Token | � |
Token ID | 250 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
KN | +0.375 |
Kem | +0.363 |
pel | +0.358 |
Primal | +0.354 |
Emin | +0.334 |
Neg logit contributions | |
wagen | -0.642 |
alore | -0.581 |
thia | -0.573 |
CLASSIFIED | -0.560 |
ciation | -0.553 |
Token | Next |
Token ID | 10019 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
wagen | +2.051 |
alore | +1.804 |
thia | +1.792 |
CLASSIFIED | +1.731 |
ciation | +1.706 |
Neg logit contributions | |
KN | -1.998 |
Kem | -1.959 |
pel | -1.938 |
Primal | -1.923 |
hower | -1.855 |
Token | year |
Token ID | 614 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
wagen | +2.861 |
alore | +2.555 |
thia | +2.498 |
CLASSIFIED | +2.398 |
ciation | +2.387 |
Neg logit contributions | |
KN | -2.675 |
Kem | -2.558 |
pel | -2.555 |
Primal | -2.519 |
hower | -2.428 |
Token | will |
Token ID | 481 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
wagen | +2.669 |
alore | +2.362 |
thia | +2.343 |
CLASSIFIED | +2.239 |
ciation | +2.229 |
Neg logit contributions | |
KN | -2.397 |
pel | -2.304 |
Kem | -2.292 |
Primal | -2.252 |
hower | -2.195 |
Token | defin |
Token ID | 2730 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
wagen | +1.456 |
alore | +1.288 |
thia | +1.266 |
ciation | +1.205 |
CLASSIFIED | +1.193 |
Neg logit contributions | |
KN | -1.327 |
Kem | -1.290 |
pel | -1.274 |
Primal | -1.257 |
Stephenson | -1.220 |
Token | - |
Token ID | 12 |
Feature activation | +1.86e+01 |
Pos logit contributions | |
wagen | +9.544 |
alore | +8.558 |
thia | +8.434 |
ciation | +8.324 |
akeru | +8.071 |
Neg logit contributions | |
KN | -8.668 |
Kem | -8.521 |
Primal | -8.446 |
pel | -8.190 |
Stephenson | -8.066 |
Token | it |
Token ID | 340 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
wagen | +11.083 |
alore | +10.650 |
ciation | +10.468 |
thia | +9.966 |
akeru | +9.475 |
Neg logit contributions | |
KN | -12.752 |
hower | -12.688 |
pel | -12.363 |
Kem | -12.171 |
Stephenson | -12.120 |
Token | e |
Token ID | 68 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
wagen | +5.225 |
thia | +4.545 |
alore | +4.539 |
ciation | +4.370 |
CLASSIFIED | +4.096 |
Neg logit contributions | |
KN | -7.129 |
Kem | -6.876 |
pel | -6.838 |
Primal | -6.834 |
hower | -6.628 |
Token | ly |
Token ID | 306 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
wagen | +4.228 |
alore | +3.788 |
thia | +3.741 |
ciation | +3.599 |
CLASSIFIED | +3.573 |
Neg logit contributions | |
KN | -3.645 |
pel | -3.502 |
Kem | -3.487 |
Primal | -3.441 |
hower | -3.322 |
Token | be |
Token ID | 307 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
wagen | +2.260 |
alore | +2.005 |
thia | +1.983 |
CLASSIFIED | +1.886 |
ciation | +1.879 |
Neg logit contributions | |
KN | -2.057 |
Kem | -2.003 |
pel | -1.985 |
Primal | -1.963 |
hower | -1.893 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
KN | +0.403 |
Kem | +0.395 |
pel | +0.387 |
Primal | +0.385 |
Stephenson | +0.367 |
Neg logit contributions | |
wagen | -0.513 |
alore | -0.459 |
thia | -0.452 |
CLASSIFIED | -0.441 |
ciation | -0.433 |
Token | :" |
Token ID | 11097 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
wagen | +3.711 |
alore | +3.245 |
thia | +3.201 |
CLASSIFIED | +3.126 |
ciation | +2.993 |
Neg logit contributions | |
KN | -4.124 |
Kem | -4.058 |
Primal | -4.004 |
pel | -3.982 |
Stephenson | -3.900 |
Token | you |
