1.470 |
verty | +1.267 |
numbered | +1.266 |
BLE | +1.248 |
ounty | +1.231 |
Neg logit contributions | |
xual | -1.164 |
Salman | -1.111 |
ctrl | -1.110 |
fell | -1.110 |
illin | -1.099 |
Token | somewhere |
Token ID | 7382 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
.? | +0.425 |
verty | +0.366 |
numbered | +0.366 |
BLE | +0.361 |
ounty | +0.356 |
Neg logit contributions | |
xual | -0.382 |
Salman | -0.366 |
fell | -0.365 |
ctrl | -0.365 |
illin | -0.361 |
Token | in |
Token ID | 287 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
.? | +2.168 |
verty | +1.835 |
numbered | +1.826 |
BLE | +1.801 |
ounty | +1.777 |
Neg logit contributions | |
xual | -2.033 |
illin | -1.922 |
fell | -1.913 |
ctrl | -1.912 |
ailable | -1.887 |
Token | Republicans |
Token ID | 4734 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
.? | +4.036 |
verty | +3.440 |
numbered | +3.407 |
BLE | +3.400 |
ounty | +3.388 |
Neg logit contributions | |
xual | -4.020 |
ctrl | -3.806 |
ailable | -3.759 |
illin | -3.751 |
fell | -3.748 |
Token | Sp |
Token ID | 1338 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
.? | +0.056 |
verty | +0.048 |
numbered | +0.048 |
BLE | +0.048 |
ounty | +0.047 |
Neg logit contributions | |
xual | -0.048 |
Salman | -0.046 |
fell | -0.046 |
ctrl | -0.046 |
illin | -0.045 |
Token | aghetti |
Token ID | 35812 |
Feature activation | +7.92e+00 |
Pos logit contributions | |
xual | +1.980 |
Salman | +1.907 |
fell | +1.906 |
illin | +1.897 |
ente | +1.896 |
Neg logit contributions | |
.? | -2.914 |
verty | -2.571 |
numbered | -2.566 |
BLE | -2.545 |
ounty | -2.488 |
Token | Dinner |
Token ID | 34584 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
.? | +6.263 |
numbered | +5.356 |
verty | +5.345 |
ounty | +5.308 |
ANA | +5.283 |
Neg logit contributions | |
xual | -5.040 |
ctrl | -5.028 |
ailable | -4.859 |
fell | -4.735 |
illin | -4.698 |
Token | at |
Token ID | 379 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
xual | +1.338 |
Salman | +1.297 |
fell | +1.282 |
ctrl | +1.267 |
ente | +1.266 |
Neg logit contributions | |
.? | -1.652 |
verty | -1.448 |
numbered | -1.437 |
BLE | -1.428 |
ounty | -1.408 |
Token | Clear |
Token ID | 11459 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
Salman | +2.628 |
xual | +2.573 |
Collider | +2.551 |
fell | +2.545 |
ente | +2.524 |
Neg logit contributions | |
.? | -3.344 |
numbered | -2.922 |
verty | -2.908 |
BLE | -2.880 |
ounty | -2.831 |
Token | Creek |
Token ID | 13509 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
.? | +9.026 |
numbered | +7.570 |
verty | +7.548 |
ANA | +7.489 |
BLE | +7.327 |
Neg logit contributions | |
xual | -9.478 |
ailable | -8.458 |
ctrl | -8.416 |
Collider | -8.253 |
Salman | -8.165 |
Token | Aman |
Token ID | 42614 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
.? | +3.106 |
verty | +2.691 |
numbered | +2.645 |
BLE | +2.642 |
ounty | +2.617 |
Neg logit contributions | |
xual | -2.442 |
ctrl | -2.309 |
fell | -2.284 |
ailable | -2.284 |
illin | -2.275 |
Token | a |
Token ID | 64 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
xual | +0.747 |
Salman | +0.712 |
fell | +0.709 |
ctrl | +0.707 |
ente | +0.699 |
Neg logit contributions | |
.? | -1.196 |
numbered | -1.056 |
verty | -1.055 |
BLE | -1.046 |
ounty | -1.030 |
Token | High |
Token ID | 3334 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
.? | +0.817 |
verty | +0.710 |
numbered | +0.706 |
BLE | +0.700 |
ounty | +0.692 |
Neg logit contributions | |
xual | -0.628 |
Salman | -0.597 |
ctrl | -0.597 |
fell | -0.595 |
illin | -0.588 |
Token | School |
Token ID | 3961 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
.? | +2.853 |
verty | +2.455 |
numbered | +2.447 |
ounty | +2.393 |
BLE | +2.392 |
Neg logit contributions | |
xual | -2.520 |
ctrl | -2.411 |
ailable | -2.383 |
Salman | -2.375 |
illin | -2.350 |
Token | with |
Token ID | 4480 |
Feature activation | -4.97e-01 |
Pos logit contributions | |
.? | +1.486 |
numbered | +1.282 |
verty | +1.268 |
BLE | +1.261 |
ounty | +1.232 |
Neg logit contributions | |
xual | -1.411 |
Salman | -1.332 |
ctrl | -1.328 |
Collider | -1.326 |
fell | -1.326 |
Token | the |
Token ID | 262 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
xual | +0.339 |
Salman | +0.327 |
fell | +0.325 |
ctrl | +0.323 |
ente | +0.320 |
Neg logit contributions | |
.? | -0.386 |
verty | -0.334 |
numbered | -0.332 |
BLE | -0.330 |
ounty | -0.325 |
Token | judgment |
Token ID | 8492 |
Feature activation | +5.35e+00 |
Pos logit contributions | |
.? | +0.605 |
verty | +0.525 |
numbered | +0.524 |
BLE | +0.517 |
ounty | +0.510 |
Neg logit contributions | |
xual | -0.500 |
Salman | -0.478 |
fell | -0.476 |
ctrl | -0.475 |
illin | -0.470 |
Token | of |
Token ID | 286 |
Feature activation | +5.88e+00 |
Pos logit contributions | |
.? | +3.930 |
numbered | +3.343 |
verty | +3.277 |
BLE | +3.256 |
ounty | +3.176 |
Neg logit contributions | |
xual | -3.891 |
ctrl | -3.714 |
illin | -3.704 |
Collider | -3.665 |
Salman | -3.655 |
Token | God |
Token ID | 1793 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
.? | +4.083 |
numbered | +3.444 |
verty | +3.417 |
BLE | +3.404 |
ounty | +3.297 |
Neg logit contributions | |
xual | -4.461 |
illin | -4.197 |
ctrl | -4.185 |
Collider | -4.169 |
fell | -4.167 |
Token | from |
Token ID | 422 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
.? | +2.483 |
verty | +2.140 |
numbered | +2.131 |
BLE | +2.102 |
ounty | +2.066 |
Neg logit contributions | |
xual | -1.950 |
ctrl | -1.854 |
illin | -1.839 |
Salman | -1.826 |
Collider | -1.824 |
Token | above |
Token ID | 2029 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
.? | +5.333 |
antiquity | +4.014 |
numbered | +3.840 |
BLE | +3.838 |
verty | +3.825 |
Neg logit contributions | |
xual | -12.876 |
illin | -12.386 |
Collider | -12.156 |
ctrl | -12.066 |
ente | -12.042 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
.? | +1.101 |
numbered | +0.942 |
verty | +0.940 |
BLE | +0.928 |
ounty | +0.915 |
Neg logit contributions | |
xual | -0.992 |
Salman | -0.948 |
fell | -0.947 |
ctrl | -0.947 |
illin | -0.940 |
Token | seven |
Token ID | 3598 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
xual | +2.029 |
Salman | +1.968 |
fell | +1.952 |
ctrl | +1.935 |
Collider | +1.909 |
Neg logit contributions | |
.? | -2.213 |
verty | -1.930 |
numbered | -1.915 |
BLE | -1.889 |
ounty | -1.864 |
Token | heavens |
Token ID | 27636 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
xual | +0.868 |
Salman | +0.833 |
fell | +0.827 |
ctrl | +0.819 |
ente | +0.803 |
Neg logit contributions | |
.? | -1.737 |
verty | -1.563 |
numbered | -1.557 |
BLE | -1.545 |
ounty | -1.528 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
.? | +2.532 |
numbered | +2.127 |
verty | +2.121 |
BLE | +2.088 |
ounty | +2.060 |
Neg logit contributions | |
xual | -2.363 |
ctrl | -2.251 |
illin | -2.247 |
fell | -2.230 |
Salman | -2.229 |
Token | V |
Token ID | 569 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
.? | +4.657 |
BLE | +3.955 |
verty | +3.929 |
numbered | +3.901 |
ounty | +3.832 |
Neg logit contributions | |
xual | -4.168 |
illin | -3.907 |
ctrl | -3.866 |
Salman | -3.843 |
ailable | -3.836 |
Token | AS |
Token ID | 1921 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
xual | +1.761 |
Salman | +1.702 |
fell | +1.701 |
ctrl | +1.695 |
ente | +1.692 |
Neg logit contributions | |
.? | -2.137 |
numbered | -1.863 |
verty | -1.862 |
BLE | -1.831 |
ounty | -1.799 |
Token | graduates |
Token ID | 19087 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
.? | +0.910 |
verty | +0.761 |
numbered | +0.759 |
BLE | +0.754 |
ounty | +0.736 |
Neg logit contributions | |
xual | -1.091 |
Salman | -1.052 |
ctrl | -1.047 |
fell | -1.045 |
illin | -1.035 |
Token | right |
Token ID | 826 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
.? | +0.584 |
verty | +0.506 |
numbered | +0.505 |
BLE | +0.499 |
ounty | +0.492 |
Neg logit contributions | |
xual | -0.472 |
Salman | -0.452 |
fell | -0.450 |
ctrl | -0.450 |
illin | -0.444 |
Token | out |
Token ID | 503 |
Feature activation | +5.37e+00 |
Pos logit contributions | |
.? | +3.234 |
numbered | +2.666 |
verty | +2.656 |
ounty | +2.639 |
BLE | +2.626 |
Neg logit contributions | |
xual | -3.449 |
illin | -3.273 |
ctrl | -3.270 |
fell | -3.247 |
Collider | -3.243 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
.? | +3.909 |
numbered | +3.301 |
verty | +3.246 |
ounty | +3.234 |
BLE | +3.174 |
Neg logit contributions | |
xual | -3.974 |
ctrl | -3.748 |
fell | -3.744 |
illin | -3.736 |
Salman | -3.734 |
Token | school |
Token ID | 1524 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
.? | +7.983 |
verty | +6.867 |
BLE | +6.790 |
antiquity | +6.711 |
ounty | +6.615 |
Neg logit contributions | |
xual | -10.389 |
ctrl | -9.539 |
ailable | -9.392 |
illin | -9.289 |
Salman | -9.149 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
.? | +2.189 |
verty | +1.868 |
numbered | +1.861 |
BLE | +1.843 |
ounty | +1.821 |
Neg logit contributions | |
xual | -1.822 |
Salman | -1.746 |
ctrl | -1.740 |
fell | -1.731 |
illin | -1.718 |
Token | This |
Token ID | 770 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
.? | +0.333 |
verty | +0.286 |
numbered | +0.286 |
BLE | +0.282 |
ounty | +0.278 |
Neg logit contributions | |
xual | -0.307 |
Salman | -0.295 |
fell | -0.294 |
ctrl | -0.293 |
illin | -0.290 |
Token | is |
Token ID | 318 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
xual | +1.037 |
Salman | +1.000 |
fell | +0.994 |
ctrl | +0.990 |
ente | +0.984 |
Neg logit contributions | |
.? | -1.188 |
numbered | -1.031 |
verty | -1.030 |
BLE | -1.017 |
ounty | -1.003 |
Token | why |
Token ID | 1521 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
xual | +1.886 |
Salman | +1.831 |
fell | +1.815 |
ctrl | +1.797 |
ente | +1.787 |
Neg logit contributions | |
.? | -2.237 |
numbered | -1.951 |
verty | -1.949 |
BLE | -1.910 |
ounty | -1.895 |
Token | in |
Token ID | 287 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
.? | +1.461 |
numbered | +1.251 |
verty | +1.249 |
BLE | +1.235 |
ounty | +1.216 |
Neg logit contributions | |
xual | -1.248 |
ctrl | -1.192 |
fell | -1.186 |
Salman | -1.181 |
illin | -1.178 |
Token | Madrid |
Token ID | 14708 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
.? | +0.155 |
numbered | +0.134 |
verty | +0.134 |
BLE | +0.132 |
ounty | +0.130 |
Neg logit contributions | |
xual | -0.125 |
fell | -0.118 |
ctrl | -0.118 |
Salman | -0.118 |
illin | -0.117 |
Token | . |
Token ID | 13 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
.? | +0.462 |
verty | +0.398 |
numbered | +0.397 |
BLE | +0.393 |
ounty | +0.387 |
Neg logit contributions | |
xual | -0.388 |
Salman | -0.371 |
ctrl | -0.371 |
fell | -0.370 |
illin | -0.366 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
.? | +0.775 |
numbered | +0.675 |
verty | +0.671 |
BLE | +0.665 |
ounty | +0.654 |
Neg logit contributions | |
xual | -0.650 |
ctrl | -0.618 |
fell | -0.614 |
Salman | -0.613 |
illin | -0.609 |
Token |
|
Token ID | 198 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
xual | +1.424 |
Salman | +1.389 |
fell | +1.385 |
ctrl | +1.374 |
ente | +1.354 |
Neg logit contributions | |
.? | -1.960 |
verty | -1.733 |
numbered | -1.716 |
BLE | -1.696 |
ounty | -1.680 |
Token | Ind |
Token ID | 5497 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
.? | +0.361 |
numbered | +0.311 |
verty | +0.310 |
BLE | +0.309 |
ounty | +0.302 |
Neg logit contributions | |
xual | -0.330 |
Salman | -0.313 |
ctrl | -0.311 |
fell | -0.310 |
illin | -0.309 |
Token | ependence |
Token ID | 15091 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
.? | +9.081 |
numbered | +7.751 |
ANA | +7.467 |
verty | +7.318 |
ounty | +7.147 |
Neg logit contributions | |
xual | -8.862 |
Collider | -8.472 |
illin | -8.296 |
Salman | -8.177 |
ctrl | -8.112 |
Token | supporters |
Token ID | 5941 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
.? | +5.171 |
numbered | +4.302 |
verty | +4.277 |
BLE | +4.229 |
bleed | +4.155 |
Neg logit contributions | |
xual | -5.283 |
ctrl | -5.091 |
illin | -5.034 |
ailable | -4.987 |
Salman | -4.981 |
Token | , |
Token ID | 11 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
.? | +1.530 |
numbered | +1.323 |
verty | +1.312 |
BLE | +1.299 |
ounty | +1.270 |
Neg logit contributions | |
xual | -1.462 |
ctrl | -1.387 |
fell | -1.384 |
Salman | -1.379 |
ente | -1.370 |
Token | many |
Token ID | 867 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
.? | +3.145 |
numbered | +2.700 |
verty | +2.688 |
BLE | +2.630 |
ounty | +2.599 |
Neg logit contributions | |
xual | -3.222 |
ctrl | -3.081 |
illin | -3.078 |
fell | -3.055 |
ailable | -3.042 |
Token | wearing |
Token ID | 5762 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
.? | +0.431 |
numbered | +0.370 |
verty | +0.369 |
BLE | +0.365 |
ounty | +0.358 |
Neg logit contributions | |
xual | -0.422 |
fell | -0.405 |
ctrl | -0.404 |
Salman | -0.404 |
illin | -0.400 |
Token | case |
Token ID | 1339 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
.? | +0.926 |
verty | +0.775 |
numbered | +0.769 |
BLE | +0.758 |
ounty | +0.745 |
Neg logit contributions | |
xual | -1.173 |
ctrl | -1.138 |
Salman | -1.132 |
fell | -1.126 |
illin | -1.125 |
Token | is |
Token ID | 318 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
.? | +3.100 |
numbered | +2.649 |
verty | +2.636 |
BLE | +2.595 |
ounty | +2.562 |
Neg logit contributions | |
xual | -2.708 |
ctrl | -2.626 |
illin | -2.580 |
ente | -2.564 |
Salman | -2.555 |
Token | requesting |
Token ID | 20623 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
.? | +0.522 |
verty | +0.442 |
numbered | +0.441 |
BLE | +0.436 |
ounty | +0.427 |
Neg logit contributions | |
xual | -0.561 |
fell | -0.536 |
ctrl | -0.535 |
Salman | -0.534 |
illin | -0.531 |
Token | three |
Token ID | 1115 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
.? | +1.383 |
verty | +1.177 |
numbered | +1.171 |
BLE | +1.168 |
ounty | +1.148 |
Neg logit contributions | |
xual | -1.284 |
fell | -1.231 |
ctrl | -1.229 |
illin | -1.212 |
ente | -1.209 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
xual | +1.944 |
Salman | +1.894 |
fell | +1.870 |
ctrl | +1.859 |
illin | +1.843 |
Neg logit contributions | |
.? | -1.905 |
numbered | -1.636 |
verty | -1.634 |
BLE | -1.616 |
ounty | -1.584 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e+01 |
Pos logit contributions | |
.? | +1.128 |
verty | +0.966 |
numbered | +0.965 |
BLE | +0.951 |
ounty | +0.943 |
Neg logit contributions | |
xual | -1.069 |
ctrl | -1.021 |
fell | -1.018 |
Salman | -1.016 |
illin | -1.009 |
Token | half |
Token ID | 2063 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
.? | +4.327 |
bleed | +2.947 |
verty | +2.742 |
numbered | +2.596 |
ounty | +2.569 |
Neg logit contributions | |
xual | -13.569 |
Collider | -13.154 |
illin | -13.039 |
ailable | -12.923 |
ctrl | -12.835 |
Token | year |
Token ID | 614 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
xual | +2.344 |
Salman | +2.283 |
fell | +2.262 |
ctrl | +2.242 |
illin | +2.234 |
Neg logit contributions | |
.? | -2.173 |
verty | -1.859 |
numbered | -1.858 |
BLE | -1.840 |
ounty | -1.790 |
Token | sentence |
Token ID | 6827 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
xual | +2.079 |
Salman | +2.006 |
fell | +1.983 |
ctrl | +1.969 |
illin | +1.967 |
Neg logit contributions | |
.? | -2.445 |
numbered | -2.129 |
verty | -2.127 |
BLE | -2.103 |
ounty | -2.060 |
Token | for |
Token ID | 329 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
xual | +1.895 |
Salman | +1.831 |
fell | +1.816 |
ente | +1.788 |
ctrl | +1.788 |
Neg logit contributions | |
.? | -2.523 |
verty | -2.229 |
numbered | -2.224 |
BLE | -2.204 |
ounty | -2.172 |
Token | the |
Token ID | 262 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
.? | +0.816 |
verty | +0.701 |
numbered | +0.697 |
BLE | +0.689 |
ounty | +0.678 |
Neg logit contributions | |
xual | -0.753 |
ctrl | -0.719 |
fell | -0.718 |
Salman | -0.712 |
illin | -0.711 |
Token | : |
Token ID | 25 |
Feature activation | -8.11e+00 |
Pos logit contributions | |
xual | +1.694 |
fell | +1.683 |
Salman | +1.675 |
ctrl | +1.662 |
ente | +1.601 |
Neg logit contributions | |
.? | -4.087 |
verty | -3.758 |
numbered | -3.686 |
BLE | -3.658 |
ounty | -3.635 |
Token | 48 |
Token ID | 2780 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
xual | +3.484 |
fell | +3.377 |
att | +3.349 |
ctrl | +3.323 |
ente | +3.260 |
Neg logit contributions | |
.? | -7.988 |
verty | -7.320 |
numbered | -7.097 |
ANA | -7.082 |
BLE | -7.057 |
Token | ] |
Token ID | 60 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
.? | +1.964 |
numbered | +1.564 |
BLE | +1.540 |
ANA | +1.483 |
ounty | +1.471 |
Neg logit contributions | |
xual | -3.065 |
Collider | -2.877 |
ailable | -2.869 |
illin | -2.865 |
Salman | -2.846 |
Token | < |
Token ID | 1279 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
.? | +0.822 |
verty | +0.698 |
numbered | +0.697 |
BLE | +0.695 |
ounty | +0.676 |
Neg logit contributions | |
xual | -0.831 |
Salman | -0.792 |
fell | -0.792 |
ctrl | -0.791 |
illin | -0.786 |
Token | min |
Token ID | 1084 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
xual | +2.603 |
fell | +2.510 |
ctrl | +2.498 |
Salman | +2.473 |
illin | +2.462 |
Neg logit contributions | |
.? | -3.334 |
verty | -2.891 |
numbered | -2.868 |
BLE | -2.850 |
ounty | -2.811 |
Token | ion |
Token ID | 295 |
Feature activation | -1.67e+01 |
Pos logit contributions | |
xual | +1.832 |
Salman | +1.766 |
fell | +1.763 |
ctrl | +1.760 |
ente | +1.748 |
Neg logit contributions | |
.? | -1.560 |
verty | -1.319 |
numbered | -1.307 |
BLE | -1.296 |
ounty | -1.262 |
Token | 13 |
Token ID | 1485 |
Feature activation | -4.72e-01 |
Pos logit contributions | |
fell | +5.581 |
att | +5.090 |
kr | +5.019 |
ctrl | +4.983 |
ente | +4.827 |
Neg logit contributions | |
.? | -16.831 |
verty | -16.491 |
�� | -15.987 |
BLE | -15.387 |
bleed | -15.349 |
Token | 37 |
Token ID | 2718 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
xual | +0.333 |
Salman | +0.319 |
ctrl | +0.318 |
fell | +0.318 |
ente | +0.314 |
Neg logit contributions | |
.? | -0.358 |
numbered | -0.307 |
verty | -0.307 |
BLE | -0.304 |
ounty | -0.298 |
Token | > |
Token ID | 29 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
.? | +0.084 |
numbered | +0.070 |
verty | +0.070 |
BLE | +0.070 |
ounty | +0.068 |
Neg logit contributions | |
xual | -0.096 |
Salman | -0.092 |
ctrl | -0.091 |
fell | -0.091 |
Collider | -0.091 |
Token | le |
Token ID | 443 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
xual | +2.035 |
Salman | +1.973 |
fell | +1.939 |
ctrl | +1.930 |
illin | +1.921 |
Neg logit contributions | |
.? | -2.363 |
numbered | -2.074 |
verty | -2.064 |
BLE | -2.029 |
ounty | -2.010 |
Token | l |
Token ID | 75 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
xual | +3.556 |
fell | +3.362 |
Salman | +3.323 |
illin | +3.308 |
ctrl | +3.280 |
Neg logit contributions | |
.? | -4.529 |
verty | -4.008 |
numbered | -3.994 |
BLE | -3.916 |
ounty | -3.850 |
Token | : |
Token ID | 25 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
xual | +0.751 |
Salman | +0.711 |
fell | +0.707 |
ctrl | +0.704 |
ente | +0.692 |
Neg logit contributions | |
.? | -1.521 |
verty | -1.357 |
numbered | -1.354 |
BLE | -1.342 |
ounty | -1.327 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
xual | +2.433 |
fell | +2.275 |
ctrl | +2.273 |
Salman | +2.271 |
ente | +2.238 |
Neg logit contributions | |
.? | -4.085 |
verty | -3.641 |
numbered | -3.610 |
BLE | -3.574 |
ounty | -3.523 |
Token | ] |
Token ID | 60 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
.? | +1.854 |
numbered | +1.473 |
BLE | +1.457 |
ANA | +1.407 |
ounty | +1.399 |
Neg logit contributions | |
xual | -2.847 |
Collider | -2.670 |
ailable | -2.668 |
illin | -2.656 |
Salman | -2.650 |
Token | < |
Token ID | 1279 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
.? | +0.100 |
verty | +0.086 |
numbered | +0.085 |
BLE | +0.085 |
ounty | +0.083 |
Neg logit contributions | |
xual | -0.095 |
Salman | -0.091 |
fell | -0.091 |
ctrl | -0.091 |
illin | -0.090 |
Token | min |
Token ID | 1084 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
xual | +1.847 |
fell | +1.774 |
ctrl | +1.770 |
Salman | +1.759 |
illin | +1.744 |
Neg logit contributions | |
.? | -2.357 |
verty | -2.047 |
numbered | -2.036 |
BLE | -2.017 |
ounty | -1.992 |
Token | ion |
Token ID | 295 |
Feature activation | -1.61e+01 |
Pos logit contributions | |
xual | +1.077 |
Salman | +1.040 |
fell | +1.036 |
ctrl | +1.035 |
ente | +1.025 |
Neg logit contributions | |
.? | -0.896 |
verty | -0.752 |
numbered | -0.750 |
BLE | -0.740 |
ounty | -0.725 |
Token | 13 |
Token ID | 1485 |
Feature activation | -8.79e-01 |
Pos logit contributions | |
fell | +5.884 |
ente | +5.520 |
ctrl | +5.473 |
kr | +5.427 |
xual | +5.423 |
Neg logit contributions | |
.? | -15.801 |
verty | -14.944 |
BLE | -14.521 |
UGE | -14.204 |
numbered | -14.126 |
Token | 37 |
Token ID | 2718 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
xual | +0.611 |
Salman | +0.588 |
fell | +0.586 |
ctrl | +0.584 |
illin | +0.578 |
Neg logit contributions | |
.? | -0.673 |
verty | -0.580 |
numbered | -0.579 |
BLE | -0.571 |
ounty | -0.563 |
Token | > |
Token ID | 29 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
xual | +0.907 |
Salman | +0.875 |
fell | +0.871 |
ctrl | +0.869 |
illin | +0.861 |
Neg logit contributions | |
.? | -0.842 |
verty | -0.713 |
numbered | -0.713 |
BLE | -0.704 |
ounty | -0.692 |
Token | lol |
Token ID | 19462 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
xual | +1.507 |
Salman | +1.457 |
fell | +1.441 |
ctrl | +1.434 |
illin | +1.424 |
Neg logit contributions | |
.? | -1.705 |
numbered | -1.485 |
verty | -1.481 |
BLE | -1.457 |
ounty | -1.441 |
Token | m |
Token ID | 285 |
Feature activation | -7.09e-01 |
Pos logit contributions | |
xual | +0.035 |
Salman | +0.034 |
fell | +0.034 |
ctrl | +0.034 |
illin | +0.033 |
Neg logit contributions | |
.? | -0.042 |
verty | -0.036 |
numbered | -0.036 |
BLE | -0.036 |
ounty | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
xual | +0.407 |
Salman | +0.388 |
fell | +0.386 |
ctrl | +0.385 |
ente | +0.380 |
Neg logit contributions | |
.? | -0.633 |
verty | -0.557 |
numbered | -0.557 |
BLE | -0.551 |
ounty | -0.544 |
Token | we |
Token ID | 356 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
xual | +0.892 |
Salman | +0.861 |
fell | +0.856 |
ctrl | +0.853 |
ente | +0.844 |
Neg logit contributions | |
.? | -1.021 |
verty | -0.882 |
numbered | -0.880 |
BLE | -0.870 |
ounty | -0.858 |
Token | wanted |
Token ID | 2227 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
.? | +0.230 |
verty | +0.198 |
numbered | +0.198 |
BLE | +0.196 |
ounty | +0.193 |
Neg logit contributions | |
xual | -0.202 |
Salman | -0.193 |
fell | -0.192 |
ctrl | -0.192 |
illin | -0.190 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
.? | +4.082 |
BLE | +3.489 |
verty | +3.472 |
numbered | +3.470 |
ounty | +3.418 |
Neg logit contributions | |
xual | -4.034 |
Salman | -3.812 |
ctrl | -3.792 |
fell | -3.787 |
illin | -3.754 |
Token | go |
Token ID | 467 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
.? | +0.749 |
numbered | +0.637 |
verty | +0.636 |
BLE | +0.631 |
ounty | +0.620 |
Neg logit contributions | |
xual | -0.731 |
Salman | -0.702 |
fell | -0.698 |
ctrl | -0.697 |
illin | -0.692 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
.? | +2.474 |
numbered | +2.118 |
verty | +2.114 |
BLE | +2.114 |
ounty | +2.048 |
Neg logit contributions | |
xual | -2.275 |
fell | -2.173 |
Salman | -2.168 |
ctrl | -2.156 |
illin | -2.143 |
Token | - |
Token ID | 12 |
Feature activation | -5.76e+00 |
Pos logit contributions | |
att | +9.499 |
ctrl | +9.053 |
xual | +8.930 |
paced | +8.915 |
fell | +8.803 |
Neg logit contributions | |
.? | -11.276 |
BLE | -10.000 |
verty | -9.965 |
ounty | -9.924 |
ANA | -9.712 |
Token | clock |
Token ID | 15750 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
xual | +2.966 |
ctrl | +2.942 |
att | +2.911 |
fell | +2.905 |
Salman | +2.809 |
Neg logit contributions | |
.? | -5.256 |
verty | -4.658 |
BLE | -4.589 |
ounty | -4.578 |
numbered | -4.546 |
Token | wise |
Token ID | 3083 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
xual | +1.141 |
Salman | +1.082 |
ctrl | +1.082 |
fell | +1.068 |
ente | +1.044 |
Neg logit contributions | |
.? | -3.685 |
verty | -3.329 |
BLE | -3.316 |
numbered | -3.300 |
ounty | -3.280 |
Token | and |
Token ID | 290 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
xual | +1.248 |
Salman | +1.200 |
fell | +1.196 |
ctrl | +1.193 |
ente | +1.173 |
Neg logit contributions | |
.? | -1.558 |
verty | -1.363 |
numbered | -1.357 |
BLE | -1.344 |
ounty | -1.331 |
Token | we |
Token ID | 356 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
.? | +0.598 |
verty | +0.512 |
numbered | +0.512 |
BLE | +0.506 |
ounty | +0.497 |
Neg logit contributions | |
xual | -0.568 |
Salman | -0.542 |
ctrl | -0.541 |
fell | -0.540 |
illin | -0.536 |
Token | slow |
Token ID | 3105 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
xual | +0.413 |
Salman | +0.395 |
fell | +0.393 |
ctrl | +0.392 |
ente | +0.388 |
Neg logit contributions | |
.? | -0.579 |
verty | -0.507 |
numbered | -0.506 |
BLE | -0.501 |
ounty | -0.494 |
Token | decline |
Token ID | 7794 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
.? | +1.646 |
numbered | +1.468 |
verty | +1.468 |
BLE | +1.456 |
ounty | +1.436 |
Neg logit contributions | |
xual | -0.824 |
Salman | -0.772 |
ctrl | -0.762 |
fell | -0.758 |
illin | -0.751 |
Token | since |
Token ID | 1201 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
.? | +2.465 |
numbered | +2.077 |
verty | +2.072 |
BLE | +2.050 |
ounty | +2.000 |
Neg logit contributions | |
xual | -2.250 |
ctrl | -2.154 |
Salman | -2.151 |
Collider | -2.151 |
fell | -2.146 |
Token | organized |
Token ID | 8389 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
.? | +2.826 |
verty | +2.412 |
numbered | +2.400 |
BLE | +2.361 |
ounty | +2.341 |
Neg logit contributions | |
xual | -2.576 |
ctrl | -2.456 |
illin | -2.454 |
fell | -2.438 |
Collider | -2.426 |
Token | crime |
Token ID | 4065 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
.? | +2.028 |
verty | +1.599 |
numbered | +1.588 |
BLE | +1.581 |
ounty | +1.564 |
Neg logit contributions | |
xual | -3.263 |
ctrl | -3.158 |
Salman | -3.147 |
fell | -3.145 |
illin | -3.143 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
xual | +1.554 |
fell | +1.523 |
Salman | +1.521 |
ctrl | +1.502 |
ente | +1.486 |
Neg logit contributions | |
.? | -1.618 |
verty | -1.390 |
numbered | -1.380 |
BLE | -1.368 |
ounty | -1.346 |
Token | measures |
Token ID | 47336 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
att | +9.374 |
fell | +8.926 |
ente | +8.498 |
xual | +8.479 |
Salman | +8.341 |
Neg logit contributions | |
.? | -12.478 |
verty | -11.237 |
BLE | -10.806 |
ANA | -10.612 |
ounty | -10.541 |
Token | were |
Token ID | 547 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
xual | +3.583 |
Salman | +3.507 |
fell | +3.503 |
ctrl | +3.421 |
ente | +3.411 |
Neg logit contributions | |
.? | -3.837 |
verty | -3.365 |
BLE | -3.327 |
numbered | -3.325 |
ANA | -3.278 |
Token | enacted |
Token ID | 17814 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
.? | +0.082 |
numbered | +0.070 |
verty | +0.070 |
BLE | +0.069 |
ounty | +0.068 |
Neg logit contributions | |
xual | -0.083 |
Salman | -0.079 |
fell | -0.079 |
ctrl | -0.079 |
illin | -0.078 |
Token | in |
Token ID | 287 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
xual | +0.333 |
Salman | +0.320 |
fell | +0.318 |
ctrl | +0.318 |
illin | +0.314 |
Neg logit contributions | |
.? | -0.403 |
verty | -0.349 |
numbered | -0.349 |
BLE | -0.345 |
ounty | -0.340 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
.? | +0.625 |
verty | +0.539 |
numbered | +0.538 |
BLE | +0.532 |
ounty | +0.524 |
Neg logit contributions | |
xual | -0.531 |
Salman | -0.506 |
fell | -0.506 |
ctrl | -0.505 |
illin | -0.501 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Salman | +2.825 |
xual | +2.816 |
fell | +2.771 |
Collider | +2.733 |
ente | +2.698 |
Neg logit contributions | |
.? | -4.243 |
verty | -3.822 |
numbered | -3.753 |
BLE | -3.705 |
ounty | -3.657 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
xual | +1.154 |
Salman | +1.122 |
fell | +1.118 |
ctrl | +1.110 |
ente | +1.094 |
Neg logit contributions | |
.? | -1.572 |
verty | -1.389 |
numbered | -1.376 |
BLE | -1.359 |
ounty | -1.346 |
Token | As |
Token ID | 1722 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
xual | +1.066 |
fell | +1.038 |
Salman | +1.038 |
ctrl | +1.031 |
ente | +1.019 |
Neg logit contributions | |
.? | -1.219 |
verty | -1.062 |
numbered | -1.054 |
BLE | -1.037 |
ounty | -1.027 |
Token | lan |
Token ID | 9620 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
xual | +1.689 |
Salman | +1.660 |
fell | +1.641 |
ctrl | +1.624 |
illin | +1.624 |
Neg logit contributions | |
.? | -1.595 |
verty | -1.357 |
numbered | -1.357 |
BLE | -1.347 |
ounty | -1.313 |
Token | came |
Token ID | 1625 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
xual | +1.327 |
Salman | +1.290 |
fell | +1.273 |
ctrl | +1.259 |
ente | +1.253 |
Neg logit contributions | |
.? | -1.667 |
numbered | -1.453 |
verty | -1.450 |
BLE | -1.442 |
ounty | -1.419 |
Token | under |
Token ID | 739 |
Feature activation | -1.55e+01 |
Pos logit contributions | |
xual | +1.074 |
Salman | +1.032 |
fell | +1.025 |
ctrl | +1.022 |
ente | +1.011 |
Neg logit contributions | |
.? | -1.413 |
verty | -1.233 |
numbered | -1.232 |
BLE | -1.217 |
ounty | -1.201 |
Token | fire |
Token ID | 2046 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Salman | +8.306 |
att | +7.923 |
xual | +7.864 |
Collider | +7.734 |
fell | +7.644 |
Neg logit contributions | |
.? | -12.474 |
verty | -11.198 |
BLE | -11.146 |
numbered | -11.091 |
ounty | -10.979 |
Token | earlier |
Token ID | 2961 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
xual | +2.531 |
Salman | +2.473 |
fell | +2.417 |
ctrl | +2.382 |
illin | +2.374 |
Neg logit contributions | |
.? | -3.141 |
verty | -2.771 |
numbered | -2.727 |
BLE | -2.719 |
ounty | -2.708 |
Token | this |
Token ID | 428 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
.? | +2.513 |
numbered | +2.093 |
verty | +2.070 |
BLE | +2.063 |
ounty | +2.024 |
Neg logit contributions | |
xual | -2.806 |
ctrl | -2.715 |
illin | -2.670 |
fell | -2.666 |
ailable | -2.663 |
Token | month |
Token ID | 1227 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
xual | +1.315 |
Salman | +1.273 |
fell | +1.269 |
ctrl | +1.253 |
ente | +1.247 |
Neg logit contributions | |
.? | -1.727 |
verty | -1.511 |
numbered | -1.504 |
BLE | -1.494 |
ounty | -1.471 |
Token | after |
Token ID | 706 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
.? | +0.051 |
numbered | +0.044 |
verty | +0.044 |
BLE | +0.044 |
ounty | +0.043 |
Neg logit contributions | |
xual | -0.046 |
Salman | -0.044 |
ctrl | -0.044 |
fell | -0.044 |
illin | -0.044 |
Token | Proceedings |
Token ID | 30641 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
xual | +2.625 |
Salman | +2.591 |
fell | +2.545 |
Collider | +2.529 |
ente | +2.523 |
Neg logit contributions | |
.? | -3.105 |
verty | -2.695 |
numbered | -2.685 |
BLE | -2.684 |
ounty | -2.618 |
Token | of |
Token ID | 286 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
xual | +2.567 |
Salman | +2.513 |
fell | +2.488 |
ctrl | +2.447 |
Collider | +2.444 |
Neg logit contributions | |
.? | -3.454 |
verty | -3.120 |
numbered | -3.054 |
BLE | -3.016 |
ounty | -3.006 |
Token | the |
Token ID | 262 |
Feature activation | -9.08e+00 |
Pos logit contributions | |
Salman | +4.081 |
xual | +4.066 |
fell | +4.017 |
Collider | +4.004 |
ente | +3.944 |
Neg logit contributions | |
.? | -5.935 |
verty | -5.283 |
numbered | -5.147 |
BLE | -5.147 |
ounty | -5.133 |
Token | National |
Token ID | 2351 |
Feature activation | -9.97e+00 |
Pos logit contributions | |
Salman | +3.652 |
Collider | +3.477 |
fell | +3.428 |
illin | +3.401 |
att | +3.399 |
Neg logit contributions | |
.? | -9.113 |
verty | -8.440 |
BLE | -8.245 |
numbered | -8.209 |
ounty | -8.204 |
Token | Academy |
Token ID | 8581 |
Feature activation | -7.87e+00 |
Pos logit contributions | |
Salman | +1.625 |
Collider | +1.550 |
att | +1.519 |
fell | +1.348 |
ente | +1.278 |
Neg logit contributions | |
.? | -12.097 |
verty | -11.751 |
numbered | -11.371 |
ANA | -11.191 |
ounty | -11.057 |
Token | of |
Token ID | 286 |
Feature activation | -1.53e+01 |
Pos logit contributions | |
xual | +4.191 |
Salman | +4.191 |
fell | +4.120 |
ente | +4.095 |
Collider | +4.057 |
Neg logit contributions | |
.? | -6.617 |
verty | -6.222 |
numbered | -6.011 |
BLE | -5.866 |
ounty | -5.830 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
kr | +5.789 |
ente | +5.712 |
Salman | +5.575 |
att | +5.467 |
ries | +5.389 |
Neg logit contributions | |
.? | -14.066 |
quickShipAvailable | -13.462 |
numbered | -13.104 |
verty | -13.036 |
eternity | -12.519 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
xual | +4.715 |
Salman | +4.590 |
ctrl | +4.524 |
att | +4.512 |
illin | +4.423 |
Neg logit contributions | |
.? | -7.391 |
verty | -6.926 |
numbered | -6.724 |
ounty | -6.555 |
BLE | -6.510 |
Token |
|
Token ID | 198 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
xual | +0.703 |
Salman | +0.676 |
fell | +0.673 |
ctrl | +0.671 |
illin | +0.664 |
Neg logit contributions | |
.? | -0.864 |
verty | -0.751 |
numbered | -0.749 |
BLE | -0.741 |
ounty | -0.730 |
Token |
|
Token ID | 198 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
.? | +0.497 |
numbered | +0.426 |
BLE | +0.422 |
verty | +0.420 |
ounty | +0.414 |
Neg logit contributions | |
xual | -0.424 |
Salman | -0.397 |
ctrl | -0.395 |
illin | -0.394 |
fell | -0.394 |
Token | Explore |
Token ID | 35433 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
.? | +2.471 |
numbered | +2.157 |
verty | +2.155 |
BLE | +2.153 |
ounty | +2.111 |
Neg logit contributions | |
xual | -1.720 |
Salman | -1.614 |
Collider | -1.581 |
fell | -1.576 |
illin | -1.568 |
Token | in |
Token ID | 287 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
.? | +2.626 |
numbered | +2.231 |
verty | +2.225 |
BLE | +2.199 |