Token ID | 345 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
wagen | +0.172 |
alore | +0.154 |
thia | +0.152 |
CLASSIFIED | +0.148 |
ciation | +0.146 |
Neg logit contributions | |
KN | -0.129 |
Kem | -0.126 |
pel | -0.124 |
Primal | -0.122 |
Stephenson | -0.117 |
Token | have |
Token ID | 423 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
wagen | +1.337 |
alore | +1.195 |
thia | +1.183 |
CLASSIFIED | +1.132 |
ciation | +1.129 |
Neg logit contributions | |
KN | -1.095 |
Kem | -1.067 |
pel | -1.051 |
Primal | -1.040 |
Stephenson | -0.998 |
Token | to |
Token ID | 284 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
wagen | +3.770 |
thia | +3.310 |
alore | +3.302 |
CLASSIFIED | +3.211 |
ciation | +3.163 |
Neg logit contributions | |
KN | -3.086 |
Kem | -2.990 |
pel | -2.975 |
Primal | -2.930 |
Emin | -2.805 |
Token | specify |
Token ID | 11986 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
wagen | +2.816 |
alore | +2.508 |
thia | +2.483 |
ciation | +2.366 |
CLASSIFIED | +2.347 |
Neg logit contributions | |
KN | -2.404 |
Kem | -2.335 |
pel | -2.295 |
Primal | -2.271 |
Stephenson | -2.203 |
Token | " |
Token ID | 366 |
Feature activation | +1.32e+01 |
Pos logit contributions | |
wagen | +2.503 |
alore | +2.210 |
thia | +2.198 |
CLASSIFIED | +2.133 |
ciation | +2.104 |
Neg logit contributions | |
KN | -2.178 |
Kem | -2.104 |
pel | -2.094 |
Primal | -2.063 |
hower | -1.978 |
Token | \\ |
Token ID | 6852 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
wagen | +9.771 |
alore | +8.457 |
thia | +8.452 |
CLASSIFIED | +8.408 |
ciation | +8.167 |
Neg logit contributions | |
KN | -9.141 |
Primal | -9.017 |
Kem | -8.985 |
Emin | -8.845 |
pel | -8.817 |
Token | : |
Token ID | 25 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
wagen | +3.608 |
alore | +3.182 |
thia | +3.159 |
CLASSIFIED | +3.071 |
ciation | +2.997 |
Neg logit contributions | |
KN | -3.447 |
Kem | -3.365 |
pel | -3.314 |
Primal | -3.308 |
Stephenson | -3.210 |
Token | ". |
Token ID | 1911 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
wagen | +3.996 |
alore | +3.492 |
thia | +3.481 |
CLASSIFIED | +3.382 |
ciation | +3.295 |
Neg logit contributions | |
KN | -3.716 |
Kem | -3.616 |
pel | -3.581 |
Primal | -3.565 |
Emin | -3.453 |
Token | No |
Token ID | 1400 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
wagen | +3.185 |
thia | +2.802 |
alore | +2.793 |
CLASSIFIED | +2.689 |
ciation | +2.665 |
Neg logit contributions | |
KN | -3.042 |
Kem | -2.933 |
pel | -2.929 |
Primal | -2.879 |
hower | -2.796 |
Token | other |
Token ID | 584 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
KN | +0.485 |
Kem | +0.473 |
pel | +0.466 |
Primal | +0.461 |
Stephenson | +0.439 |
Neg logit contributions | |
wagen | -0.644 |
alore | -0.578 |
thia | -0.570 |
CLASSIFIED | -0.555 |
ciation | -0.548 |
Token | e |
Token ID | 304 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
wagen | +3.375 |
alore | +2.924 |
thia | +2.904 |
ciation | +2.776 |
CLASSIFIED | +2.687 |
Neg logit contributions | |
KN | -4.317 |
Kem | -4.208 |
pel | -4.156 |
Primal | -4.107 |
Stephenson | -4.010 |
Token | . |
Token ID | 13 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
wagen | +1.266 |
alore | +1.125 |
thia | +1.112 |
CLASSIFIED | +1.077 |
ciation | +1.061 |
Neg logit contributions | |
KN | -1.115 |
Kem | -1.087 |
pel | -1.073 |
Primal | -1.061 |
Stephenson | -1.017 |
Token | g |
Token ID | 70 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