ounty | +2.179 |
Neg logit contributions | |
xual | -2.448 |
ctrl | -2.362 |
illin | -2.352 |
fell | -2.340 |
Collider | -2.327 |
Token | Sweden |
Token ID | 10710 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
xual | +0.723 |
Salman | +0.692 |
fell | +0.689 |
ctrl | +0.687 |
illin | +0.679 |
Neg logit contributions | |
.? | -0.922 |
verty | -0.802 |
numbered | -0.801 |
BLE | -0.792 |
ounty | -0.781 |
Token | . |
Token ID | 13 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
.? | +3.011 |
verty | +2.560 |
numbered | +2.555 |
BLE | +2.515 |
ounty | +2.487 |
Neg logit contributions | |
xual | -2.578 |
ctrl | -2.492 |
illin | -2.473 |
Collider | -2.452 |
fell | -2.444 |
Token | Assange |
Token ID | 21882 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
xual | +0.971 |
Salman | +0.937 |
fell | +0.930 |
ctrl | +0.925 |
illin | +0.915 |
Neg logit contributions | |
.? | -1.215 |
verty | -1.056 |
numbered | -1.054 |
BLE | -1.042 |
ounty | -1.028 |
Token | has |
Token ID | 468 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
.? | +0.099 |
verty | +0.086 |
numbered | +0.085 |
BLE | +0.084 |
ounty | +0.083 |
Neg logit contributions | |
xual | -0.083 |
ctrl | -0.079 |
Salman | -0.079 |
fell | -0.079 |
illin | -0.078 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
xual | +0.232 |
ctrl | +0.222 |
Salman | +0.222 |
fell | +0.222 |
illin | +0.220 |
Neg logit contributions | |
.? | -0.231 |
verty | -0.197 |
numbered | -0.197 |
BLE | -0.194 |
ounty | -0.191 |
Token | - |
Token ID | 12 |
Feature activation | -8.57e+00 |
Pos logit contributions | |
att | +8.577 |
xual | +8.228 |
fell | +8.182 |
ailable | +7.924 |
Salman | +7.875 |
Neg logit contributions | |
.? | -12.141 |
verty | -10.816 |
BLE | -10.670 |
UGE | -10.364 |
quickShipAvailable | -10.345 |
Token | claimed |
Token ID | 12795 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
att | +4.976 |
xual | +4.971 |
fell | +4.877 |
Salman | +4.682 |
ente | +4.669 |
Neg logit contributions | |
.? | -7.291 |
verty | -6.450 |
BLE | -6.284 |
ounty | -6.230 |
antiquity | -6.198 |
Token | that |
Token ID | 326 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
.? | +2.360 |
numbered | +2.012 |
BLE | +2.001 |
verty | +1.994 |
ounty | +1.956 |
Neg logit contributions | |
xual | -2.518 |
illin | -2.454 |
fell | -2.436 |
ctrl | -2.428 |
Collider | -2.396 |
Token | the |
Token ID | 262 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
xual | +0.148 |
ctrl | +0.143 |
fell | +0.142 |
Salman | +0.142 |
illin | +0.141 |
Neg logit contributions | |
.? | -0.160 |
verty | -0.137 |
numbered | -0.136 |
BLE | -0.135 |
ounty | -0.133 |
Token | investigation |
Token ID | 3645 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
.? | +0.325 |
verty | +0.279 |
numbered | +0.277 |
BLE | +0.275 |
ounty | +0.271 |
Neg logit contributions | |
xual | -0.310 |
ctrl | -0.298 |
Salman | -0.297 |
fell | -0.296 |
illin | -0.294 |
Token | but |
Token ID | 475 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
.? | +1.655 |
numbered | +1.429 |
verty | +1.420 |
BLE | +1.407 |
ounty | +1.365 |
Neg logit contributions | |
xual | -1.513 |
ctrl | -1.445 |
fell | -1.429 |
illin | -1.425 |
Salman | -1.423 |
Token | " |
Token ID | 366 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
xual | +1.155 |
Salman | +1.113 |
fell | +1.107 |
ctrl | +1.102 |
illin | +1.091 |
Neg logit contributions | |
.? | -1.318 |
verty | -1.136 |
numbered | -1.133 |
BLE | -1.121 |
ounty | -1.107 |
Token | Eastern |
Token ID | 46109 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
.? | +1.878 |
numbered | +1.636 |
BLE | +1.600 |
verty | +1.595 |
ANA | +1.555 |
Neg logit contributions | |
xual | -1.934 |
Salman | -1.834 |
Collider | -1.819 |
illin | -1.806 |
ctrl | -1.801 |
Token | " |
Token ID | 1 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
.? | +0.672 |
verty | +0.567 |
numbered | +0.567 |
BLE | +0.557 |
ounty | +0.547 |
Neg logit contributions | |
xual | -0.786 |
Salman | -0.757 |
ctrl | -0.755 |
fell | -0.754 |
illin | -0.746 |
Token | forces |
Token ID | 3386 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
xual | +1.412 |
Salman | +1.366 |
fell | +1.356 |
ctrl | +1.344 |
ente | +1.334 |
Neg logit contributions | |
.? | -1.835 |
verty | -1.601 |
numbered | -1.589 |
BLE | -1.576 |
ounty | -1.561 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.50e+01 |
Pos logit contributions | |
xual | +2.759 |
Salman | +2.722 |
fell | +2.710 |
ente | +2.647 |
att | +2.638 |
Neg logit contributions | |
.? | -3.341 |
verty | -2.910 |
BLE | -2.865 |
numbered | -2.857 |
ounty | -2.846 |
Token | att |
Token ID | 1078 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
att | +9.122 |
fell | +8.344 |
xual | +8.233 |
Salman | +8.144 |
upp | +7.949 |
Neg logit contributions | |
.? | -11.783 |
verty | -10.671 |
ounty | -10.356 |
BLE | -10.238 |
quickShipAvailable | -10.098 |
Token | acked |
Token ID | 6021 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
att | +5.659 |
ente | +5.544 |
xual | +5.379 |
fell | +5.328 |
ailable | +5.247 |
Neg logit contributions | |
.? | -9.517 |
verty | -8.643 |
BLE | -8.560 |
ANA | -8.504 |
quickShipAvailable | -8.483 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
xual | +2.599 |
Salman | +2.547 |
fell | +2.517 |
ctrl | +2.493 |
ente | +2.479 |
Neg logit contributions | |
.? | -2.953 |
verty | -2.578 |
numbered | -2.551 |
ounty | -2.531 |
BLE | -2.531 |
Token | by |
Token ID | 416 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
xual | +1.369 |
Salman | +1.319 |
fell | +1.314 |
ctrl | +1.308 |
ente | +1.296 |
Neg logit contributions | |
.? | -1.434 |
verty | -1.229 |
numbered | -1.227 |
BLE | -1.212 |
ounty | -1.195 |
Token | 1 |
Token ID | 352 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
.? | +3.446 |
numbered | +2.967 |
verty | +2.890 |
BLE | +2.872 |
bleed | +2.826 |
Neg logit contributions | |
xual | -3.256 |
illin | -3.065 |
fell | -3.065 |
ctrl | -3.062 |
ailable | -3.062 |
Token | Proceedings |
Token ID | 30641 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
Salman | +3.481 |
xual | +3.373 |
fell | +3.361 |
illin | +3.340 |
Collider | +3.330 |
Neg logit contributions | |
.? | -4.342 |
verty | -3.844 |
BLE | -3.826 |
numbered | -3.784 |
ounty | -3.679 |
Token | of |
Token ID | 286 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
xual | +2.353 |
Salman | +2.311 |
fell | +2.287 |
ctrl | +2.249 |
Collider | +2.238 |
Neg logit contributions | |
.? | -3.160 |
verty | -2.852 |
numbered | -2.790 |
BLE | -2.762 |
ounty | -2.742 |
Token | the |
Token ID | 262 |
Feature activation | -9.54e+00 |
Pos logit contributions | |
Salman | +4.097 |
fell | +3.996 |
xual | +3.992 |
Collider | +3.959 |
ente | +3.925 |
Neg logit contributions | |
.? | -6.001 |
verty | -5.382 |
BLE | -5.256 |
numbered | -5.202 |
ounty | -5.180 |
Token | National |
Token ID | 2351 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
Salman | +3.828 |
Collider | +3.526 |
fell | +3.517 |
att | +3.496 |
illin | +3.495 |
Neg logit contributions | |
.? | -9.597 |
verty | -8.938 |
BLE | -8.751 |
numbered | -8.593 |
ounty | -8.569 |
Token | Academy |
Token ID | 8581 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
Salman | +1.646 |
Collider | +1.434 |
att | +1.362 |
ente | +1.318 |
fell | +1.190 |
Neg logit contributions | |
.? | -12.667 |
verty | -12.281 |
numbered | -11.831 |
ANA | -11.714 |
BLE | -11.545 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e+01 |
Pos logit contributions | |
Salman | +3.988 |
xual | +3.947 |
fell | +3.909 |
ente | +3.865 |
Collider | +3.839 |
Neg logit contributions | |
.? | -6.066 |
verty | -5.643 |
numbered | -5.463 |
BLE | -5.359 |
ounty | -5.285 |
Token | Sciences |
Token ID | 13473 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
Salman | +5.534 |
kr | +5.477 |
ente | +5.441 |
fell | +5.249 |
att | +5.204 |
Neg logit contributions | |
.? | -13.698 |
quickShipAvailable | -13.257 |
verty | -12.722 |
numbered | -12.390 |
eternity | -12.154 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Salman | +4.595 |
xual | +4.483 |
att | +4.449 |
ctrl | +4.416 |
illin | +4.402 |
Neg logit contributions | |
.? | -7.315 |
verty | -6.887 |
numbered | -6.593 |
BLE | -6.526 |
ANA | -6.481 |
Token | Work |
Token ID | 5521 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
xual | +0.139 |
Salman | +0.134 |
fell | +0.133 |
ctrl | +0.133 |
illin | +0.131 |
Neg logit contributions | |
.? | -0.165 |
verty | -0.143 |
numbered | -0.143 |
BLE | -0.141 |
ounty | -0.139 |
Token | to |
Token ID | 284 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
xual | +2.544 |
Salman | +2.472 |
fell | +2.468 |
ctrl | +2.448 |
ente | +2.422 |
Neg logit contributions | |
.? | -3.104 |
verty | -2.710 |
BLE | -2.693 |
numbered | -2.667 |
ounty | -2.604 |
Token | accomplish |
Token ID | 9989 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
xual | +1.551 |
Salman | +1.502 |
ctrl | +1.500 |
fell | +1.496 |
ente | +1.472 |
Neg logit contributions | |
.? | -1.566 |
verty | -1.357 |
numbered | -1.340 |
BLE | -1.330 |
ounty | -1.306 |
Token | and |
Token ID | 290 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
xual | +0.591 |
Salman | +0.565 |
fell | +0.563 |
ctrl | +0.560 |
illin | +0.554 |
Neg logit contributions | |
.? | -0.801 |
verty | -0.700 |
numbered | -0.700 |
BLE | -0.693 |
ounty | -0.684 |
Token | disgust |
Token ID | 16234 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
.? | +2.347 |
verty | +1.996 |
numbered | +1.980 |
BLE | +1.940 |
bleed | +1.930 |
Neg logit contributions | |
xual | -2.455 |
ctrl | -2.359 |
fell | -2.349 |
illin | -2.342 |
ailable | -2.327 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
.? | +2.704 |
numbered | +2.326 |
verty | +2.324 |
BLE | +2.295 |
ounty | +2.262 |
Neg logit contributions | |
xual | -2.105 |
ctrl | -2.046 |
Salman | -2.036 |
fell | -2.014 |
Collider | -2.010 |
Token | our |
Token ID | 674 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
.? | +1.911 |
verty | +1.653 |
numbered | +1.643 |
BLE | +1.628 |
ounty | +1.597 |
Neg logit contributions | |
xual | -1.640 |
ctrl | -1.567 |
fell | -1.556 |
Salman | -1.551 |
illin | -1.550 |
Token | dem |
Token ID | 1357 |
Feature activation | +8.10e-02 |
Pos logit contributions | |
xual | +0.162 |
Salman | +0.156 |
fell | +0.156 |
ctrl | +0.155 |
illin | +0.154 |
Neg logit contributions | |
.? | -0.165 |
verty | -0.141 |
numbered | -0.141 |
BLE | -0.139 |
ounty | -0.137 |
Token | ig |
Token ID | 328 |
Feature activation | -1.43e+01 |
Pos logit contributions | |
.? | +0.063 |
verty | +0.055 |
numbered | +0.055 |
BLE | +0.054 |
ounty | +0.053 |
Neg logit contributions | |
xual | -0.055 |
Salman | -0.053 |
fell | -0.053 |
ctrl | -0.052 |
Collider | -0.052 |
Token | odd |
Token ID | 5088 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
fell | +4.445 |
ente | +4.247 |
att | +4.067 |
illin | +3.971 |
ctrl | +3.928 |
Neg logit contributions | |
.? | -14.259 |
verty | -14.029 |
BLE | -13.988 |
numbered | -13.672 |
UGE | -13.427 |
Token | ess |
Token ID | 408 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
xual | +2.266 |
Salman | +2.160 |
fell | +2.144 |
ctrl | +2.125 |
ente | +2.118 |
Neg logit contributions | |
.? | -3.407 |
verty | -3.008 |
numbered | -2.998 |
BLE | -2.965 |
ounty | -2.942 |
Token | of |
Token ID | 286 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
xual | +1.110 |
Salman | +1.065 |
fell | +1.061 |
ctrl | +1.052 |
ente | +1.046 |
Neg logit contributions | |
.? | -1.354 |
numbered | -1.180 |
verty | -1.178 |
BLE | -1.162 |
ounty | -1.153 |
Token | depression |
Token ID | 8862 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
.? | +0.150 |
verty | +0.128 |
numbered | +0.128 |
BLE | +0.126 |
ounty | +0.124 |
Neg logit contributions | |
xual | -0.152 |
Salman | -0.146 |
fell | -0.146 |
ctrl | -0.145 |
illin | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
.? | +1.375 |
verty | +1.181 |
numbered | +1.175 |
BLE | +1.165 |
ounty | +1.142 |
Neg logit contributions | |
xual | -1.204 |
Salman | -1.155 |
ctrl | -1.153 |
fell | -1.150 |
illin | -1.141 |
Token | Mem |
Token ID | 4942 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
.? | +4.608 |
numbered | +3.808 |
BLE | +3.792 |
verty | +3.706 |
ANA | +3.692 |
Neg logit contributions | |
xual | -4.960 |
ailable | -4.655 |
illin | -4.611 |
ente | -4.601 |
ctrl | -4.567 |
Token | c |
Token ID | 66 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
xual | +1.611 |
fell | +1.554 |
ctrl | +1.551 |
Salman | +1.517 |
ente | +1.511 |
Neg logit contributions | |
.? | -3.058 |
verty | -2.751 |
numbered | -2.729 |
BLE | -2.698 |
ounty | -2.668 |
Token | py |
Token ID | 9078 |
Feature activation | -6.93e+00 |
Pos logit contributions | |
xual | +2.870 |
fell | +2.794 |
ctrl | +2.791 |
Salman | +2.755 |
ente | +2.754 |
Neg logit contributions | |
.? | -4.413 |
verty | -3.971 |
numbered | -3.874 |
BLE | -3.832 |
ounty | -3.780 |
Token | Reading |
Token ID | 36120 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
fell | +4.715 |
ctrl | +4.694 |
Salman | +4.687 |
att | +4.657 |
xual | +4.655 |
Neg logit contributions | |
.? | -4.925 |
verty | -4.323 |
numbered | -4.240 |
ounty | -4.195 |
bleed | -4.106 |
Token | 55 |
Token ID | 5996 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
xual | +2.337 |
Salman | +2.264 |
fell | +2.256 |
ctrl | +2.241 |
Collider | +2.213 |
Neg logit contributions | |
.? | -3.471 |
verty | -3.076 |
numbered | -3.074 |
BLE | -3.023 |
ounty | -2.992 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
xual | +0.972 |
Salman | +0.930 |
fell | +0.927 |
ctrl | +0.924 |
ente | +0.911 |
Neg logit contributions | |
.? | -1.405 |
verty | -1.234 |
numbered | -1.231 |
BLE | -1.219 |
ounty | -1.202 |
Token | 953 |
Token ID | 49649 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
kr | +5.103 |
fell | +5.045 |
Salman | +5.030 |
att | +4.931 |
ctrl | +4.886 |
Neg logit contributions | |
.? | -13.262 |
verty | -12.813 |
numbered | -12.327 |
BLE | -12.248 |
ANA | -12.227 |
Token | 16 |
Token ID | 1467 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
xual | +0.021 |
Salman | +0.020 |
fell | +0.020 |
ctrl | +0.020 |
illin | +0.020 |
Neg logit contributions | |
.? | -0.029 |
verty | -0.025 |
numbered | -0.025 |
BLE | -0.025 |
ounty | -0.024 |
Token | 27 |
Token ID | 1983 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
xual | +0.918 |
Salman | +0.883 |
fell | +0.881 |
ctrl | +0.878 |
ente | +0.863 |
Neg logit contributions | |
.? | -1.217 |
verty | -1.064 |
numbered | -1.059 |
BLE | -1.048 |
ounty | -1.036 |
Token | 145 |
Token ID | 18781 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
xual | +2.597 |
Salman | +2.549 |
fell | +2.525 |
ctrl | +2.485 |
att | +2.485 |
Neg logit contributions | |
.? | -4.428 |
verty | -3.965 |
numbered | -3.929 |
BLE | -3.909 |
ounty | -3.833 |
Token | Flat |
Token ID | 21939 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
.? | +0.215 |
verty | +0.190 |
numbered | +0.190 |
BLE | +0.188 |
ounty | +0.186 |
Neg logit contributions | |
xual | -0.124 |
Salman | -0.117 |
fell | -0.116 |
ctrl | -0.116 |
illin | -0.115 |
Token | Hotel |
Token ID | 12696 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
.? | +1.599 |
verty | +1.371 |
numbered | +1.365 |
BLE | +1.349 |
ounty | +1.334 |
Neg logit contributions | |
xual | -1.548 |
Salman | -1.465 |
ctrl | -1.461 |
fell | -1.460 |
illin | -1.445 |
Token | Manor |
Token ID | 33555 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
.? | +0.996 |
verty | +0.859 |
numbered | +0.858 |
BLE | +0.850 |
ounty | +0.836 |
Neg logit contributions | |
xual | -0.822 |
Salman | -0.782 |
ctrl | -0.779 |
fell | -0.776 |
illin | -0.771 |
Token | and |
Token ID | 290 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
xual | +1.912 |
fell | +1.848 |
Salman | +1.842 |
ctrl | +1.830 |
ente | +1.816 |
Neg logit contributions | |
.? | -2.336 |
numbered | -2.031 |
verty | -2.027 |
BLE | -2.004 |
ounty | -1.977 |
Token | h |
Token ID | 289 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
xual | +2.964 |
Salman | +2.952 |
fell | +2.947 |
Collider | +2.887 |
ctrl | +2.855 |
Neg logit contributions | |
.? | -3.603 |
verty | -3.114 |
numbered | -3.100 |
BLE | -3.081 |
ounty | -3.079 |
Token | iked |
Token ID | 17951 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
xual | +1.128 |
Salman | +1.087 |
fell | +1.085 |
ctrl | +1.079 |
illin | +1.071 |
Neg logit contributions | |
.? | -1.320 |
verty | -1.141 |
numbered | -1.138 |
BLE | -1.128 |
ounty | -1.110 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.37e+01 |
Pos logit contributions | |
.? | +1.476 |
numbered | +1.270 |
verty | +1.265 |
BLE | +1.259 |
ANA | +1.220 |
Neg logit contributions | |
xual | -1.251 |
ctrl | -1.180 |
illin | -1.179 |
fell | -1.178 |
Salman | -1.177 |
Token | - |
Token ID | 12 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
att | +7.743 |
xual | +7.340 |
ctrl | +7.213 |
fell | +6.986 |
Salman | +6.863 |
Neg logit contributions | |
.? | -10.905 |
BLE | -9.825 |
verty | -9.758 |
ounty | -9.586 |
ANA | -9.359 |
Token | clock |
Token ID | 15750 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
att | +3.946 |
ctrl | +3.822 |