KN | +1.930 |
pel | +1.869 |
Kem | +1.797 |
Primal | +1.784 |
Emin | +1.637 |
Neg logit contributions | |
wagen | -4.950 |
alore | -4.553 |
CLASSIFIED | -4.551 |
thia | -4.464 |
ciation | -4.326 |
Token | .: |
Token ID | 11207 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
wagen | +2.228 |
alore | +1.892 |
thia | +1.865 |
CLASSIFIED | +1.764 |
ciation | +1.760 |
Neg logit contributions | |
KN | -3.338 |
Kem | -3.270 |
pel | -3.239 |
Primal | -3.201 |
Stephenson | -3.116 |
Token |
|
Token ID | 198 |
Feature activation | +8.15e+00 |
Pos logit contributions | |
wagen | +7.528 |
alore | +6.545 |
thia | +6.485 |
ciation | +6.326 |
CLASSIFIED | +6.237 |
Neg logit contributions | |
KN | -8.015 |
Kem | -7.881 |
pel | -7.646 |
Stephenson | -7.472 |
Primal | -7.444 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e+01 |
Pos logit contributions | |
wagen | +5.962 |
thia | +5.356 |
alore | +5.196 |
ciation | +5.012 |
Wo | +4.976 |
Neg logit contributions | |
KN | -6.280 |
Kem | -6.198 |
hower | -6.105 |
pel | -6.089 |
Primal | -6.050 |
Token | ruby |
Token ID | 49137 |
Feature activation | +6.22e+00 |
Pos logit contributions | |
wagen | +9.509 |
thia | +8.273 |
alore | +8.158 |
CLASSIFIED | +8.001 |
Wo | +7.865 |
Neg logit contributions | |
Kem | -9.495 |
Stephenson | -9.203 |
KN | -9.134 |
Primal | -8.935 |
Ike | -8.720 |
Token | [ |
Token ID | 685 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
wagen | +4.744 |
alore | +4.174 |
thia | +4.078 |
CLASSIFIED | +3.956 |
ciation | +3.935 |
Neg logit contributions | |
KN | -4.893 |
Kem | -4.794 |
pel | -4.727 |
Primal | -4.608 |
Stephenson | -4.533 |
Token | 1 |
Token ID | 16 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
KN | +0.078 |
Kem | +0.075 |
pel | +0.075 |
Primal | +0.074 |
Stephenson | +0.070 |
Neg logit contributions | |
wagen | -0.094 |
alore | -0.084 |
thia | -0.083 |
CLASSIFIED | -0.080 |
ciation | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
wagen | +0.211 |
alore | +0.188 |
thia | +0.186 |
CLASSIFIED | +0.180 |
ciation | +0.177 |
Neg logit contributions | |
KN | -0.177 |
Kem | -0.173 |
pel | -0.171 |
Primal | -0.169 |
Stephenson | -0.162 |
Token | 2 |
Token ID | 17 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
wagen | +0.298 |
alore | +0.265 |
thia | +0.262 |
CLASSIFIED | +0.254 |
ciation | +0.250 |
Neg logit contributions | |
KN | -0.258 |
Kem | -0.252 |
pel | -0.249 |
Primal | -0.246 |
Stephenson | -0.236 |
Token | � |
Token ID | 564 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
wagen | +1.282 |
alore | +1.148 |
thia | +1.140 |
CLASSIFIED | +1.107 |
ciation | +1.096 |
Neg logit contributions | |
KN | -0.911 |
Kem | -0.881 |
pel | -0.877 |
Primal | -0.852 |
hower | -0.818 |
Token | � |
Token ID | 250 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
KN | +0.375 |
Kem | +0.363 |
pel | +0.358 |
Primal | +0.354 |
Emin | +0.334 |
Neg logit contributions | |
wagen | -0.642 |
alore | -0.581 |
thia | -0.573 |
CLASSIFIED | -0.560 |
ciation | -0.553 |
Token | Next |
Token ID | 10019 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
wagen | +2.051 |
alore | +1.804 |
thia | +1.792 |
CLASSIFIED | +1.731 |
ciation | +1.706 |
Neg logit contributions | |
KN | -1.998 |
Kem | -1.959 |
pel | -1.938 |
Primal | -1.923 |
hower | -1.855 |
Token | year |
Token ID | 614 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
wagen | +2.861 |
alore | +2.555 |
thia | +2.498 |
CLASSIFIED | +2.398 |
ciation | +2.387 |
Neg logit contributions | |
KN | -2.675 |
Kem | -2.558 |
pel | -2.555 |
Primal | -2.519 |
hower | -2.428 |
Token | will |
Token ID | 481 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
wagen | +2.669 |
alore | +2.362 |
thia | +2.343 |
CLASSIFIED | +2.239 |
ciation | +2.229 |
Neg logit contributions | |
KN | -2.397 |
pel | -2.304 |
Kem | -2.292 |
Primal | -2.252 |
hower | -2.195 |
Token | defin |
Token ID | 2730 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
wagen | +1.456 |
alore | +1.288 |
thia | +1.266 |
ciation | +1.205 |
CLASSIFIED | +1.193 |
Neg logit contributions | |
KN | -1.327 |
Kem | -1.290 |
pel | -1.274 |
Primal | -1.257 |
Stephenson | -1.220 |
Token | - |
Token ID | 12 |
Feature activation | +1.86e+01 |
Pos logit contributions | |
wagen | +9.544 |
alore | +8.558 |
thia | +8.434 |
ciation | +8.324 |
akeru | +8.071 |
Neg logit contributions | |
KN | -8.668 |
Kem | -8.521 |
Primal | -8.446 |
pel | -8.190 |
Stephenson | -8.066 |
Token | it |
Token ID | 340 |
Feature activation | +8.08e+00 |
Pos logit contributions | |
wagen | +11.083 |
alore | +10.650 |
ciation | +10.468 |
thia | +9.966 |
akeru | +9.475 |
Neg logit contributions | |
KN | -12.752 |
hower | -12.688 |
pel | -12.363 |
Kem | -12.171 |
Stephenson | -12.120 |
Token | e |
Token ID | 68 |
Feature activation | +5.05e+00 |
Pos logit contributions | |
wagen | +5.225 |
thia | +4.545 |
alore | +4.539 |
ciation | +4.370 |
CLASSIFIED | +4.096 |
Neg logit contributions | |
KN | -7.129 |
Kem | -6.876 |
pel | -6.838 |
Primal | -6.834 |
hower | -6.628 |
Token | ly |
Token ID | 306 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
wagen | +4.228 |
alore | +3.788 |
thia | +3.741 |
ciation | +3.599 |
CLASSIFIED | +3.573 |
Neg logit contributions | |
KN | -3.645 |
pel | -3.502 |
Kem | -3.487 |
Primal | -3.441 |
hower | -3.322 |
Token | be |
Token ID | 307 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
wagen | +2.260 |
alore | +2.005 |
thia | +1.983 |
CLASSIFIED | +1.886 |
ciation | +1.879 |
Neg logit contributions | |
KN | -2.057 |
Kem | -2.003 |
pel | -1.985 |
Primal | -1.963 |
hower | -1.893 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
wagen | +5.696 |
CLASSIFIED | +5.034 |
thia | +4.920 |
Wo | +4.656 |
alore | +4.610 |
Neg logit contributions | |
Primal | -10.361 |
Kem | -10.278 |
Stephenson | -10.126 |
KN | -10.080 |
hower | -10.047 |
Token | Steve |
Token ID | 6542 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
wagen | +1.778 |
thia | +1.592 |
alore | +1.590 |
CLASSIFIED | +1.517 |
ciation | +1.511 |
Neg logit contributions | |
KN | -1.470 |
pel | -1.420 |
Kem | -1.406 |
Primal | -1.384 |
hower | -1.340 |
Token | Care |
Token ID | 7276 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
wagen | +2.305 |
alore | +2.073 |
thia | +2.056 |
ciation | +1.976 |
CLASSIFIED | +1.968 |
Neg logit contributions | |
KN | -1.994 |
pel | -1.913 |
Kem | -1.911 |
Primal | -1.869 |
hower | -1.807 |
Token | ll |
Token ID | 297 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
wagen | +0.558 |
alore | +0.507 |
thia | +0.501 |
CLASSIFIED | +0.497 |
ciation | +0.484 |
Neg logit contributions | |
KN | -0.266 |
pel | -0.256 |
Kem | -0.255 |
Primal | -0.247 |
Emin | -0.232 |
Token |
|
Token ID | 198 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
wagen | +4.445 |
thia | +3.957 |
alore | +3.886 |