fell | +3.790 |
xual | +3.786 |
Salman | +3.652 |
Neg logit contributions | |
.? | -7.116 |
verty | -6.368 |
BLE | -6.291 |
ounty | -6.226 |
numbered | -6.107 |
Token | wise |
Token ID | 3083 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
xual | +1.665 |
Salman | +1.563 |
ctrl | +1.561 |
fell | +1.544 |
att | +1.534 |
Neg logit contributions | |
.? | -5.812 |
verty | -5.285 |
BLE | -5.257 |
numbered | -5.227 |
ounty | -5.189 |
Token | for |
Token ID | 329 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
xual | +2.151 |
fell | +2.072 |
Salman | +2.071 |
ctrl | +2.057 |
Collider | +2.016 |
Neg logit contributions | |
.? | -2.805 |
verty | -2.474 |
numbered | -2.458 |
BLE | -2.439 |
ounty | -2.424 |
Token | the |
Token ID | 262 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
.? | +1.756 |
numbered | +1.458 |
verty | +1.456 |
BLE | +1.444 |
ounty | +1.390 |
Neg logit contributions | |
xual | -2.182 |
illin | -2.085 |
ctrl | -2.076 |
fell | -2.066 |
Salman | -2.062 |
Token | Mem |
Token ID | 4942 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
.? | +5.253 |
BLE | +4.286 |
numbered | +4.284 |
ANA | +4.181 |
verty | +4.170 |
Neg logit contributions | |
xual | -5.900 |
ailable | -5.567 |
illin | -5.479 |
ente | -5.456 |
ctrl | -5.413 |
Token | c |
Token ID | 66 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
xual | +1.148 |
fell | +1.096 |
ctrl | +1.093 |
Salman | +1.087 |
ente | +1.072 |
Neg logit contributions | |
.? | -2.079 |
verty | -1.854 |
numbered | -1.846 |
BLE | -1.827 |
ounty | -1.805 |
Token | py |
Token ID | 9078 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
xual | +2.526 |
fell | +2.448 |
ctrl | +2.440 |
Salman | +2.421 |
ente | +2.415 |
Neg logit contributions | |
.? | -3.735 |
verty | -3.335 |
numbered | -3.270 |
BLE | -3.237 |
ounty | -3.188 |
Token | Reading |
Token ID | 36120 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
fell | +4.226 |
ctrl | +4.153 |
Salman | +4.149 |
att | +4.112 |
illin | +4.071 |
Neg logit contributions | |
.? | -4.380 |
verty | -3.902 |
ounty | -3.770 |
numbered | -3.762 |
bleed | -3.742 |
Token | 55 |
Token ID | 5996 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
xual | +1.920 |
Salman | +1.856 |
fell | +1.851 |
ctrl | +1.843 |
ente | +1.818 |
Neg logit contributions | |
.? | -2.856 |
verty | -2.535 |
numbered | -2.531 |
BLE | -2.491 |
ounty | -2.455 |
Token | 80 |
Token ID | 1795 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
xual | +0.622 |
Salman | +0.593 |
fell | +0.590 |
ctrl | +0.589 |
illin | +0.582 |
Neg logit contributions | |
.? | -0.868 |
verty | -0.758 |
numbered | -0.758 |
BLE | -0.750 |
ounty | -0.740 |
Token | 953 |
Token ID | 49649 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
kr | +5.057 |
Salman | +5.043 |
fell | +5.002 |
att | +4.938 |
ctrl | +4.859 |
Neg logit contributions | |
.? | -13.018 |
verty | -12.594 |
numbered | -12.138 |
ANA | -12.039 |
BLE | -12.035 |
Token | 16 |
Token ID | 1467 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
.? | +1.295 |
verty | +1.125 |
numbered | +1.117 |
BLE | +1.106 |
ounty | +1.082 |
Neg logit contributions | |
xual | -1.012 |
Salman | -0.953 |
illin | -0.949 |
ctrl | -0.946 |
fell | -0.945 |
Token | 27 |
Token ID | 1983 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
xual | +0.387 |
Salman | +0.370 |
fell | +0.368 |
ctrl | +0.367 |
illin | +0.364 |
Neg logit contributions | |
.? | -0.488 |
numbered | -0.424 |
verty | -0.424 |
BLE | -0.419 |
ounty | -0.413 |
Token | 145 |
Token ID | 18781 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
xual | +2.198 |
Salman | +2.140 |
fell | +2.126 |
ctrl | +2.101 |
ente | +2.085 |
Neg logit contributions | |
.? | -3.594 |
verty | -3.202 |
numbered | -3.176 |
BLE | -3.155 |
ounty | -3.098 |
Token | Flat |
Token ID | 21939 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
.? | +0.864 |
verty | +0.764 |
numbered | +0.762 |
BLE | +0.757 |
ounty | +0.746 |
Neg logit contributions | |
xual | -0.485 |
Salman | -0.456 |
fell | -0.451 |
ctrl | -0.451 |
illin | -0.450 |
Token | is |
Token ID | 318 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
.? | +2.174 |
verty | +1.874 |
numbered | +1.864 |
BLE | +1.827 |
ounty | +1.807 |
Neg logit contributions | |
xual | -1.895 |
ctrl | -1.824 |
illin | -1.800 |
Collider | -1.796 |
Salman | -1.794 |
Token | discreet |
Token ID | 38724 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
xual | +0.248 |
Salman | +0.237 |
fell | +0.237 |
ctrl | +0.237 |
illin | +0.234 |
Neg logit contributions | |
.? | -0.268 |
verty | -0.230 |
numbered | -0.230 |
BLE | -0.227 |
ounty | -0.223 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
xual | +0.773 |
Salman | +0.741 |
fell | +0.737 |
ctrl | +0.735 |
ente | +0.726 |
Neg logit contributions | |
.? | -0.979 |
verty | -0.851 |
numbered | -0.851 |
BLE | -0.841 |
ounty | -0.830 |
Token | It |
Token ID | 632 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
.? | +0.250 |
numbered | +0.213 |
verty | +0.212 |
BLE | +0.210 |
ounty | +0.205 |
Neg logit contributions | |
xual | -0.256 |
ctrl | -0.245 |
Salman | -0.243 |
fell | -0.243 |
illin | -0.242 |
Token | ref |
Token ID | 1006 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
xual | +0.171 |
Salman | +0.164 |
ctrl | +0.163 |
fell | +0.163 |
illin | +0.161 |
Neg logit contributions | |
.? | -0.204 |
verty | -0.177 |
numbered | -0.176 |
BLE | -0.174 |
ounty | -0.172 |
Token | r |
Token ID | 81 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
xual | +0.662 |
Salman | +0.634 |
fell | +0.631 |
ctrl | +0.630 |
illin | +0.622 |
Neg logit contributions | |
.? | -0.848 |
verty | -0.737 |
numbered | -0.737 |
BLE | -0.728 |
ounty | -0.719 |
Token | ains |
Token ID | 1299 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
att | +2.371 |
illin | +1.994 |
kr | +1.722 |
xual | +1.699 |
Salman | +1.652 |
Neg logit contributions | |
.? | -15.964 |
verty | -15.084 |
numbered | -14.980 |
BLE | -14.968 |
UGE | -14.779 |
Token | from |
Token ID | 422 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
xual | +1.240 |
Salman | +1.186 |
fell | +1.178 |
ctrl | +1.171 |
illin | +1.158 |
Neg logit contributions | |
.? | -1.826 |
verty | -1.605 |
numbered | -1.604 |
BLE | -1.587 |
ounty | -1.565 |
Token | prose |
Token ID | 27149 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
.? | +1.263 |
numbered | +1.064 |
verty | +1.060 |
BLE | +1.048 |
ounty | +1.028 |
Neg logit contributions | |
xual | -1.377 |
ctrl | -1.330 |
fell | -1.321 |
illin | -1.316 |
Salman | -1.312 |
Token | ly |
Token ID | 306 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
xual | +0.276 |
Salman | +0.263 |
fell | +0.262 |
ctrl | +0.261 |
illin | +0.258 |
Neg logit contributions | |
.? | -0.402 |
verty | -0.353 |
numbered | -0.353 |
BLE | -0.349 |
ounty | -0.345 |
Token | t |
Token ID | 83 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
xual | +1.527 |
fell | +1.408 |
Salman | +1.402 |
ctrl | +1.398 |
illin | +1.374 |
Neg logit contributions | |
.? | -3.409 |
verty | -3.050 |
numbered | -3.049 |
BLE | -3.029 |
ounty | -2.993 |
Token | Jen |
Token ID | 13364 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
.? | +0.741 |
verty | +0.640 |
numbered | +0.638 |
BLE | +0.636 |
ounty | +0.624 |
Neg logit contributions | |
xual | -0.558 |
ctrl | -0.531 |
fell | -0.531 |
Salman | -0.531 |
illin | -0.528 |
Token | elle |
Token ID | 13485 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
.? | +2.270 |
verty | +2.008 |
numbered | +2.004 |
BLE | +1.998 |
ounty | +1.968 |
Neg logit contributions | |
xual | -1.024 |
Salman | -0.963 |
ctrl | -0.952 |
fell | -0.946 |
Collider | -0.930 |
Token | ?! |
Token ID | 12248 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
xual | +0.006 |
Salman | +0.006 |
fell | +0.006 |
ctrl | +0.006 |
illin | +0.006 |
Neg logit contributions | |
.? | -0.007 |
verty | -0.006 |
numbered | -0.006 |
BLE | -0.006 |
ounty | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
.? | +0.512 |
verty | +0.434 |
numbered | +0.432 |
BLE | +0.430 |
ounty | +0.421 |
Neg logit contributions | |
xual | -0.467 |
ctrl | -0.444 |
Salman | -0.444 |
fell | -0.444 |
illin | -0.440 |
Token | Res |
Token ID | 4965 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
xual | +1.263 |
fell | +1.225 |
Salman | +1.222 |
ctrl | +1.221 |
ente | +1.203 |
Neg logit contributions | |
.? | -1.393 |
verty | -1.201 |
numbered | -1.195 |
BLE | -1.176 |
ounty | -1.165 |
Token | isting |
Token ID | 9665 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
.? | +2.304 |
numbered | +2.012 |
verty | +2.004 |
BLE | +1.957 |
ounty | +1.947 |
Neg logit contributions | |
xual | -1.874 |
Salman | -1.799 |
ctrl | -1.785 |
Collider | -1.776 |
fell | -1.766 |
Token | violations |
Token ID | 11734 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Salman | +8.896 |
xual | +8.701 |
Collider | +8.656 |
fell | +8.564 |
ente | +8.491 |
Neg logit contributions | |
.? | -9.316 |
verty | -8.273 |
numbered | -8.038 |
BLE | -7.920 |
ounty | -7.889 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
xual | +1.368 |
Salman | +1.311 |
fell | +1.307 |
ctrl | +1.294 |
Collider | +1.283 |
Neg logit contributions | |
.? | -1.697 |
verty | -1.493 |
numbered | -1.484 |
BLE | -1.467 |
ounty | -1.442 |
Token | the |
Token ID | 262 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
xual | +2.292 |
Salman | +2.248 |
fell | +2.235 |
ctrl | +2.194 |
Collider | +2.185 |
Neg logit contributions | |
.? | -2.619 |
numbered | -2.263 |
verty | -2.253 |
BLE | -2.233 |
ounty | -2.198 |
Token | Supreme |
Token ID | 5617 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
xual | +2.090 |
Salman | +2.043 |
fell | +2.025 |
ctrl | +2.002 |
Collider | +1.991 |
Neg logit contributions | |
.? | -2.250 |
numbered | -1.935 |
verty | -1.930 |
BLE | -1.911 |
ounty | -1.875 |
Token | Court |
Token ID | 3078 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
.? | +2.262 |
numbered | +1.894 |
verty | +1.889 |
BLE | +1.869 |
ounty | +1.829 |
Neg logit contributions | |
xual | -2.652 |
ctrl | -2.529 |
illin | -2.510 |
ailable | -2.509 |
fell | -2.506 |
Token | scaff |
Token ID | 41498 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
xual | +0.373 |
Salman | +0.357 |
fell | +0.356 |
ctrl | +0.356 |
ente | +0.352 |
Neg logit contributions | |
.? | -0.374 |
verty | -0.319 |
numbered | -0.319 |
BLE | -0.315 |
ounty | -0.310 |
Token | old |
Token ID | 727 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
xual | +0.412 |
Salman | +0.395 |
fell | +0.394 |
ctrl | +0.392 |
illin | +0.388 |
Neg logit contributions | |
.? | -0.509 |
verty | -0.442 |
numbered | -0.442 |
BLE | -0.437 |
ounty | -0.430 |
Token | into |
Token ID | 656 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
.? | +0.713 |
verty | +0.601 |
numbered | +0.599 |
BLE | +0.598 |
ounty | +0.586 |
Neg logit contributions | |
xual | -0.649 |
Salman | -0.620 |
ctrl | -0.619 |
fell | -0.616 |
illin | -0.612 |
Token | the |
Token ID | 262 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
xual | +1.196 |
Salman | +1.153 |
fell | +1.146 |
ctrl | +1.145 |
illin | +1.130 |
Neg logit contributions | |
.? | -1.298 |
verty | -1.117 |
numbered | -1.116 |
BLE | -1.099 |
ounty | -1.084 |
Token | per |
Token ID | 583 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
xual | +2.659 |
Salman | +2.590 |
ctrl | +2.570 |
fell | +2.567 |
Collider | +2.547 |
Neg logit contributions | |
.? | -2.557 |
numbered | -2.190 |
verty | -2.189 |
BLE | -2.149 |
ounty | -2.117 |
Token | ov |
Token ID | 709 |
Feature activation | -1.35e+01 |
Pos logit contributions | |
xual | +0.674 |
Salman | +0.643 |
fell | +0.641 |
ctrl | +0.639 |
ente | +0.631 |
Neg logit contributions | |
.? | -0.937 |
verty | -0.819 |
numbered | -0.819 |
BLE | -0.810 |
ounty | -0.799 |
Token | sk |
Token ID | 8135 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
fell | +3.895 |
ctrl | +3.822 |
xual | +3.701 |
att | +3.694 |
kr | +3.560 |
Neg logit contributions | |
.? | -14.494 |
verty | -13.314 |
BLE | -13.289 |
quickShipAvailable | -13.175 |
numbered | -13.093 |
Token | ite |
Token ID | 578 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
.? | +0.582 |
verty | +0.510 |
numbered | +0.509 |
BLE | +0.504 |
ounty | +0.498 |
Neg logit contributions | |
xual | -0.398 |
Salman | -0.380 |
fell | -0.378 |
ctrl | -0.377 |
illin | -0.372 |
Token | - |
Token ID | 12 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
xual | +2.465 |
Salman | +2.396 |
fell | +2.376 |
ctrl | +2.357 |
Collider | +2.342 |
Neg logit contributions | |
.? | -2.769 |
numbered | -2.440 |
verty | -2.425 |
BLE | -2.382 |
ounty | -2.345 |
Token | f |
Token ID | 69 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
.? | +0.628 |
numbered | +0.542 |
verty | +0.537 |
BLE | +0.532 |
ounty | +0.523 |
Neg logit contributions | |
xual | -0.606 |
Salman | -0.582 |
ctrl | -0.574 |
fell | -0.572 |
Collider | -0.569 |
Token | lled |
Token ID | 3353 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
xual | +0.688 |
fell | +0.662 |
Salman | +0.662 |
ctrl | +0.658 |
ente | +0.654 |
Neg logit contributions | |
.? | -0.691 |
numbered | -0.591 |
verty | -0.591 |
BLE | -0.583 |
ounty | -0.573 |
Token | client |
Token ID | 5456 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
xual | +0.628 |
Salman | +0.608 |
fell | +0.605 |
ctrl | +0.604 |
ente | +0.598 |
Neg logit contributions | |
.? | -0.609 |
numbered | -0.520 |
verty | -0.520 |
BLE | -0.512 |
ounty | -0.504 |
Token | . |
Token ID | 13 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
xual | +0.324 |
Salman | +0.311 |
fell | +0.310 |
ctrl | +0.309 |
ente | +0.305 |
Neg logit contributions | |
.? | -0.430 |
numbered | -0.376 |
verty | -0.376 |
BLE | -0.372 |
ounty | -0.367 |
Token | And |
Token ID | 843 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
.? | +1.959 |
numbered | +1.636 |
verty | +1.618 |
BLE | +1.614 |
ANA | +1.588 |
Neg logit contributions | |
xual | -2.008 |
ctrl | -1.888 |
illin | -1.870 |
ailable | -1.865 |
ente | -1.860 |
Token | as |
Token ID | 355 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
.? | +0.861 |
numbered | +0.734 |
verty | +0.733 |
BLE | +0.724 |
ounty | +0.711 |
Neg logit contributions | |
xual | -0.795 |
ctrl | -0.756 |
fell | -0.756 |
Salman | -0.754 |
illin | -0.751 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
.? | +0.777 |
verty | +0.662 |
numbered | +0.661 |
BLE | +0.653 |
ounty | +0.643 |
Neg logit contributions | |
xual | -0.730 |
fell | -0.690 |
ctrl | -0.690 |
Salman | -0.688 |
illin | -0.684 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
xual | +0.073 |
Salman | +0.070 |
fell | +0.070 |
ctrl | +0.069 |
illin | +0.069 |
Neg logit contributions | |
.? | -0.076 |
verty | -0.065 |
numbered | -0.065 |
BLE | -0.064 |
ounty | -0.063 |
Token | party |
Token ID | 10608 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
att | +5.689 |
fell | +5.362 |
ctrl | +5.335 |
ente | +5.326 |
xual | +5.223 |
Neg logit contributions | |
.? | -12.527 |
verty | -11.466 |
BLE | -11.389 |
UGE | -11.270 |
numbered | -11.095 |
Token | , |
Token ID | 11 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
xual | +0.582 |
Salman | +0.558 |
fell | +0.555 |
ctrl | +0.553 |
ente | +0.546 |
Neg logit contributions | |
.? | -0.816 |
verty | -0.717 |
numbered | -0.716 |
BLE | -0.707 |
ounty | -0.699 |
Token | you |
Token ID | 345 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
.? | +0.625 |
verty | +0.526 |
numbered | +0.526 |
BLE | +0.520 |
ounty | +0.510 |
Neg logit contributions | |
xual | -0.672 |
Salman | -0.644 |
fell | -0.643 |
ctrl | -0.643 |
illin | -0.639 |
Token | � |
Token ID | 447 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
.? | +1.050 |
verty | +0.881 |
numbered | +0.880 |
BLE | +0.867 |
ounty | +0.854 |
Neg logit contributions | |
xual | -1.168 |
Salman | -1.120 |
ctrl | -1.119 |
fell | -1.115 |
illin | -1.110 |
Token | � |
Token ID | 247 |
Feature activation | -6.12e-01 |
Pos logit contributions | |
xual | +1.775 |
Salman | +1.721 |
fell | +1.707 |
ctrl | +1.694 |
ente | +1.693 |
Neg logit contributions | |
.? | -1.712 |
numbered | -1.488 |
verty | -1.461 |
BLE | -1.437 |
ounty | -1.419 |
Token | rip |
Token ID | 5528 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
xual | +0.215 |
Salman | +0.205 |
fell | +0.205 |
ctrl | +0.203 |
ente | +0.201 |
Neg logit contributions | |
.? | -0.283 |
numbered | -0.246 |
verty | -0.246 |
BLE | -0.243 |
ounty | -0.240 |
Token | et |
Token ID | 316 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
xual | +1.520 |
ente | +1.447 |
fell | +1.420 |
att | +1.394 |
ctrl | +1.385 |
Neg logit contributions | |
.? | -4.593 |
numbered | -4.161 |
verty | -4.161 |
BLE | -4.119 |
ANA | -4.059 |
Token | al |
Token ID | 282 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
xual | +1.915 |
fell | +1.860 |
ctrl | +1.853 |
Salman | +1.847 |
illin | +1.834 |
Neg logit contributions | |
.? | -1.953 |
verty | -1.680 |
numbered | -1.671 |
BLE | -1.642 |
ounty | -1.613 |
Token | acceleration |
Token ID | 20309 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
.? | +0.407 |
verty | +0.346 |
numbered | +0.346 |
BLE | +0.343 |
ounty | +0.337 |