ciation | +3.757 |
CLASSIFIED | +3.700 |
Neg logit contributions | |
KN | -4.096 |
pel | -3.953 |
Kem | -3.922 |
Primal | -3.824 |
hower | -3.761 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
wagen | +1.493 |
alore | +1.339 |
thia | +1.324 |
CLASSIFIED | +1.285 |
ciation | +1.268 |
Neg logit contributions | |
KN | -1.111 |
Kem | -1.081 |
pel | -1.066 |
Primal | -1.053 |
Stephenson | -1.004 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
wagen | +6.066 |
CLASSIFIED | +5.365 |
thia | +5.300 |
Wo | +5.083 |
alore | +4.862 |
Neg logit contributions | |
Primal | -11.973 |
Kem | -11.819 |
Stephenson | -11.689 |
KN | -11.591 |
hower | -11.552 |
Token | Lee |
Token ID | 5741 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
wagen | +3.335 |
thia | +3.026 |
alore | +2.996 |
ciation | +2.859 |
CLASSIFIED | +2.846 |
Neg logit contributions | |
KN | -2.758 |
pel | -2.677 |
Kem | -2.599 |
Primal | -2.572 |
hower | -2.532 |
Token | Pace |
Token ID | 44111 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Kem | +1.714 |
KN | +1.685 |
Primal | +1.606 |
pel | +1.604 |
Stephenson | +1.562 |
Neg logit contributions | |
wagen | -3.130 |
alore | -2.837 |
CLASSIFIED | -2.809 |
thia | -2.777 |
ciation | -2.706 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
wagen | +1.674 |
alore | +1.486 |
thia | +1.483 |
CLASSIFIED | +1.422 |
ciation | +1.418 |
Neg logit contributions | |
KN | -1.374 |
Kem | -1.326 |
pel | -1.319 |
Primal | -1.298 |
Emin | -1.234 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
KN | +0.275 |
Kem | +0.267 |
pel | +0.263 |
Primal | +0.259 |
Ike | +0.247 |
Neg logit contributions | |
wagen | -0.413 |
alore | -0.372 |
thia | -0.364 |
CLASSIFIED | -0.363 |
ciation | -0.351 |
Token | York |
Token ID | 1971 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
wagen | +4.456 |
alore | +3.899 |
thia | +3.897 |
ciation | +3.667 |
CLASSIFIED | +3.653 |
Neg logit contributions | |
KN | -4.897 |
Kem | -4.689 |
pel | -4.672 |
Primal | -4.627 |
hower | -4.568 |
Token | , |
Token ID | 11 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
wagen | +4.376 |
alore | +3.862 |
thia | +3.791 |
CLASSIFIED | +3.669 |
ciation | +3.573 |
Neg logit contributions | |
KN | -5.111 |
pel | -4.989 |
Kem | -4.943 |
Primal | -4.848 |
hower | -4.797 |
Token | NY |
Token ID | 6645 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
wagen | +3.204 |
alore | +2.834 |
thia | +2.783 |
CLASSIFIED | +2.713 |
ciation | +2.649 |
Neg logit contributions | |
KN | -3.306 |
pel | -3.230 |
Kem | -3.200 |
Primal | -3.145 |
hower | -3.093 |
Token | : |
Token ID | 1058 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
wagen | +2.672 |
alore | +2.308 |
thia | +2.299 |
CLASSIFIED | +2.252 |
ciation | +2.141 |
Neg logit contributions | |
KN | -3.572 |
pel | -3.513 |
Kem | -3.474 |
Primal | -3.437 |
hower | -3.388 |
Token | Worth |
Token ID | 22301 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
wagen | +3.098 |
alore | +2.804 |
thia | +2.780 |
CLASSIFIED | +2.719 |
ciation | +2.666 |
Neg logit contributions | |
KN | -2.385 |
pel | -2.328 |
Kem | -2.277 |
Primal | -2.215 |
hower | -2.187 |
Token | Publishers |
Token ID | 43403 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
wagen | +2.785 |
alore | +2.403 |
thia | +2.373 |
CLASSIFIED | +2.295 |
ciation | +2.245 |
Neg logit contributions | |
KN | -3.258 |
Kem | -3.174 |
pel | -3.151 |
Primal | -3.130 |
hower | -2.999 |