Neg logit contributions | |
xual | -0.391 |
Salman | -0.375 |
fell | -0.374 |
ctrl | -0.372 |
ente | -0.370 |
Token | only |
Token ID | 691 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
.? | +3.124 |
numbered | +2.604 |
BLE | +2.591 |
bleed | +2.578 |
verty | +2.566 |
Neg logit contributions | |
xual | -2.944 |
ailable | -2.837 |
Salman | -2.828 |
ente | -2.816 |
illin | -2.814 |
Token | counter |
Token ID | 3753 |
Feature activation | -1.34e+01 |
Pos logit contributions | |
.? | +3.314 |
BLE | +2.740 |
numbered | +2.739 |
verty | +2.722 |
bleed | +2.712 |
Neg logit contributions | |
xual | -3.445 |
illin | -3.293 |
ente | -3.287 |
ailable | -3.282 |
Salman | -3.275 |
Token | acts |
Token ID | 8656 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
att | +5.129 |
xual | +5.014 |
fell | +4.845 |
ctrl | +4.567 |
Collider | +4.393 |
Neg logit contributions | |
.? | -13.524 |
verty | -12.218 |
ounty | -12.207 |
numbered | -12.113 |
UGE | -12.001 |
Token | Earth |
Token ID | 3668 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
xual | +1.437 |
Salman | +1.390 |
ctrl | +1.382 |
fell | +1.376 |
Collider | +1.364 |
Neg logit contributions | |
.? | -1.613 |
verty | -1.404 |
numbered | -1.399 |
BLE | -1.382 |
ounty | -1.363 |
Token | 's |
Token ID | 338 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
xual | +2.600 |
fell | +2.514 |
ctrl | +2.498 |
Salman | +2.482 |
Collider | +2.470 |
Neg logit contributions | |
.? | -3.214 |
numbered | -2.831 |
verty | -2.826 |
BLE | -2.772 |
ounty | -2.754 |
Token | gravity |
Token ID | 13522 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
xual | +1.988 |
Salman | +1.921 |
ctrl | +1.918 |
fell | +1.899 |
Collider | +1.898 |
Neg logit contributions | |
.? | -2.222 |
numbered | -1.936 |
verty | -1.936 |
BLE | -1.911 |
ounty | -1.889 |
Token | by |
Token ID | 416 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
xual | +1.054 |
Salman | +1.012 |
fell | +1.007 |
ctrl | +1.006 |
ente | +0.990 |
Neg logit contributions | |
.? | -1.386 |
verty | -1.219 |
numbered | -1.216 |
BLE | -1.200 |
ounty | -1.186 |
Token | ry |
Token ID | 563 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
xual | +0.707 |
Salman | +0.664 |
fell | +0.658 |
ctrl | +0.656 |
ente | +0.645 |
Neg logit contributions | |
.? | -1.846 |
numbered | -1.660 |
verty | -1.660 |
BLE | -1.647 |
ounty | -1.628 |
Token | short |
Token ID | 1790 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
xual | +0.683 |
Salman | +0.646 |
ctrl | +0.642 |
fell | +0.640 |
ente | +0.629 |
Neg logit contributions | |
.? | -1.433 |
verty | -1.279 |
numbered | -1.278 |
BLE | -1.266 |
ounty | -1.252 |
Token | limit |
Token ID | 4179 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
.? | +3.747 |
numbered | +3.090 |
BLE | +3.069 |
bleed | +3.063 |
verty | +3.043 |
Neg logit contributions | |
xual | -3.765 |
fell | -3.598 |
illin | -3.569 |
Salman | -3.551 |
ailable | -3.512 |
Token | : |
Token ID | 25 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
xual | +1.219 |
Salman | +1.171 |
fell | +1.167 |
ctrl | +1.161 |
ente | +1.132 |
Neg logit contributions | |
.? | -2.630 |
verty | -2.377 |
numbered | -2.353 |
BLE | -2.334 |
ounty | -2.313 |
Token | 7 |
Token ID | 22 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
xual | +2.894 |
ctrl | +2.867 |
fell | +2.823 |
Salman | +2.819 |
att | +2.769 |
Neg logit contributions | |
.? | -5.012 |
verty | -4.526 |
numbered | -4.459 |
ounty | -4.373 |
BLE | -4.365 |
Token | R |
Token ID | 371 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
xual | +1.457 |
Salman | +1.407 |
ctrl | +1.397 |
fell | +1.395 |
Collider | +1.373 |
Neg logit contributions | |
.? | -1.860 |
verty | -1.625 |
numbered | -1.619 |
BLE | -1.601 |
ounty | -1.583 |
Token | TS |
Token ID | 4694 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ctrl | +5.720 |
att | +5.712 |
ente | +5.562 |
fell | +5.512 |
Salman | +5.406 |
Neg logit contributions | |
.? | -11.802 |
verty | -11.095 |
bleed | -10.758 |
numbered | -10.695 |
antiquity | -10.681 |
Token | thr |
Token ID | 5636 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
xual | +2.626 |
Salman | +2.603 |
ctrl | +2.597 |
fell | +2.564 |
att | +2.538 |
Neg logit contributions | |
.? | -2.215 |
verty | -1.905 |
numbered | -1.905 |
BLE | -1.873 |
ounty | -1.849 |
Token | : |
Token ID | 25 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
xual | +0.701 |
Salman | +0.660 |
fell | +0.656 |
ctrl | +0.654 |
illin | +0.645 |
Neg logit contributions | |
.? | -1.391 |
numbered | -1.237 |
verty | -1.236 |
BLE | -1.225 |
ounty | -1.210 |
Token | off |
Token ID | 2364 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
xual | +0.702 |
Salman | +0.666 |
fell | +0.661 |
ctrl | +0.658 |
illin | +0.651 |
Neg logit contributions | |
.? | -1.199 |
numbered | -1.060 |
verty | -1.059 |
BLE | -1.049 |
ounty | -1.035 |
Token | Frag |
Token ID | 24229 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
.? | +4.661 |
numbered | +3.991 |
verty | +3.979 |
BLE | +3.931 |
ounty | +3.842 |
Neg logit contributions | |
xual | -3.739 |
illin | -3.481 |
fell | -3.417 |
ente | -3.398 |
ctrl | -3.373 |
Token | I |
Token ID | 314 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
.? | +0.690 |
verty | +0.591 |
numbered | +0.587 |
BLE | +0.581 |
ounty | +0.569 |
Neg logit contributions | |
xual | -0.592 |
Salman | -0.561 |
ctrl | -0.560 |
fell | -0.559 |
illin | -0.554 |
Token | did |
Token ID | 750 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
.? | +0.115 |
verty | +0.099 |
numbered | +0.099 |
BLE | +0.098 |
ounty | +0.096 |
Neg logit contributions | |
xual | -0.106 |
Salman | -0.101 |
fell | -0.101 |
ctrl | -0.101 |
illin | -0.100 |
Token | give |
Token ID | 1577 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
xual | +2.328 |
Salman | +2.249 |
fell | +2.240 |
ctrl | +2.221 |
ente | +2.199 |
Neg logit contributions | |
.? | -2.764 |
numbered | -2.439 |
verty | -2.433 |
BLE | -2.383 |
ounty | -2.373 |
Token | it |
Token ID | 340 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
xual | +1.956 |
Salman | +1.886 |
fell | +1.875 |
ctrl | +1.865 |
illin | +1.839 |
Neg logit contributions | |
.? | -2.488 |
verty | -2.185 |
numbered | -2.176 |
BLE | -2.146 |
ounty | -2.122 |
Token | a |
Token ID | 257 |
Feature activation | -8.64e+00 |
Pos logit contributions | |
xual | +4.125 |
Salman | +4.096 |
ctrl | +4.063 |
fell | +4.053 |
att | +3.930 |
Neg logit contributions | |
.? | -5.814 |
numbered | -5.302 |
verty | -5.223 |
BLE | -5.116 |
ounty | -5.078 |
Token | little |
Token ID | 1310 |
Feature activation | -1.33e+01 |
Pos logit contributions | |
Salman | +4.930 |
fell | +4.853 |
ctrl | +4.812 |
Collider | +4.800 |
xual | +4.785 |
Neg logit contributions | |
.? | -7.044 |
verty | -6.356 |
numbered | -6.354 |
BLE | -6.234 |
ounty | -6.159 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Salman | +7.190 |
Collider | +7.025 |
fell | +6.992 |
att | +6.855 |
ctrl | +6.832 |
Neg logit contributions | |
.? | -10.285 |
numbered | -9.826 |
verty | -9.439 |
BLE | -9.226 |
ounty | -9.207 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
xual | +0.925 |
Salman | +0.886 |
ctrl | +0.882 |
fell | +0.881 |
illin | +0.869 |
Neg logit contributions | |
.? | -1.236 |
verty | -1.084 |
numbered | -1.084 |
BLE | -1.072 |
ounty | -1.056 |
Token | I |
Token ID | 314 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
xual | +1.162 |
Salman | +1.128 |
fell | +1.122 |
ctrl | +1.113 |
Collider | +1.101 |
Neg logit contributions | |
.? | -1.331 |
verty | -1.155 |
numbered | -1.151 |
BLE | -1.137 |
ounty | -1.124 |
Token | started |
Token ID | 2067 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
xual | +0.340 |
Salman | +0.327 |
fell | +0.326 |
ctrl | +0.324 |
illin | +0.321 |
Neg logit contributions | |
.? | -0.375 |
verty | -0.324 |
numbered | -0.323 |
BLE | -0.320 |
ounty | -0.314 |
Token | to |
Token ID | 284 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
.? | +1.009 |
verty | +0.856 |
numbered | +0.855 |
BLE | +0.840 |
ounty | +0.830 |
Neg logit contributions | |
xual | -1.007 |
Salman | -0.967 |
ctrl | -0.964 |
fell | -0.963 |
illin | -0.958 |
Token | elling |
Token ID | 9417 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
xual | +2.480 |
Salman | +2.430 |
illin | +2.399 |
ente | +2.386 |
att | +2.381 |
Neg logit contributions | |
.? | -3.984 |
verty | -3.540 |
numbered | -3.529 |
BLE | -3.477 |
ounty | -3.418 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
xual | +1.144 |
Salman | +1.098 |
fell | +1.093 |
ctrl | +1.091 |
illin | +1.078 |
Neg logit contributions | |
.? | -1.335 |
verty | -1.154 |
numbered | -1.152 |
BLE | -1.139 |
ounty | -1.122 |
Token | outbreak |
Token ID | 17645 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
xual | +0.082 |
fell | +0.078 |
Salman | +0.078 |
ctrl | +0.077 |
ente | +0.076 |
Neg logit contributions | |
.? | -0.105 |
verty | -0.092 |
numbered | -0.092 |
BLE | -0.091 |
ounty | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
.? | +4.305 |
BLE | +3.578 |
verty | +3.532 |
numbered | +3.523 |
antiquity | +3.493 |
Neg logit contributions | |
xual | -4.456 |
fell | -4.223 |
Collider | -4.201 |
ctrl | -4.149 |
ailable | -4.139 |
Token | full |
Token ID | 1336 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
.? | +0.689 |
verty | +0.593 |
numbered | +0.592 |
BLE | +0.588 |
ounty | +0.577 |
Neg logit contributions | |
xual | -0.614 |
fell | -0.581 |
Salman | -0.579 |
ctrl | -0.579 |
illin | -0.570 |
Token | - |
Token ID | 12 |
Feature activation | +8.36e+00 |
Pos logit contributions | |
.? | +2.885 |
verty | +2.518 |
numbered | +2.496 |
ounty | +2.484 |
BLE | +2.476 |
Neg logit contributions | |
xual | -2.394 |
ctrl | -2.206 |
Salman | -2.203 |
Collider | -2.193 |
fell | -2.191 |
Token | blown |
Token ID | 31290 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
.? | +3.677 |
numbered | +3.094 |
verty | +2.857 |
ounty | +2.776 |
BLE | +2.740 |
Neg logit contributions | |
xual | -8.519 |
Collider | -7.977 |
Salman | -7.959 |
ailable | -7.798 |
illin | -7.718 |
Token | pand |
Token ID | 19798 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
.? | +2.387 |
verty | +2.082 |
numbered | +2.077 |
BLE | +2.060 |
ounty | +2.042 |
Neg logit contributions | |
xual | -1.708 |
ctrl | -1.598 |
fell | -1.591 |
Salman | -1.563 |
ailable | -1.558 |
Token | emic |
Token ID | 5314 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
xual | +0.757 |
ente | +0.734 |
Salman | +0.733 |
fell | +0.733 |
ctrl | +0.732 |
Neg logit contributions | |
.? | -0.412 |
numbered | -0.333 |
verty | -0.332 |
BLE | -0.324 |
ounty | -0.313 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
.? | +2.968 |
numbered | +2.502 |
verty | +2.493 |
BLE | +2.493 |
ounty | +2.449 |
Neg logit contributions | |
xual | -2.463 |
fell | -2.367 |
Salman | -2.343 |
ctrl | -2.339 |
Collider | -2.333 |
Token | SW |
Token ID | 12672 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
.? | +0.161 |
numbered | +0.139 |
verty | +0.139 |
BLE | +0.137 |
ounty | +0.135 |
Neg logit contributions | |
xual | -0.136 |
fell | -0.129 |
ctrl | -0.129 |
Salman | -0.129 |
ente | -0.127 |
Token |
|
Token ID | 198 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
.? | +1.290 |
numbered | +1.099 |
BLE | +1.091 |
verty | +1.074 |
ounty | +1.062 |
Neg logit contributions | |
xual | -1.148 |
Salman | -1.062 |
ctrl | -1.061 |
Collider | -1.061 |
illin | -1.060 |
Token | The |
Token ID | 464 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
.? | +2.492 |
BLE | +2.115 |
numbered | +2.114 |
verty | +2.106 |
ANA | +2.067 |
Neg logit contributions | |
xual | -2.569 |
Salman | -2.412 |
Collider | -2.384 |
illin | -2.379 |
ctrl | -2.362 |
Token | timing |
Token ID | 10576 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
.? | +2.246 |
verty | +1.931 |
numbered | +1.904 |
BLE | +1.894 |
ounty | +1.855 |
Neg logit contributions | |
xual | -2.195 |
Salman | -2.081 |
fell | -2.079 |
ctrl | -2.073 |
ente | -2.054 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
.? | +2.172 |
numbered | +1.856 |
verty | +1.844 |
BLE | +1.826 |
ounty | +1.784 |
Neg logit contributions | |
xual | -1.975 |
illin | -1.886 |
ctrl | -1.881 |
Salman | -1.880 |
fell | -1.872 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
.? | +0.842 |
verty | +0.722 |
numbered | +0.720 |
BLE | +0.712 |
ounty | +0.700 |
Neg logit contributions | |
xual | -0.798 |
Salman | -0.761 |
fell | -0.760 |
ctrl | -0.760 |
illin | -0.753 |
Token | injury |
Token ID | 5095 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
.? | +1.322 |
verty | +1.126 |
numbered | +1.120 |
BLE | +1.106 |
ounty | +1.086 |
Neg logit contributions | |
xual | -1.403 |
Salman | -1.340 |
fell | -1.336 |
ctrl | -1.335 |
ente | -1.324 |
Token | is |
Token ID | 318 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
.? | +8.496 |
bleed | +7.066 |
numbered | +6.968 |
verty | +6.956 |
repl | +6.822 |
Neg logit contributions | |
xual | -8.416 |
ailable | -8.069 |
illin | -7.921 |
ctrl | -7.883 |
ente | -7.815 |
Token | especially |
Token ID | 2592 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
.? | +2.096 |
verty | +1.752 |
BLE | +1.744 |
numbered | +1.742 |
ounty | +1.685 |
Neg logit contributions | |
xual | -2.159 |
ctrl | -2.039 |
fell | -2.032 |
illin | -2.024 |
Salman | -2.011 |
Token | unfortunate |
Token ID | 14855 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
.? | +1.920 |
verty | +1.604 |
numbered | +1.592 |
BLE | +1.581 |
ounty | +1.542 |
Neg logit contributions | |
xual | -2.385 |
ctrl | -2.275 |
fell | -2.262 |
Salman | -2.246 |
illin | -2.242 |
Token | for |
Token ID | 329 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
.? | +3.465 |
numbered | +2.948 |
verty | +2.916 |
BLE | +2.897 |
ounty | +2.815 |
Neg logit contributions | |
xual | -3.376 |
ctrl | -3.218 |
Salman | -3.198 |
Collider | -3.191 |
ailable | -3.190 |
Token | Vol |
Token ID | 4709 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
.? | +2.976 |
verty | +2.553 |
numbered | +2.543 |
BLE | +2.522 |
ounty | +2.465 |
Neg logit contributions | |
xual | -2.710 |
ctrl | -2.562 |
fell | -2.558 |
Salman | -2.533 |
illin | -2.533 |
Token | � |
Token ID | 447 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
xual | +1.386 |
Salman | +1.341 |
fell | +1.333 |
ctrl | +1.324 |
ente | +1.313 |
Neg logit contributions | |
.? | -1.595 |
verty | -1.387 |
numbered | -1.380 |
BLE | -1.362 |
ounty | -1.346 |
Token | � |
Token ID | 251 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
.? | +1.429 |
verty | +1.181 |
BLE | +1.162 |
numbered | +1.160 |
ounty | +1.136 |
Neg logit contributions | |
xual | -2.035 |
ctrl | -1.969 |
Salman | -1.962 |
fell | -1.960 |
illin | -1.950 |
Token |
|
Token ID | 198 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
.? | +1.243 |
numbered | +1.058 |
BLE | +1.053 |
verty | +1.052 |
ounty | +1.029 |
Neg logit contributions | |
xual | -1.106 |
ctrl | -1.054 |
fell | -1.047 |
Salman | -1.046 |
illin | -1.043 |
Token |
|
Token ID | 198 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
xual | +0.294 |
Salman | +0.279 |
ctrl | +0.277 |
fell | +0.277 |
illin | +0.275 |
Neg logit contributions | |
.? | -0.364 |
numbered | -0.315 |
verty | -0.313 |
BLE | -0.312 |
ounty | -0.306 |
Token | T |
Token ID | 51 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
xual | +0.177 |
Salman | +0.170 |
fell | +0.169 |
ctrl | +0.169 |
illin | +0.167 |
Neg logit contributions | |
.? | -0.193 |
verty | -0.166 |
numbered | -0.166 |
BLE | -0.164 |
ounty | -0.161 |
Token | ina |
Token ID | 1437 |
Feature activation | +8.90e+00 |
Pos logit contributions | |
xual | +1.407 |
fell | +1.374 |
ente | +1.374 |
Salman | +1.368 |
illin | +1.358 |
Neg logit contributions | |
.? | -1.880 |
verty | -1.644 |
numbered | -1.642 |
BLE | -1.625 |
ounty | -1.594 |
Token | Ole |
Token ID | 30093 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
.? | +6.913 |
verty | +5.914 |
numbered | +5.844 |
BLE | +5.780 |
ANA | +5.669 |
Neg logit contributions | |
xual | -5.641 |
ctrl | -5.528 |
illin | -5.389 |
fell | -5.360 |
Collider | -5.274 |
Token | ch |
Token ID | 354 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
.? | +1.391 |
verty | +1.219 |
numbered | +1.218 |
BLE | +1.192 |
ounty | +1.176 |
Neg logit contributions | |
xual | -0.981 |
Salman | -0.927 |
ctrl | -0.927 |
fell | -0.923 |
illin | -0.914 |
Token | owski |
Token ID | 12079 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
.? | +3.436 |
verty | +3.013 |
numbered | +2.966 |
BLE | +2.906 |
ounty | +2.887 |
Neg logit contributions | |
xual | -2.712 |
ctrl | -2.542 |
Collider | -2.529 |
Salman | -2.527 |
illin | -2.522 |
Token | , |
Token ID | 11 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
.? | +1.366 |
verty | +1.183 |
numbered | +1.171 |
BLE | +1.165 |
ANA | +1.143 |
Neg logit contributions | |
xual | -1.093 |
ctrl | -1.036 |
fell | -1.028 |
illin | -1.024 |
Salman | -1.021 |
Token | a |
Token ID | 257 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
xual | +1.736 |
Salman | +1.695 |
fell | +1.671 |
ctrl | +1.658 |
ente | +1.657 |
Neg logit contributions | |
.? | -2.147 |
verty | -1.877 |