Token | . |
Token ID | 764 |
Feature activation | +4.63e+00 |
Pos logit contributions | |
wagen | +6.564 |
thia | +5.262 |
alore | +5.088 |
CLASSIFIED | +4.842 |
ciation | +4.841 |
Neg logit contributions | |
KN | -11.418 |
pel | -11.153 |
Primal | -10.994 |
hower | -10.874 |
Emin | -10.854 |
Token |
|
Token ID | 198 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
wagen | +3.841 |
alore | +3.462 |
thia | +3.438 |
CLASSIFIED | +3.265 |
ciation | +3.241 |
Neg logit contributions | |
KN | -3.357 |
pel | -3.224 |
Kem | -3.220 |
Primal | -3.165 |
Emin | -3.067 |
Token |
|
Token ID | 198 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
wagen | +2.374 |
alore | +2.124 |
thia | +2.113 |
CLASSIFIED | +2.024 |
ciation | +2.016 |
Neg logit contributions | |
KN | -1.850 |
Kem | -1.801 |
pel | -1.780 |
Primal | -1.757 |
hower | -1.686 |
Token | Google |
Token ID | 11708 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
wagen | +2.524 |
alore | +2.191 |
thia | +2.170 |
CLASSIFIED | +2.102 |
ciation | +2.048 |
Neg logit contributions | |
KN | -2.828 |
Kem | -2.778 |
Primal | -2.750 |
pel | -2.748 |
hower | -2.647 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
KN | +1.029 |
Kem | +1.009 |
pel | +0.989 |
Primal | +0.985 |
Stephenson | +0.950 |
Neg logit contributions | |
wagen | -1.002 |
alore | -0.888 |
thia | -0.861 |
CLASSIFIED | -0.841 |
ciation | -0.824 |
Token | into |
Token ID | 656 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
KN | +0.634 |
Kem | +0.618 |
pel | +0.610 |
Primal | +0.603 |
Stephenson | +0.575 |
Neg logit contributions | |
wagen | -0.781 |
alore | -0.698 |
thia | -0.689 |
CLASSIFIED | -0.670 |
ciation | -0.659 |
Token | so |
Token ID | 523 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
wagen | +3.948 |
alore | +3.506 |
thia | +3.497 |
CLASSIFIED | +3.380 |
ciation | +3.301 |
Neg logit contributions | |
KN | -3.140 |
Kem | -3.031 |
pel | -3.029 |
Primal | -2.948 |
hower | -2.869 |
Token | many |
Token ID | 867 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
wagen | +1.531 |
alore | +1.369 |
thia | +1.360 |
CLASSIFIED | +1.314 |
ciation | +1.296 |
Neg logit contributions | |
KN | -1.231 |
Kem | -1.203 |
pel | -1.178 |
Primal | -1.162 |
Stephenson | -1.116 |
Token | apparent |
Token ID | 4156 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
wagen | +4.053 |
alore | +3.584 |
thia | +3.569 |
CLASSIFIED | +3.454 |
ciation | +3.394 |
Neg logit contributions | |
KN | -3.262 |
Kem | -3.147 |
pel | -3.134 |
Primal | -3.066 |
hower | -2.993 |
Token | stren |
Token ID | 43071 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
wagen | +3.966 |
alore | +3.501 |
thia | +3.500 |
CLASSIFIED | +3.376 |
ciation | +3.317 |
Neg logit contributions | |
KN | -3.338 |
Kem | -3.225 |
pel | -3.225 |
Primal | -3.148 |
hower | -3.065 |
Token | gh |
Token ID | 456 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
wagen | +4.359 |
alore | +3.897 |
thia | +3.874 |
ciation | +3.706 |
CLASSIFIED | +3.673 |
Neg logit contributions | |
KN | -3.850 |
Kem | -3.791 |
pel | -3.677 |
Primal | -3.654 |
hower | -3.560 |
Token | ts |
Token ID | 912 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
wagen | +8.771 |
thia | +7.627 |
alore | +7.551 |
ciation | +7.440 |
CLASSIFIED | +6.899 |
Neg logit contributions | |
KN | -9.279 |
Kem | -9.122 |
Primal | -8.970 |
pel | -8.887 |
hower | -8.647 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
wagen | +0.570 |
alore | +0.508 |
thia | +0.503 |
CLASSIFIED | +0.486 |
ciation | +0.481 |
Neg logit contributions | |
KN | -0.477 |
Kem | -0.465 |
pel | -0.459 |
Primal | -0.454 |
Stephenson | -0.435 |
Token | It |
Token ID | 1026 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
KN | +0.240 |
Kem | +0.234 |
pel | +0.230 |
Primal | +0.228 |
Stephenson | +0.218 |
Neg logit contributions | |
wagen | -0.281 |
alore | -0.250 |
thia | -0.246 |
CLASSIFIED | -0.238 |
ciation | -0.235 |
Token | unleashed |
Token ID | 28136 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
KN | +0.560 |
Kem | +0.545 |
pel | +0.538 |
Primal | +0.530 |
Stephenson | +0.505 |
Neg logit contributions | |
wagen | -0.795 |
alore | -0.714 |
thia | -0.706 |
CLASSIFIED | -0.689 |
ciation | -0.678 |
Token | into |
Token ID | 656 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
wagen | +3.034 |
alore | +2.713 |
thia | +2.687 |
CLASSIFIED | +2.584 |
ciation | +2.547 |
Neg logit contributions | |
KN | -2.469 |
Kem | -2.387 |
pel | -2.373 |
Primal | -2.334 |
hower | -2.252 |
Token | Scholar |
Token ID | 11713 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
KN | +1.042 |
Kem | +1.021 |
pel | +1.001 |
Primal | +0.996 |
Stephenson | +0.961 |
Neg logit contributions | |
wagen | -1.012 |
alore | -0.898 |
thia | -0.869 |
CLASSIFIED | -0.851 |
ciation | -0.831 |
Token | Crossref |
Token ID | 23613 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
wagen | +1.174 |
alore | +1.035 |
thia | +1.024 |
CLASSIFIED | +0.994 |
ciation | +0.973 |
Neg logit contributions | |
KN | -1.224 |
Kem | -1.201 |
pel | -1.188 |
Primal | -1.169 |
Emin | -1.131 |
Token | | |
Token ID | 930 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
wagen | +0.771 |
alore | +0.689 |
thia | +0.681 |
CLASSIFIED | +0.662 |
ciation | +0.651 |
Neg logit contributions | |
KN | -0.637 |
Kem | -0.621 |
pel | -0.613 |
Primal | -0.604 |
Stephenson | -0.578 |
Token | ISI |
Token ID | 22048 |
Feature activation | +8.58e+00 |
Pos logit contributions | |
KN | +1.132 |
Kem | +1.102 |
Primal | +1.083 |
pel | +1.070 |
Stephenson | +1.033 |
Neg logit contributions | |
wagen | -1.353 |
alore | -1.205 |
thia | -1.174 |
CLASSIFIED | -1.130 |
ciation | -1.121 |
Token |
|
Token ID | 198 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
wagen | +6.295 |
thia | +5.717 |
alore | +5.440 |
ciation | +5.396 |
Wo | +5.249 |
Neg logit contributions | |
KN | -6.531 |
pel | -6.401 |
Kem | -6.369 |
hower | -6.301 |
Primal | -6.180 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e+01 |
Pos logit contributions | |
wagen | +5.031 |
thia | +4.534 |
alore | +4.433 |
ciation | +4.264 |
Wo | +4.170 |
Neg logit contributions | |
KN | -4.754 |
Kem | -4.644 |
pel | -4.623 |
hower | -4.560 |
Primal | -4.539 |
Token | Sal |
Token ID | 19221 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
wagen | +8.897 |
Wo | +7.894 |
CLASSIFIED | +7.742 |
thia | +7.729 |
alore | +7.387 |
Neg logit contributions | |
Kem | -9.009 |
hower | -8.876 |
ohyd | -8.740 |
Primal | -8.711 |
Emin | -8.662 |
Token | m |
Token ID | 76 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
wagen | +1.239 |
alore | +1.104 |
thia | +1.092 |
CLASSIFIED | +1.056 |
ciation | +1.042 |
Neg logit contributions | |
KN | -1.039 |
Kem | -1.012 |
pel | -0.998 |
Primal | -0.988 |
Stephenson | -0.945 |
Token | iv |
Token ID | 452 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