numbered | -1.877 |
BLE | -1.846 |
ounty | -1.824 |
Token | if |
Token ID | 611 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
.? | +0.842 |
verty | +0.718 |
numbered | +0.717 |
BLE | +0.709 |
ounty | +0.695 |
Neg logit contributions | |
xual | -0.821 |
fell | -0.786 |
ctrl | -0.785 |
Salman | -0.784 |
illin | -0.778 |
Token | you |
Token ID | 345 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
xual | +2.049 |
Salman | +2.010 |
fell | +1.971 |
ctrl | +1.958 |
ente | +1.957 |
Neg logit contributions | |
.? | -2.238 |
numbered | -1.936 |
verty | -1.921 |
BLE | -1.895 |
ounty | -1.883 |
Token | look |
Token ID | 804 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
xual | +0.740 |
Salman | +0.722 |
fell | +0.718 |
ctrl | +0.711 |
ente | +0.706 |
Neg logit contributions | |
.? | -0.747 |
verty | -0.643 |
numbered | -0.641 |
BLE | -0.633 |
ounty | -0.620 |
Token | at |
Token ID | 379 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
xual | +2.326 |
Salman | +2.262 |
fell | +2.224 |
ente | +2.188 |
ctrl | +2.186 |
Neg logit contributions | |
.? | -3.507 |
numbered | -3.113 |
verty | -3.087 |
BLE | -3.071 |
ounty | -3.041 |
Token | it |
Token ID | 340 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
.? | +0.469 |
verty | +0.402 |
numbered | +0.401 |
BLE | +0.397 |
ounty | +0.388 |
Neg logit contributions | |
xual | -0.439 |
fell | -0.420 |
ctrl | -0.420 |
Salman | -0.418 |
illin | -0.415 |
Token | from |
Token ID | 422 |
Feature activation | +8.80e+00 |
Pos logit contributions | |
.? | +1.660 |
verty | +1.426 |
numbered | +1.416 |
BLE | +1.392 |
ounty | +1.376 |
Neg logit contributions | |
xual | -1.413 |
ctrl | -1.354 |
fell | -1.350 |
Salman | -1.347 |
illin | -1.347 |
Token | the |
Token ID | 262 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
.? | +5.845 |
antiquity | +5.035 |
verty | +5.014 |
bleed | +4.855 |
BLE | +4.851 |
Neg logit contributions | |
xual | -6.562 |
fell | -6.241 |
illin | -6.209 |
ctrl | -6.164 |
ailable | -6.019 |
Token | point |
Token ID | 966 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
.? | +4.635 |
verty | +4.016 |
antiquity | +3.867 |
BLE | +3.844 |
numbered | +3.836 |
Neg logit contributions | |
xual | -5.403 |
fell | -5.087 |
ctrl | -5.078 |
illin | -5.041 |
ente | -4.992 |
Token | of |
Token ID | 286 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
.? | +2.835 |
verty | +2.410 |
numbered | +2.396 |
BLE | +2.380 |
ounty | +2.327 |
Neg logit contributions | |
xual | -2.832 |
fell | -2.737 |
illin | -2.730 |
ctrl | -2.707 |
ente | -2.690 |
Token | view |
Token ID | 1570 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
.? | +0.627 |
verty | +0.542 |
numbered | +0.537 |
BLE | +0.532 |
ounty | +0.524 |
Neg logit contributions | |
xual | -0.571 |
fell | -0.546 |
Salman | -0.546 |
ctrl | -0.545 |
illin | -0.539 |
Token | of |
Token ID | 286 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
.? | +3.736 |
verty | +3.179 |
BLE | +3.107 |
numbered | +3.096 |
ounty | +3.050 |
Neg logit contributions | |
xual | -3.817 |
illin | -3.689 |
fell | -3.689 |
ctrl | -3.674 |
Collider | -3.627 |
Token | 't |
Token ID | 470 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
xual | +0.646 |
Salman | +0.623 |
fell | +0.622 |
ctrl | +0.620 |
illin | +0.613 |
Neg logit contributions | |
.? | -0.631 |
verty | -0.540 |
numbered | -0.538 |
BLE | -0.531 |
ounty | -0.523 |
Token | have |
Token ID | 423 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
.? | +0.412 |
numbered | +0.350 |
verty | +0.349 |
BLE | +0.345 |
ounty | +0.340 |
Neg logit contributions | |
xual | -0.415 |
Salman | -0.400 |
fell | -0.398 |
ctrl | -0.398 |
illin | -0.394 |
Token | any |
Token ID | 597 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
.? | +0.759 |
verty | +0.650 |
numbered | +0.648 |
BLE | +0.645 |
ounty | +0.633 |
Neg logit contributions | |
xual | -0.673 |
Salman | -0.643 |
fell | -0.642 |
ctrl | -0.639 |
ente | -0.634 |
Token | items |
Token ID | 3709 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
.? | +1.135 |
verty | +0.954 |
numbered | +0.946 |
BLE | +0.942 |
ounty | +0.923 |
Neg logit contributions | |
xual | -1.205 |
Salman | -1.156 |
fell | -1.156 |
ctrl | -1.148 |
ente | -1.141 |
Token | out |
Token ID | 503 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
xual | +0.903 |
Salman | +0.869 |
fell | +0.865 |
ctrl | +0.862 |
ente | +0.853 |
Neg logit contributions | |
.? | -1.070 |
verty | -0.931 |
numbered | -0.931 |
BLE | -0.920 |
ounty | -0.906 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+01 |
Pos logit contributions | |
xual | +0.455 |
Salman | +0.437 |
fell | +0.436 |
ctrl | +0.435 |
ente | +0.429 |
Neg logit contributions | |
.? | -0.576 |
verty | -0.503 |
numbered | -0.500 |
BLE | -0.497 |
ounty | -0.489 |
Token | mid |
Token ID | 3095 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
.? | +7.590 |
verty | +6.450 |
numbered | +6.322 |
bleed | +6.298 |
antiquity | +6.231 |
Neg logit contributions | |
xual | -9.050 |
illin | -8.508 |
ailable | -8.335 |
ctrl | -8.325 |
Salman | -8.291 |
Token | as |
Token ID | 292 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
.? | +0.235 |
verty | +0.202 |
numbered | +0.202 |
BLE | +0.199 |
ounty | +0.196 |
Neg logit contributions | |
xual | -0.213 |
Salman | -0.204 |
fell | -0.203 |
ctrl | -0.203 |
illin | -0.201 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
.? | +3.045 |
verty | +2.586 |
numbered | +2.583 |
BLE | +2.548 |
ounty | +2.527 |
Neg logit contributions | |
xual | -2.564 |
Salman | -2.458 |
fell | -2.436 |
ctrl | -2.414 |
Collider | -2.402 |
Token | brown |
Token ID | 7586 |
Feature activation | +7.39e+00 |
Pos logit contributions | |
.? | +1.241 |
verty | +1.061 |
numbered | +1.054 |
BLE | +1.046 |
ounty | +1.032 |
Neg logit contributions | |
xual | -1.154 |
fell | -1.102 |
Salman | -1.102 |
ctrl | -1.096 |
illin | -1.090 |
Token | boots |
Token ID | 14412 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
.? | +5.654 |
numbered | +4.828 |
verty | +4.815 |
bleed | +4.762 |
ounty | +4.740 |
Neg logit contributions | |
xual | -4.905 |
Salman | -4.708 |
Collider | -4.683 |
ctrl | -4.662 |
ailable | -4.605 |
Token | of |
Token ID | 286 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
.? | +0.664 |
numbered | +0.555 |
verty | +0.554 |
BLE | +0.546 |
ounty | +0.536 |
Neg logit contributions | |
xual | -0.803 |
Salman | -0.773 |
fell | -0.772 |
ctrl | -0.771 |
illin | -0.764 |
Token | returning |
Token ID | 8024 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
.? | +0.945 |
verty | +0.809 |
numbered | +0.808 |
BLE | +0.799 |
ounty | +0.787 |
Neg logit contributions | |
xual | -0.887 |
ctrl | -0.849 |
fell | -0.849 |
Salman | -0.846 |
illin | -0.839 |
Token | citizens |
Token ID | 4290 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
xual | +0.619 |
Salman | +0.596 |
fell | +0.593 |
ctrl | +0.590 |
illin | +0.583 |
Neg logit contributions | |
.? | -0.745 |
verty | -0.647 |
numbered | -0.646 |
BLE | -0.637 |
ounty | -0.628 |
Token | � |
Token ID | 447 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
xual | +0.851 |
Salman | +0.817 |
fell | +0.813 |
ctrl | +0.810 |
illin | +0.802 |
Neg logit contributions | |
.? | -1.024 |
verty | -0.887 |
numbered | -0.886 |
BLE | -0.876 |
ounty | -0.863 |
Token | � |
Token ID | 247 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
.? | +0.304 |
verty | +0.261 |
numbered | +0.260 |
BLE | +0.257 |
ounty | +0.253 |
Neg logit contributions | |
xual | -0.283 |
Salman | -0.272 |
fell | -0.272 |
ctrl | -0.271 |
illin | -0.268 |
Token | phone |
Token ID | 3072 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
.? | +0.839 |
numbered | +0.726 |
verty | +0.725 |
BLE | +0.718 |
ounty | +0.709 |
Neg logit contributions | |
xual | -0.690 |
Salman | -0.669 |
ctrl | -0.665 |
Collider | -0.660 |
fell | -0.659 |
Token | calls |
Token ID | 3848 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
.? | +0.726 |
numbered | +0.623 |
verty | +0.620 |
BLE | +0.615 |
ounty | +0.604 |
Neg logit contributions | |
xual | -0.689 |
ctrl | -0.661 |
Salman | -0.660 |
fell | -0.655 |
ente | -0.651 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
.? | +0.951 |
numbered | +0.816 |
verty | +0.815 |
BLE | +0.804 |
ounty | +0.793 |
Neg logit contributions | |
xual | -0.811 |
ctrl | -0.779 |
fell | -0.775 |
Salman | -0.774 |
illin | -0.766 |
Token | After |
Token ID | 2293 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
xual | +0.782 |
Salman | +0.752 |
fell | +0.748 |
ctrl | +0.746 |
illin | +0.738 |
Neg logit contributions | |
.? | -0.921 |
verty | -0.797 |
numbered | -0.796 |
BLE | -0.787 |
ounty | -0.775 |
Token | a |
Token ID | 257 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
xual | +2.856 |
Salman | +2.810 |
fell | +2.772 |
ente | +2.736 |
ctrl | +2.721 |
Neg logit contributions | |
.? | -3.038 |
verty | -2.630 |
numbered | -2.625 |
BLE | -2.585 |
ounty | -2.557 |
Token | teacher |
Token ID | 4701 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
xual | +1.515 |
Salman | +1.473 |
fell | +1.464 |
ctrl | +1.454 |
ente | +1.443 |
Neg logit contributions | |
.? | -1.544 |
verty | -1.328 |
numbered | -1.325 |
BLE | -1.308 |
ounty | -1.294 |
Token | supporter |
Token ID | 15525 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
.? | +2.804 |
numbered | +2.435 |
verty | +2.362 |
bleed | +2.325 |
BLE | +2.321 |
Neg logit contributions | |
xual | -3.157 |
illin | -3.032 |
Salman | -2.966 |
ctrl | -2.953 |
fell | -2.893 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
.? | +3.543 |
numbered | +2.940 |
verty | +2.935 |
BLE | +2.868 |
ANA | +2.808 |
Neg logit contributions | |
xual | -3.247 |
illin | -3.096 |
ente | -3.050 |
fell | -3.009 |
Salman | -2.959 |
Token | Powered |
Token ID | 45090 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
.? | +0.635 |
numbered | +0.514 |
verty | +0.505 |
BLE | +0.493 |
ounty | +0.475 |
Neg logit contributions | |
xual | -1.154 |
ctrl | -1.101 |
fell | -1.100 |
illin | -1.098 |
ente | -1.090 |
Token | by |
Token ID | 416 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
xual | +1.260 |
Salman | +1.201 |
ctrl | +1.194 |
fell | +1.192 |
illin | +1.182 |
Neg logit contributions | |
.? | -1.949 |
numbered | -1.708 |
verty | -1.708 |
BLE | -1.691 |
ounty | -1.670 |
Token | Press |
Token ID | 4332 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
.? | +0.431 |
numbered | +0.376 |
verty | +0.376 |
BLE | +0.372 |
ounty | +0.366 |
Neg logit contributions | |
xual | -0.353 |
Salman | -0.343 |
fell | -0.340 |
ctrl | -0.337 |
ente | -0.335 |
Token | Pat |
Token ID | 12130 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
.? | +0.800 |
BLE | +0.657 |
numbered | +0.654 |
verty | +0.654 |
ounty | +0.640 |
Neg logit contributions | |
xual | -1.148 |
fell | -1.091 |
Salman | -1.088 |
ente | -1.088 |
ctrl | -1.080 |
Token | ron |
Token ID | 1313 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
.? | +2.797 |
verty | +2.503 |
numbered | +2.490 |
BLE | +2.479 |
ounty | +2.453 |
Neg logit contributions | |
xual | -0.955 |
ctrl | -0.859 |
illin | -0.838 |
fell | -0.838 |
Salman | -0.832 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
Salman | +4.141 |
Collider | +4.039 |
xual | +3.924 |
ctrl | +3.860 |
ente | +3.791 |
Neg logit contributions | |
.? | -5.955 |
numbered | -5.485 |
BLE | -5.478 |
verty | -5.470 |
UGE | -5.323 |
Token | Washington |
Token ID | 17402 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
xual | +2.378 |
fell | +2.361 |
ctrl | +2.350 |
Salman | +2.330 |
ente | +2.301 |
Neg logit contributions | |
.? | -2.676 |
verty | -2.315 |
numbered | -2.288 |
ounty | -2.238 |
BLE | -2.237 |
Token | Post |
Token ID | 2947 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
xual | +1.388 |
Salman | +1.336 |
fell | +1.328 |
ctrl | +1.323 |
ente | +1.311 |
Neg logit contributions | |
.? | -1.956 |
numbered | -1.715 |
verty | -1.712 |
BLE | -1.693 |
ounty | -1.670 |
Token | columnist |
Token ID | 22309 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
xual | +0.010 |
Salman | +0.010 |
fell | +0.010 |
ctrl | +0.010 |
illin | +0.010 |
Neg logit contributions | |
.? | -0.013 |
verty | -0.011 |
numbered | -0.011 |
BLE | -0.011 |
ounty | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
xual | +0.387 |
Salman | +0.371 |
fell | +0.369 |
ctrl | +0.368 |
illin | +0.364 |
Neg logit contributions | |
.? | -0.464 |
verty | -0.402 |
numbered | -0.402 |
BLE | -0.397 |
ounty | -0.391 |
Token | the |
Token ID | 262 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
.? | +0.914 |
verty | +0.779 |
numbered | +0.777 |
BLE | +0.766 |
ounty | +0.757 |
Neg logit contributions | |
xual | -0.911 |
ctrl | -0.871 |
fell | -0.869 |
Salman | -0.867 |
illin | -0.863 |
Token | J |
Token ID | 449 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
.? | +0.131 |
verty | +0.110 |
numbered | +0.110 |
BLE | +0.109 |
ounty | +0.107 |
Neg logit contributions | |
xual | -0.147 |
Salman | -0.142 |
fell | -0.142 |
ctrl | -0.141 |
illin | -0.140 |
Token | at |
Token ID | 265 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
xual | +2.601 |
att | +2.552 |
Salman | +2.529 |
fell | +2.522 |
ente | +2.515 |
Neg logit contributions | |
.? | -4.404 |
numbered | -3.965 |
verty | -3.932 |
BLE | -3.921 |
ounty | -3.831 |
Token | reservation |
Token ID | 24048 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
.? | +1.238 |
verty | +1.029 |
numbered | +1.019 |
BLE | +1.007 |
ounty | +1.001 |
Neg logit contributions | |
xual | -1.488 |
ctrl | -1.432 |
fell | -1.422 |
illin | -1.420 |
Salman | -1.419 |
Token | movement |
Token ID | 3356 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
.? | +2.507 |
numbered | +2.122 |
verty | +2.121 |
BLE | +2.084 |
ounty | +2.068 |
Neg logit contributions | |
xual | -2.161 |
ctrl | -2.068 |
Collider | -2.052 |
illin | -2.050 |
Salman | -2.049 |
Token | � |
Token ID | 447 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
.? | +1.201 |
verty | +1.028 |
numbered | +1.028 |
BLE | +1.017 |
ounty | +1.000 |
Neg logit contributions | |
xual | -0.997 |
ctrl | -0.948 |
Salman | -0.948 |
fell | -0.944 |
illin | -0.938 |
Token | � |
Token ID | 251 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
.? | +1.237 |
verty | +1.015 |
BLE | +0.990 |
numbered | +0.985 |
ounty | +0.967 |
Neg logit contributions | |
xual | -1.873 |
ctrl | -1.815 |
Salman | -1.802 |
illin | -1.794 |
fell | -1.791 |
Token | , |
Token ID | 11 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
.? | +0.242 |
verty | +0.210 |
numbered | +0.210 |
BLE | +0.208 |
ounty | +0.205 |
Neg logit contributions | |
xual | -0.180 |
ctrl | -0.171 |
Salman | -0.170 |
fell | -0.170 |
illin | -0.168 |
Token | it |
Token ID | 340 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
xual | +0.615 |
Salman | +0.595 |
fell | +0.592 |
ctrl | +0.590 |
ente | +0.584 |
Neg logit contributions | |
.? | -0.573 |
verty | -0.486 |
numbered | -0.486 |
BLE | -0.479 |
ounty | -0.471 |
Token | reads |
Token ID | 9743 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
xual | +0.318 |
Salman | +0.306 |
fell | +0.305 |
ctrl | +0.305 |
illin | +0.302 |
Neg logit contributions | |
.? | -0.285 |
verty | -0.241 |
numbered | -0.240 |
BLE | -0.237 |
ounty | -0.233 |
Token | 80 |
Token ID | 4019 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
xual | +1.179 |
Salman | +1.133 |
ctrl | +1.131 |
fell | +1.126 |
ente | +1.113 |
Neg logit contributions | |
.? | -1.306 |
numbered | -1.129 |
verty | -1.126 |
BLE | -1.104 |
ounty | -1.096 |
Token | ) |
Token ID | 8 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
.? | +0.345 |
verty | +0.296 |
numbered | +0.295 |
BLE | +0.293 |
ounty | +0.288 |
Neg logit contributions | |
xual | -0.305 |
Salman | -0.293 |
fell | -0.292 |
ctrl | -0.290 |
illin | -0.289 |
Token |
|
Token ID | 198 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
.? | +3.526 |
BLE | +3.024 |
verty | +3.019 |
numbered | +2.998 |
bleed | +2.910 |
Neg logit contributions | |
xual | -3.247 |
illin | -3.110 |
fell | -3.089 |
ctrl | -3.079 |
Salman | -3.053 |
Token |
|
Token ID | 198 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
.? | +0.964 |
numbered | +0.821 |
BLE | +0.814 |
verty | +0.801 |
ounty | +0.791 |
Neg logit contributions | |
xual | -0.868 |
illin | -0.802 |
Collider | -0.802 |
Salman | -0.801 |
ctrl | -0.800 |
Token | 27 |
Token ID | 1983 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
.? | +0.649 |
verty | +0.558 |
numbered | +0.557 |
BLE | +0.555 |
ounty | +0.542 |
Neg logit contributions | |
xual | -0.590 |
Salman | -0.564 |
fell | -0.558 |
illin | -0.557 |
ctrl | -0.556 |
Token | " |
Token ID | 366 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
xual | +0.871 |
Salman | +0.838 |
fell | +0.834 |
ctrl | +0.831 |
ente | +0.823 |
Neg logit contributions | |
.? | -1.028 |
numbered | -0.892 |
verty | -0.891 |
BLE | -0.879 |
ounty | -0.868 |
Token | 4 |
Token ID | 604 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
.? | +0.617 |
verty | +0.530 |
numbered | +0.527 |
BLE | +0.524 |
ounty | +0.513 |
Neg logit contributions | |
xual | -0.588 |
Salman | -0.563 |
fell | -0.562 |
ctrl | -0.559 |
illin | -0.557 |
Token | ms |
Token ID | 907 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
xual | +0.759 |
Salman | +0.729 |
fell | +0.725 |
ctrl | +0.723 |
ente | +0.715 |
Neg logit contributions | |
.? | -0.942 |
verty | -0.819 |
numbered | -0.819 |
BLE | -0.808 |
ounty | -0.797 |
Token | G |
Token ID | 402 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
.? | +1.399 |
verty | +1.157 |
BLE | +1.152 |
numbered | +1.149 |
ounty | +1.112 |
Neg logit contributions | |
xual | -1.741 |
fell | -1.671 |
Salman | -1.668 |
illin | -1.663 |
ctrl | -1.659 |
Token | 2 |
Token ID | 17 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
xual | +0.248 |
Salman | +0.239 |
fell | +0.238 |
ctrl | +0.237 |
illin | +0.235 |
Neg logit contributions | |
.? | -0.219 |
numbered | -0.184 |
verty | -0.184 |
BLE | -0.183 |
ounty | -0.179 |
Token | G |
Token ID | 38 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
.? | +2.024 |
BLE | +1.522 |
ANA | +1.395 |
numbered | +1.326 |
verty | +1.246 |
Neg logit contributions | |
xual | -5.709 |
ente | -5.411 |
illin | -5.391 |
ailable | -5.388 |
Salman | -5.377 |
Token | impact |
Token ID | 2928 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
.? | +1.838 |
numbered | +1.568 |
verty | +1.568 |
BLE | +1.539 |
ounty | +1.510 |
Neg logit contributions | |
xual | -1.886 |
Salman | -1.789 |
fell | -1.788 |
illin | -1.777 |
ctrl | -1.775 |
Token | point |
Token ID | 966 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
.? | +2.339 |
numbered | +1.998 |
verty | +1.983 |
BLE | +1.966 |
ounty | +1.931 |
Neg logit contributions | |
xual | -2.391 |
Salman | -2.273 |
fell | -2.263 |
ctrl | -2.255 |
illin | -2.233 |
Token | would |
Token ID | 561 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
xual | +0.822 |
Salman | +0.789 |
fell | +0.786 |
ctrl | +0.784 |
ente | +0.774 |
Neg logit contributions | |
.? | -1.034 |
verty | -0.899 |
numbered | -0.896 |
BLE | -0.887 |
ounty | -0.875 |
Token | have |
Token ID | 423 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
.? | +2.112 |
numbered | +1.816 |
verty | +1.780 |
BLE | +1.763 |
bleed | +1.751 |
Neg logit contributions | |
xual | -2.081 |
Salman | -1.994 |
illin | -1.974 |
ctrl | -1.959 |
fell | -1.952 |
Token | the |
Token ID | 262 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
.? | +2.703 |
numbered | +2.321 |
verty | +2.301 |
BLE | +2.260 |
ANA | +2.213 |
Neg logit contributions | |
xual | -2.786 |
illin | -2.623 |
Salman | -2.618 |
ctrl | -2.616 |
ente | -2.595 |
Token | optimum |
Token ID | 39475 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
.? | +4.746 |
numbered | +3.954 |
verty | +3.920 |
bleed | +3.861 |
BLE | +3.810 |
Neg logit contributions | |
xual | -5.347 |
illin | -5.022 |
Salman | -4.981 |
fell | -4.968 |
ctrl | -4.928 |
Token | lighting |
Token ID | 12019 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
.? | +4.096 |
numbered | +3.430 |
verty | +3.404 |
bleed | +3.385 |
BLE | +3.342 |
Neg logit contributions | |
xual | -4.637 |
illin | -4.351 |
fell | -4.350 |
Salman | -4.307 |
ctrl | -4.305 |
Token | conditions |
Token ID | 3403 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
xual | +1.009 |
Salman | +0.977 |
fell | +0.974 |
ctrl | +0.969 |
ente | +0.958 |
Neg logit contributions | |
.? | -1.023 |
verty | -0.885 |
numbered | -0.880 |
BLE | -0.871 |
ounty | -0.860 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
.? | +0.150 |
verty | +0.129 |
numbered | +0.129 |
BLE | +0.128 |
ounty | +0.126 |
Neg logit contributions | |
xual | -0.122 |
Salman | -0.116 |
fell | -0.116 |
ctrl | -0.116 |
illin | -0.115 |
Token | About |
Token ID | 7994 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
xual | +0.267 |
Salman | +0.256 |
fell | +0.255 |
ctrl | +0.255 |
illin | +0.252 |
Neg logit contributions | |
.? | -0.294 |
verty | -0.253 |
numbered | -0.253 |
BLE | -0.250 |
ounty | -0.245 |
Token | one |
Token ID | 530 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
.? | +0.331 |
numbered | +0.280 |
verty | +0.278 |
BLE | +0.275 |
ounty | +0.270 |
Neg logit contributions | |
xual | -0.367 |
Salman | -0.350 |
fell | -0.350 |
ctrl | -0.349 |
illin | -0.347 |
Token | Mer |
Token ID | 4638 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
.? | +1.373 |
numbered | +1.176 |
verty | +1.172 |
BLE | +1.152 |
ounty | +1.144 |
Neg logit contributions | |
xual | -1.217 |
ctrl | -1.134 |
fell | -1.132 |
Salman | -1.125 |
illin | -1.113 |
Token | ica |
Token ID | 3970 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
xual | +1.272 |
fell | +1.221 |
Salman | +1.220 |
ente | +1.215 |
illin | +1.212 |
Neg logit contributions | |
.? | -3.237 |
verty | -2.949 |
numbered | -2.904 |
BLE | -2.888 |
ounty | -2.859 |
Token | (@ |
Token ID | 4275 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
.? | +2.892 |
verty | +2.532 |
BLE | +2.518 |
numbered | +2.504 |
ounty | +2.471 |
Neg logit contributions | |
xual | -1.898 |
fell | -1.776 |
ctrl | -1.775 |
ente | -1.747 |
Salman | -1.745 |
Token | dan |
Token ID | 25604 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
.? | +1.029 |
numbered | +0.884 |
verty | +0.874 |
BLE | +0.872 |
ounty | +0.860 |
Neg logit contributions | |
xual | -1.011 |
Salman | -0.969 |
ctrl | -0.952 |
fell | -0.948 |
illin | -0.947 |
Token | meric |
Token ID | 946 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
xual | +0.056 |
Salman | +0.054 |
fell | +0.054 |
ctrl | +0.054 |
Collider | +0.054 |
Neg logit contributions | |
.? | -0.054 |
numbered | -0.046 |
verty | -0.046 |
BLE | -0.045 |
ounty | -0.044 |
Token | a |
Token ID | 64 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
xual | +0.171 |
Salman | +0.164 |
fell | +0.164 |
ctrl | +0.163 |
illin | +0.161 |
Neg logit contributions | |
.? | -0.172 |
verty | -0.147 |
numbered | -0.147 |
BLE | -0.144 |
ounty | -0.143 |
Token | CNN |
Token ID | 18474 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
xual | +0.785 |
Salman | +0.756 |
fell | +0.752 |
ctrl | +0.751 |
illin | +0.740 |
Neg logit contributions | |
.? | -1.182 |
verty | -1.033 |
numbered | -1.033 |
BLE | -1.018 |
ounty | -1.005 |
Token | ) |
Token ID | 8 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
xual | +0.817 |
Salman | +0.777 |
fell | +0.774 |
ctrl | +0.769 |
ente | +0.756 |
Neg logit contributions | |
.? | -1.658 |
verty | -1.481 |
numbered | -1.476 |
BLE | -1.460 |
ounty | -1.445 |
Token | October |
Token ID | 3267 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
xual | +0.798 |
Salman | +0.774 |
fell | +0.765 |
ctrl | +0.762 |
Collider | +0.753 |
Neg logit contributions | |
.? | -1.169 |
verty | -1.035 |
numbered | -1.033 |
BLE | -1.020 |
ounty | -1.008 |
Token | 23 |
Token ID | 2242 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Salman | +2.834 |
fell | +2.761 |
xual | +2.755 |
ctrl | +2.704 |
Collider | +2.690 |
Neg logit contributions | |
.? | -4.037 |
verty | -3.702 |
ounty | -3.628 |
numbered | -3.618 |
BLE | -3.571 |
Token | , |
Token ID | 11 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
xual | +1.188 |
Salman | +1.141 |
fell | +1.135 |
ctrl | +1.128 |
ente | +1.111 |
Neg logit contributions | |
.? | -1.912 |
verty | -1.691 |
numbered | -1.688 |
BLE | -1.671 |
ounty | -1.651 |
Token | over |
Token ID | 625 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
.? | +0.400 |
numbered | +0.339 |
verty | +0.338 |
BLE | +0.335 |
ounty | +0.330 |
Neg logit contributions | |
xual | -0.408 |
ctrl | -0.392 |
Salman | -0.391 |
fell | -0.390 |
illin | -0.389 |
Token | 265 |
Token ID | 32090 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
xual | +1.691 |
Salman | +1.635 |
fell | +1.632 |
ctrl | +1.619 |
illin | +1.598 |
Neg logit contributions | |
.? | -1.847 |
verty | -1.600 |
numbered | -1.587 |
BLE | -1.570 |
ounty | -1.544 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
xual | +2.035 |
Salman | +1.940 |
fell | +1.932 |
ente | +1.895 |
ctrl | +1.889 |
Neg logit contributions | |
.? | -3.268 |
numbered | -2.920 |
verty | -2.918 |
BLE | -2.860 |
ounty | -2.816 |
Token | 000 |
Token ID | 830 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
xual | +1.296 |
Salman | +1.234 |
fell | +1.231 |
ctrl | +1.223 |
ente | +1.211 |
Neg logit contributions | |
.? | -1.875 |
verty | -1.654 |
numbered | -1.645 |
BLE | -1.626 |
ounty | -1.596 |
Token | complaints |
Token ID | 9687 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
xual | +0.901 |
Salman | +0.866 |
fell | +0.863 |
ctrl | +0.856 |
ente | +0.849 |
Neg logit contributions | |
.? | -1.110 |
verty | -0.969 |
numbered | -0.966 |
BLE | -0.952 |
ounty | -0.940 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
xual | +0.777 |
Salman | +0.751 |
fell | +0.746 |
ctrl | +0.742 |
ente | +0.736 |
Neg logit contributions | |
.? | -0.757 |
verty | -0.652 |
numbered | -0.649 |
BLE | -0.641 |
ounty | -0.630 |
Token | Bank |
Token ID | 5018 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
xual | +0.928 |
Salman | +0.899 |
fell | +0.894 |
ctrl | +0.887 |
Collider | +0.878 |
Neg logit contributions | |
.? | -1.125 |
verty | -0.979 |
numbered | -0.976 |
BLE | -0.963 |
ounty | -0.952 |
Token | of |
Token ID | 286 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
.? | +1.307 |
numbered | +1.118 |
verty | +1.116 |
BLE | +1.106 |
ounty | +1.091 |
Neg logit contributions | |
xual | -1.187 |
Salman | -1.130 |
ctrl | -1.128 |
fell | -1.121 |
illin | -1.116 |
Token | America |
Token ID | 2253 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
xual | +1.340 |
Salman | +1.331 |
fell | +1.306 |
ctrl | +1.298 |
Collider | +1.290 |
Neg logit contributions | |
.? | -1.527 |
verty | -1.330 |
numbered | -1.320 |
BLE | -1.311 |
ounty | -1.288 |
Token | earned |
Token ID | 7366 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
xual | +1.892 |
Salman | +1.833 |
fell | +1.830 |
ctrl | +1.807 |
Collider | +1.791 |
Neg logit contributions | |
.? | -2.404 |
numbered | -2.111 |
verty | -2.111 |
BLE | -2.082 |
ounty | -2.061 |
Token | 38 |
Token ID | 4353 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
Salman | +3.626 |
xual | +3.600 |
fell | +3.546 |
att | +3.474 |
Collider | +3.472 |
Neg logit contributions | |
.? | -4.452 |
numbered | -3.971 |
verty | -3.907 |
BLE | -3.850 |
ounty | -3.796 |
Token | exaggerated |
Token ID | 25291 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
xual | +2.539 |
Salman | +2.501 |
ente | +2.464 |
ctrl | +2.459 |
fell | +2.444 |
Neg logit contributions | |
.? | -2.802 |
verty | -2.475 |
numbered | -2.462 |
ounty | -2.417 |
BLE | -2.380 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
xual | +2.789 |
Salman | +2.699 |
ctrl | +2.660 |
fell | +2.650 |
ente | +2.627 |
Neg logit contributions | |
.? | -3.493 |
verty | -3.093 |
numbered | -3.057 |
ounty | -3.010 |
BLE | -2.992 |
Token | Like |
Token ID | 4525 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
.? | +0.104 |
numbered | +0.090 |
verty | +0.090 |
BLE | +0.089 |
ounty | +0.087 |
Neg logit contributions | |
xual | -0.089 |
Salman | -0.085 |
ctrl | -0.085 |
fell | -0.085 |
illin | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
xual | +0.868 |
Salman | +0.839 |
fell | +0.830 |
ctrl | +0.829 |
ente | +0.821 |
Neg logit contributions | |
.? | -1.028 |
verty | -0.893 |
numbered | -0.891 |
BLE | -0.880 |
ounty | -0.867 |
Token | I |
Token ID | 314 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
xual | +0.397 |
Salman | +0.382 |
fell | +0.380 |
ctrl | +0.379 |
illin | +0.375 |
Neg logit contributions | |
.? | -0.460 |
verty | -0.398 |
numbered | -0.397 |
BLE | -0.392 |
ounty | -0.387 |
Token | say |
Token ID | 910 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
.? | +0.359 |
verty | +0.305 |
numbered | +0.305 |
BLE | +0.302 |
ounty | +0.296 |
Neg logit contributions | |
xual | -0.345 |
Salman | -0.331 |
ctrl | -0.329 |
fell | -0.329 |
illin | -0.326 |
Token | yeah |
Token ID | 10194 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
xual | +0.631 |
Salman | +0.604 |
fell | +0.602 |
ctrl | +0.600 |
illin | +0.593 |
Neg logit contributions | |
.? | -0.782 |
verty | -0.678 |
numbered | -0.677 |
BLE | -0.670 |
ounty | -0.660 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
.? | +0.452 |
verty | +0.391 |
numbered | +0.391 |
BLE | +0.389 |
ounty | +0.382 |
Neg logit contributions | |
xual | -0.331 |
Salman | -0.315 |
fell | -0.315 |
ctrl | -0.313 |
illin | -0.311 |
Token | they |
Token ID | 484 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
.? | +1.100 |
verty | +0.946 |
numbered | +0.946 |
BLE | +0.943 |
ounty | +0.922 |
Neg logit contributions | |
xual | -0.926 |
fell | -0.882 |
Salman | -0.881 |
ctrl | -0.877 |
illin | -0.872 |
Token | might |
Token ID | 1244 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
.? | +0.388 |
verty | +0.331 |
numbered | +0.329 |
BLE | +0.327 |
ounty | +0.320 |
Neg logit contributions | |
xual | -0.379 |
Salman | -0.364 |
ctrl | -0.363 |
fell | -0.362 |
illin | -0.359 |
Token | say |
Token ID | 910 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
.? | +0.025 |
verty | +0.021 |
numbered | +0.021 |
BLE | +0.021 |
ounty | +0.021 |
Neg logit contributions | |
xual | -0.022 |
Salman | -0.022 |
fell | -0.021 |
ctrl | -0.021 |
illin | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
.? | +2.167 |
numbered | +1.861 |
verty | +1.853 |
BLE | +1.843 |
ounty | +1.823 |
Neg logit contributions | |
xual | -1.898 |
Salman | -1.827 |
fell | -1.820 |
ctrl | -1.801 |
illin | -1.798 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
.? | +0.691 |
verty | +0.588 |
numbered | +0.588 |
BLE | +0.582 |
ounty | +0.573 |
Neg logit contributions | |
xual | -0.682 |
Salman | -0.655 |
fell | -0.654 |
ctrl | -0.652 |
illin | -0.648 |
Token | risks |
Token ID | 7476 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
xual | +0.088 |
Salman | +0.085 |
fell | +0.085 |
ctrl | +0.084 |
ente | +0.084 |
Neg logit contributions | |
.? | -0.079 |
verty | -0.067 |
numbered | -0.067 |
BLE | -0.066 |
ounty | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
xual | +1.492 |
Salman | +1.438 |
fell | +1.430 |
ctrl | +1.423 |
ente | +1.410 |
Neg logit contributions | |
.? | -1.485 |
verty | -1.280 |
numbered | -1.277 |
BLE | -1.257 |
ounty | -1.233 |
Token | not |
Token ID | 407 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
xual | +2.129 |
Salman | +2.079 |
ctrl | +2.055 |
fell | +2.045 |
ente | +2.045 |
Neg logit contributions | |
.? | -2.068 |
verty | -1.781 |
numbered | -1.779 |
BLE | -1.736 |
ounty | -1.710 |
Token | deploying |
Token ID | 29682 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
xual | +4.131 |
att | +4.019 |
fell | +4.012 |
Salman | +4.008 |
ctrl | +4.004 |
Neg logit contributions | |
.? | -3.991 |
verty | -3.464 |
numbered | -3.452 |
BLE | -3.373 |
ounty | -3.296 |
Token | them |
Token ID | 606 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
xual | +0.856 |
Salman | +0.824 |
fell | +0.817 |
ctrl | +0.817 |
ente | +0.808 |
Neg logit contributions | |
.? | -1.149 |
verty | -1.008 |
numbered | -1.007 |
BLE | -0.993 |
ounty | -0.980 |
Token | . |
Token ID | 13 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
.? | +0.931 |
numbered | +0.797 |
verty | +0.796 |
BLE | +0.789 |
ounty | +0.777 |
Neg logit contributions | |
xual | -0.771 |
Salman | -0.737 |
fell | -0.734 |
ctrl | -0.729 |
illin | -0.724 |
Token | In |
Token ID | 554 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
xual | +0.463 |
Salman | +0.447 |
fell | +0.445 |
ctrl | +0.444 |
ente | +0.439 |
Neg logit contributions | |
.? | -0.504 |
verty | -0.434 |
numbered | -0.433 |
BLE | -0.427 |
ounty | -0.421 |
Token | Bitcoin |
Token ID | 6185 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
xual | +0.227 |
Salman | +0.218 |
fell | +0.217 |
ctrl | +0.217 |
ente | +0.214 |
Neg logit contributions | |
.? | -0.249 |
verty | -0.214 |
numbered | -0.214 |
BLE | -0.212 |
ounty | -0.208 |
Token | Core |
Token ID | 7231 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
xual | +1.320 |
Salman | +1.270 |
fell | +1.269 |
ctrl | +1.260 |
ente | +1.250 |
Neg logit contributions | |
.? | -1.548 |
numbered | -1.342 |
verty | -1.336 |
BLE | -1.322 |
ounty | -1.302 |
Token | C |
Token ID | 34 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
xual | +0.674 |
Salman | +0.649 |
fell | +0.648 |
ctrl | +0.646 |
ente | +0.639 |
Neg logit contributions | |
.? | -0.701 |
verty | -0.600 |
numbered | -0.599 |
BLE | -0.592 |
ounty | -0.583 |
Token | ameron |
Token ID | 41639 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
.? | +4.079 |
numbered | +3.620 |
verty | +3.615 |
BLE | +3.601 |
ounty | +3.578 |
Neg logit contributions | |
xual | -1.959 |
Salman | -1.829 |
Collider | -1.823 |
ctrl | -1.818 |
fell | -1.777 |
Token | is |
Token ID | 318 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
xual | +3.428 |
fell | +3.412 |
Salman | +3.407 |
ente | +3.308 |
ctrl | +3.283 |
Neg logit contributions | |
.? | -4.160 |
numbered | -3.628 |
verty | -3.613 |
BLE | -3.600 |
ounty | -3.557 |
Token | deeply |
Token ID | 7744 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
.? | +0.517 |
numbered | +0.442 |
verty | +0.442 |
BLE | +0.437 |
ounty | +0.428 |
Neg logit contributions | |
xual | -0.498 |
ctrl | -0.471 |
fell | -0.469 |
Salman | -0.468 |
illin | -0.467 |
Token | wary |
Token ID | 23300 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
.? | +1.009 |
numbered | +0.815 |
verty | +0.814 |
BLE | +0.806 |
ounty | +0.773 |
Neg logit contributions | |
xual | -1.731 |
ctrl | -1.662 |
Collider | -1.641 |
illin | -1.635 |
Salman | -1.627 |
Token | of |
Token ID | 286 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
.? | +1.828 |
numbered | +1.558 |
verty | +1.553 |
BLE | +1.546 |
ounty | +1.508 |
Neg logit contributions | |
xual | -1.748 |
ctrl | -1.673 |
fell | -1.670 |
illin | -1.666 |
Salman | -1.656 |
Token | Jun |
Token ID | 7653 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
xual | +0.663 |
Salman | +0.639 |
fell | +0.636 |
ctrl | +0.634 |
ente | +0.627 |
Neg logit contributions | |
.? | -0.728 |
verty | -0.627 |
numbered | -0.626 |
BLE | -0.619 |
ounty | -0.609 |
Token | cker |
Token ID | 15280 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
xual | +0.230 |
Salman | +0.216 |
fell | +0.213 |
ctrl | +0.213 |
illin | +0.209 |
Neg logit contributions | |
.? | -0.555 |
verty | -0.497 |
numbered | -0.497 |
BLE | -0.493 |
ounty | -0.488 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
.? | +0.165 |
verty | +0.143 |
numbered | +0.142 |
BLE | +0.141 |
ounty | +0.138 |
Neg logit contributions | |
xual | -0.141 |
Salman | -0.135 |
ctrl | -0.135 |
fell | -0.135 |
illin | -0.133 |
Token | an |
Token ID | 281 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
.? | +1.027 |
verty | +0.881 |
numbered | +0.876 |
BLE | +0.867 |
ounty | +0.851 |
Neg logit contributions | |
xual | -0.984 |
ctrl | -0.940 |
fell | -0.937 |
illin | -0.934 |
Salman | -0.933 |
Token | EU |
Token ID | 4576 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
.? | +0.028 |
verty | +0.024 |
numbered | +0.024 |
BLE | +0.024 |
ounty | +0.023 |
Neg logit contributions | |
xual | -0.028 |
Salman | -0.027 |
fell | -0.027 |
ente | -0.027 |
ctrl | -0.027 |
Token | outgoing |
Token ID | 28181 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
.? | +3.641 |
verty | +3.021 |
BLE | +2.988 |
numbered | +2.948 |
bleed | +2.927 |
Neg logit contributions | |
xual | -4.367 |
fell | -4.155 |
ctrl | -4.154 |
illin | -4.142 |
ailable | -4.101 |
Token | and |
Token ID | 290 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
.? | +0.734 |
verty | +0.632 |
numbered | +0.631 |
BLE | +0.625 |
ounty | +0.613 |
Neg logit contributions | |
xual | -0.624 |
Salman | -0.598 |
fell | -0.597 |
ctrl | -0.595 |
illin | -0.589 |
Token | is |
Token ID | 318 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
.? | +1.026 |
verty | +0.875 |
numbered | +0.868 |
BLE | +0.862 |
ounty | +0.844 |
Neg logit contributions | |
xual | -1.036 |
fell | -0.993 |
ctrl | -0.989 |
Salman | -0.985 |
illin | -0.983 |
Token | a |
Token ID | 257 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
xual | +0.774 |
Salman | +0.755 |
fell | +0.745 |
ctrl | +0.740 |
ente | +0.738 |
Neg logit contributions | |
.? | -0.819 |
numbered | -0.705 |
verty | -0.702 |
BLE | -0.693 |
ounty | -0.684 |
Token | good |
Token ID | 922 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
xual | +0.226 |
Salman | +0.217 |
fell | +0.217 |
ctrl | +0.216 |
illin | +0.214 |
Neg logit contributions | |
.? | -0.228 |
verty | -0.195 |
numbered | -0.194 |
BLE | -0.192 |
ounty | -0.189 |
Token | conversation |
Token ID | 5273 |
Feature activation | -9.93e+00 |
Pos logit contributions | |
xual | +0.202 |
Salman | +0.193 |
ctrl | +0.193 |
fell | +0.192 |
illin | +0.190 |
Neg logit contributions | |
.? | -0.216 |
verty | -0.186 |
numbered | -0.185 |
BLE | -0.183 |
ounty | -0.180 |
Token | starter |
Token ID | 14217 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
ente | +5.955 |
att | +5.863 |
Salman | +5.840 |
ctrl | +5.822 |
xual | +5.795 |
Neg logit contributions | |
.? | -7.616 |
verty | -7.028 |
numbered | -6.987 |
ounty | -6.907 |
BLE | -6.587 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
.? | +0.373 |
verty | +0.322 |
numbered | +0.322 |
BLE | +0.319 |
ounty | +0.313 |
Neg logit contributions | |
xual | -0.295 |
Salman | -0.283 |
fell | -0.282 |
ctrl | -0.282 |
illin | -0.278 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
.? | +0.898 |
verty | +0.774 |
numbered | +0.773 |
BLE | +0.768 |
ounty | +0.751 |
Neg logit contributions | |
xual | -0.749 |
fell | -0.712 |
ctrl | -0.711 |
Salman | -0.710 |
illin | -0.701 |
Token | Well |
Token ID | 5779 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
xual | +2.186 |
fell | +2.159 |
ctrl | +2.151 |
Salman | +2.135 |
ente | +2.109 |
Neg logit contributions | |
.? | -2.446 |
verty | -2.115 |
numbered | -2.093 |
BLE | -2.048 |
ounty | -2.045 |
Token | , |
Token ID | 11 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
xual | +0.102 |
Salman | +0.097 |
ctrl | +0.097 |
fell | +0.097 |
illin | +0.096 |
Neg logit contributions | |
.? | -0.132 |
verty | -0.115 |
numbered | -0.115 |
BLE | -0.114 |
ounty | -0.112 |
Token | . |
Token ID | 764 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
.? | +0.363 |
verty | +0.306 |
numbered | +0.306 |
BLE | +0.302 |
ounty | +0.296 |
Neg logit contributions | |
xual | -0.413 |
Salman | -0.399 |
fell | -0.397 |
ctrl | -0.396 |
illin | -0.392 |
Token | pieces |
Token ID | 34154 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
att | +5.313 |
fell | +5.311 |
ctrl | +5.209 |
xual | +5.124 |
ente | +5.069 |
Neg logit contributions | |
.? | -6.621 |
verty | -5.786 |
ounty | -5.714 |
BLE | -5.668 |
ANA | -5.646 |
Token | . |
Token ID | 764 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
xual | +4.317 |
ctrl | +4.182 |
Salman | +4.166 |
att | +4.148 |
Collider | +4.145 |
Neg logit contributions | |
.? | -4.997 |
verty | -4.370 |
BLE | -4.363 |
numbered | -4.327 |
ANA | -4.271 |
Token | clone |
Token ID | 21018 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
xual | +2.297 |
ctrl | +2.224 |
fell | +2.218 |
Salman | +2.210 |
illin | +2.196 |
Neg logit contributions | |
.? | -2.597 |
verty | -2.259 |
numbered | -2.223 |
BLE | -2.221 |
ounty | -2.182 |
Token | (), |
Token ID | 29994 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
.? | +0.718 |
numbered | +0.626 |
verty | +0.623 |
BLE | +0.616 |
ounty | +0.604 |
Neg logit contributions | |
xual | -0.570 |
Salman | -0.549 |
fell | -0.547 |
ctrl | -0.543 |
illin | -0.539 |
Token | half |
Token ID | 2063 |
Feature activation | -8.62e+00 |
Pos logit contributions | |
.? | +0.408 |
verty | +0.347 |
numbered | +0.347 |
BLE | +0.342 |
ounty | +0.337 |
Neg logit contributions | |
xual | -0.424 |
Salman | -0.409 |
fell | -0.407 |
ctrl | -0.406 |
illin | -0.402 |
Token | _ |
Token ID | 62 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
xual | +3.629 |
fell | +3.596 |
ctrl | +3.552 |
Salman | +3.522 |
att | +3.511 |
Neg logit contributions | |
.? | -8.354 |
verty | -7.575 |
BLE | -7.460 |
numbered | -7.409 |
ounty | -7.388 |
Token | m |
Token ID | 76 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
xual | +1.504 |
fell | +1.439 |
ctrl | +1.427 |
Salman | +1.418 |
ente | +1.402 |
Neg logit contributions | |
.? | -2.605 |
verty | -2.316 |
BLE | -2.292 |
numbered | -2.289 |
ounty | -2.257 |
Token | oves |
Token ID | 5241 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
xual | +1.035 |
Salman | +0.983 |
fell | +0.979 |
ctrl | +0.975 |
ente | +0.961 |
Neg logit contributions | |
.? | -1.741 |
verty | -1.539 |
numbered | -1.538 |
BLE | -1.523 |
ounty | -1.503 |
Token | : |
Token ID | 1058 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
xual | +3.050 |
ctrl | +3.015 |
Salman | +3.002 |
fell | +2.997 |
ente | +2.964 |
Neg logit contributions | |
.? | -3.076 |
verty | -2.693 |
numbered | -2.625 |
BLE | -2.619 |
ounty | -2.582 |
Token | self |
Token ID | 2116 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
.? | +1.433 |
verty | +1.188 |
numbered | +1.184 |
BLE | +1.164 |
ounty | +1.134 |
Neg logit contributions | |
xual | -1.865 |
Salman | -1.787 |
fell | -1.774 |
ctrl | -1.774 |
illin | -1.768 |
Token | people |
Token ID | 661 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
xual | +1.553 |
Salman | +1.508 |
fell | +1.504 |
ctrl | +1.496 |
illin | +1.478 |
Neg logit contributions | |
.? | -1.797 |
verty | -1.561 |
numbered | -1.560 |
BLE | -1.540 |
ounty | -1.517 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
xual | +1.139 |
Salman | +1.103 |
fell | +1.099 |
ctrl | +1.091 |
ente | +1.077 |
Neg logit contributions | |
.? | -1.336 |
numbered | -1.165 |
verty | -1.165 |
BLE | -1.151 |
ounty | -1.133 |
Token |
|
Token ID | 198 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
xual | +0.762 |
Salman | +0.737 |
fell | +0.733 |
ctrl | +0.730 |
ente | +0.722 |
Neg logit contributions | |
.? | -0.899 |
verty | -0.780 |
numbered | -0.779 |
BLE | -0.769 |
ounty | -0.759 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
xual | +0.410 |
Salman | +0.390 |
fell | +0.388 |
ctrl | +0.388 |
illin | +0.384 |
Neg logit contributions | |
.? | -0.516 |
numbered | -0.447 |
verty | -0.446 |
BLE | -0.443 |
ounty | -0.436 |
Token | Thank |
Token ID | 10449 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
xual | +0.117 |
Salman | +0.113 |
fell | +0.112 |
ctrl | +0.112 |
illin | +0.111 |
Neg logit contributions | |
.? | -0.116 |
verty | -0.099 |
numbered | -0.099 |
BLE | -0.098 |
ounty | -0.096 |
Token | you |
Token ID | 345 |
Feature activation | -9.20e+00 |
Pos logit contributions | |
xual | +0.631 |
Salman | +0.611 |
fell | +0.610 |
ctrl | +0.606 |
ente | +0.601 |
Neg logit contributions | |
.? | -0.577 |
numbered | -0.489 |
verty | -0.488 |
BLE | -0.480 |
ounty | -0.472 |
Token | everyone |
Token ID | 2506 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
Salman | +5.326 |
fell | +5.288 |
xual | +5.276 |
ente | +5.100 |
att | +5.070 |
Neg logit contributions | |
.? | -7.341 |
numbered | -6.783 |
verty | -6.603 |
ounty | -6.484 |
BLE | -6.466 |
Token | again |
Token ID | 757 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
xual | +3.129 |
Salman | +3.061 |
fell | +3.035 |
ctrl | +2.980 |
ente | +2.959 |
Neg logit contributions | |
.? | -4.507 |
numbered | -4.070 |
verty | -4.014 |
BLE | -3.956 |
ounty | -3.915 |
Token | for |
Token ID | 329 |
Feature activation | -6.84e+00 |
Pos logit contributions | |
xual | +4.399 |
Salman | +4.352 |
fell | +4.339 |
ctrl | +4.210 |
ente | +4.204 |
Neg logit contributions | |
.? | -6.865 |
numbered | -6.319 |
verty | -6.161 |
BLE | -6.064 |
ounty | -6.051 |
Token | the |
Token ID | 262 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
Salman | +4.297 |
xual | +4.280 |
fell | +4.182 |
ctrl | +4.132 |
att | +4.105 |
Neg logit contributions | |
.? | -5.374 |
verty | -4.774 |
numbered | -4.762 |
BLE | -4.706 |
ounty | -4.618 |
Token | love |
Token ID | 1842 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
xual | +2.799 |
Salman | +2.783 |
fell | +2.740 |
ctrl | +2.712 |
Collider | +2.694 |
Neg logit contributions | |
.? | -3.922 |
numbered | -3.480 |
verty | -3.470 |
BLE | -3.440 |
ounty | -3.363 |
Token | ]) |
Token ID | 12962 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
.? | +2.693 |
numbered | +2.270 |
verty | +2.270 |
BLE | +2.239 |
ounty | +2.212 |
Neg logit contributions | |
xual | -2.885 |
Salman | -2.776 |
illin | -2.763 |
ente | -2.753 |
fell | -2.748 |
Token | ) |
Token ID | 1267 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
.? | +1.233 |
numbered | +1.059 |
verty | +1.055 |
BLE | +1.045 |
ounty | +1.032 |
Neg logit contributions | |
xual | -1.041 |
Salman | -0.995 |
fell | -0.982 |
ctrl | -0.980 |
illin | -0.974 |
Token | ), |
Token ID | 828 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
.? | +1.710 |
numbered | +1.444 |
verty | +1.432 |
BLE | +1.422 |
ounty | +1.394 |
Neg logit contributions | |
xual | -1.776 |
Salman | -1.696 |
ctrl | -1.676 |
fell | -1.673 |
illin | -1.673 |
Token | ( |
Token ID | 357 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
xual | +1.429 |
Salman | +1.374 |
fell | +1.373 |
ctrl | +1.372 |
illin | +1.351 |
Neg logit contributions | |
.? | -1.765 |
verty | -1.532 |
numbered | -1.527 |
BLE | -1.511 |
ounty | -1.492 |
Token | new |
Token ID | 3605 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
xual | +2.103 |
ctrl | +2.065 |
fell | +2.055 |
Salman | +2.029 |
Collider | +2.010 |
Neg logit contributions | |
.? | -3.019 |
verty | -2.666 |
numbered | -2.632 |
BLE | -2.621 |
ounty | -2.595 |
Token | - |
Token ID | 12 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
Collider | +3.901 |
fell | +3.887 |
xual | +3.835 |
Salman | +3.831 |
att | +3.822 |
Neg logit contributions | |
.? | -6.084 |
verty | -5.320 |
numbered | -5.312 |
ANA | -5.304 |
BLE | -5.275 |
Token | object |
Token ID | 15252 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ctrl | +4.695 |
fell | +4.686 |
att | +4.644 |
ente | +4.448 |
kr | +4.408 |
Neg logit contributions | |
.? | -7.550 |
verty | -6.550 |
ounty | -6.518 |
BLE | -6.455 |
antiquity | -6.452 |
Token | system |
Token ID | 1080 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
xual | +1.717 |
Salman | +1.663 |
fell | +1.662 |
ctrl | +1.651 |
Collider | +1.646 |
Neg logit contributions | |
.? | -2.051 |
verty | -1.780 |
numbered | -1.777 |
BLE | -1.761 |
ounty | -1.741 |
Token | . |
Token ID | 13 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
fell | +2.718 |
ctrl | +2.699 |
xual | +2.675 |
Salman | +2.654 |
att | +2.587 |
Neg logit contributions | |
.? | -4.292 |
verty | -3.976 |
numbered | -3.890 |
BLE | -3.831 |
ounty | -3.828 |
Token | draw |
Token ID | 19334 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
fell | +3.976 |
att | +3.912 |
ctrl | +3.906 |
xual | +3.819 |
ente | +3.668 |
Neg logit contributions | |
.? | -9.210 |
ounty | -8.162 |
antiquity | -8.098 |
verty | -8.066 |
BLE | -8.066 |
Token | ing |
Token ID | 278 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
xual | +1.597 |
fell | +1.588 |
Salman | +1.557 |
ctrl | +1.554 |
ente | +1.548 |
Neg logit contributions | |
.? | -1.790 |
verty | -1.567 |
numbered | -1.544 |
BLE | -1.539 |
ounty | -1.506 |
Token | � |
Token ID | 123 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
.? | +4.232 |
verty | +3.642 |
BLE | +3.524 |
numbered | +3.450 |
ANA | +3.390 |
Neg logit contributions | |
xual | -5.727 |
Salman | -5.649 |
fell | -5.638 |
ctrl | -5.621 |
Collider | -5.621 |
Token | � |
Token ID | 228 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
.? | +2.704 |
verty | +2.156 |
BLE | +2.050 |
numbered | +2.037 |
ANA | +2.021 |
Neg logit contributions | |
xual | -4.898 |
Salman | -4.798 |
ctrl | -4.792 |
Collider | -4.774 |
ailable | -4.770 |
Token | ς |
Token ID | 35558 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
.? | +0.832 |
verty | +0.702 |
numbered | +0.701 |
BLE | +0.697 |
ounty | +0.677 |
Neg logit contributions | |
xual | -0.862 |
Salman | -0.833 |
ctrl | -0.830 |
fell | -0.827 |
illin | -0.824 |
Token | ( |
Token ID | 357 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
xual | +0.186 |
Salman | +0.179 |
fell | +0.178 |
ctrl | +0.178 |
illin | +0.176 |
Neg logit contributions | |
.? | -0.208 |
verty | -0.179 |
numbered | -0.179 |
BLE | -0.177 |
ounty | -0.173 |
Token | Ant |
Token ID | 13217 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
.? | +3.269 |
numbered | +2.869 |
verty | +2.828 |
BLE | +2.808 |
ounty | +2.724 |
Neg logit contributions | |
xual | -2.847 |
Salman | -2.697 |
Collider | -2.671 |
ente | -2.657 |
ctrl | -2.648 |
Token | iqu |
Token ID | 1557 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
xual | +1.126 |
Salman | +1.093 |
ctrl | +1.088 |
fell | +1.088 |
illin | +1.081 |
Neg logit contributions | |
.? | -1.318 |
numbered | -1.147 |
BLE | -1.144 |
verty | -1.141 |
ounty | -1.118 |
Token | ities |
Token ID | 871 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
illin | +7.225 |
att | +7.180 |
xual | +7.171 |
ente | +7.035 |
fell | +7.018 |
Neg logit contributions | |
.? | -5.901 |
verty | -5.231 |
numbered | -5.187 |
UGE | -5.117 |
BLE | -5.100 |
Token | of |
Token ID | 286 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
xual | +3.496 |
Salman | +3.406 |
fell | +3.389 |
ctrl | +3.337 |
Collider | +3.323 |
Neg logit contributions | |
.? | -4.494 |
verty | -3.979 |
numbered | -3.950 |
BLE | -3.946 |
ounty | -3.936 |
Token | the |
Token ID | 262 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
xual | +0.488 |
Salman | +0.472 |
fell | +0.469 |
ctrl | +0.467 |
illin | +0.463 |
Neg logit contributions | |
.? | -0.542 |
verty | -0.467 |
numbered | -0.466 |
BLE | -0.461 |
ounty | -0.454 |
Token | Jews |
Token ID | 6771 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
xual | +0.632 |
Salman | +0.610 |
fell | +0.607 |
ctrl | +0.605 |
illin | +0.599 |
Neg logit contributions | |
.? | -0.677 |
verty | -0.582 |
numbered | -0.582 |
BLE | -0.575 |
ounty | -0.566 |
Token | I |
Token ID | 314 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
xual | +1.667 |
Salman | +1.607 |
fell | +1.600 |
ctrl | +1.584 |
ente | +1.565 |
Neg logit contributions | |
.? | -2.521 |
verty | -2.228 |
numbered | -2.221 |
BLE | -2.203 |
ounty | -2.184 |