wagen | +0.962 |
alore | +0.856 |
thia | +0.846 |
CLASSIFIED | +0.823 |
ciation | +0.808 |
Neg logit contributions | |
KN | -0.834 |
Kem | -0.814 |
pel | -0.804 |
Primal | -0.794 |
Stephenson | -0.761 |
Token | alli |
Token ID | 36546 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
wagen | +2.851 |
alore | +2.536 |
thia | +2.511 |
ciation | +2.394 |
CLASSIFIED | +2.380 |
Neg logit contributions | |
KN | -2.475 |
Kem | -2.408 |
pel | -2.370 |
Primal | -2.363 |
Stephenson | -2.245 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
wagen | +2.795 |
alore | +2.464 |
thia | +2.440 |
CLASSIFIED | +2.344 |
ciation | +2.320 |
Neg logit contributions | |
KN | -2.579 |
Kem | -2.487 |
pel | -2.479 |
Primal | -2.448 |
Emin | -2.353 |
Token | Tony |
Token ID | 8832 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
wagen | +3.054 |
thia | +2.762 |
alore | +2.739 |
ciation | +2.617 |
CLASSIFIED | +2.608 |
Neg logit contributions | |
KN | -2.464 |
pel | -2.384 |
Kem | -2.318 |
Primal | -2.297 |
hower | -2.253 |
Token | Shal |
Token ID | 47974 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
wagen | +1.588 |
alore | +1.367 |
thia | +1.357 |
CLASSIFIED | +1.281 |
ciation | +1.266 |
Neg logit contributions | |
KN | -2.283 |
Kem | -2.225 |
pel | -2.215 |
Primal | -2.181 |
hower | -2.119 |
Token | h |
Token ID | 71 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
wagen | +0.068 |
alore | +0.060 |
CLASSIFIED | +0.059 |
thia | +0.059 |
ciation | +0.056 |
Neg logit contributions | |
KN | -0.067 |
pel | -0.065 |
Kem | -0.065 |
Primal | -0.064 |
hower | -0.061 |
Token | oub |
Token ID | 12944 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
wagen | +1.563 |
alore | +1.409 |
thia | +1.395 |
CLASSIFIED | +1.354 |
ciation | +1.338 |
Neg logit contributions | |
KN | -1.038 |
Kem | -1.008 |
pel | -0.992 |
Primal | -0.980 |
Stephenson | -0.931 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
wagen | +5.000 |
thia | +4.445 |
alore | +4.350 |
ciation | +4.253 |
CLASSIFIED | +4.218 |
Neg logit contributions | |
KN | -4.842 |
pel | -4.594 |
Kem | -4.570 |
Primal | -4.469 |
Emin | -4.306 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
wagen | +0.343 |
alore | +0.308 |
thia | +0.303 |
CLASSIFIED | +0.299 |
ciation | +0.291 |
Neg logit contributions | |
KN | -0.238 |
Kem | -0.232 |
pel | -0.228 |
Primal | -0.225 |
Ike | -0.214 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
wagen | +5.961 |
CLASSIFIED | +5.377 |
thia | +5.191 |
Wo | +5.020 |
alore | +4.824 |
Neg logit contributions | |
Primal | -11.554 |
Kem | -11.411 |
Stephenson | -11.274 |
KN | -11.242 |
hower | -11.165 |
Token | Charlie |
Token ID | 11526 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
wagen | +1.536 |
alore | +1.372 |
thia | +1.370 |
CLASSIFIED | +1.313 |
ciation | +1.307 |
Neg logit contributions | |
KN | -1.279 |
pel | -1.234 |
Kem | -1.226 |
Primal | -1.204 |
hower | -1.162 |
Token | Sheen |
Token ID | 50189 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
KN | +0.445 |
Kem | +0.438 |
pel | +0.429 |
Primal | +0.427 |
Stephenson | +0.412 |
Neg logit contributions | |
wagen | -0.442 |
alore | -0.388 |
thia | -0.377 |
CLASSIFIED | -0.373 |
ciation | -0.360 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
wagen | +5.100 |
thia | +4.554 |
alore | +4.438 |
ciation | +4.348 |
CLASSIFIED | +4.254 |
Neg logit contributions | |
KN | -5.420 |
pel | -5.162 |
Kem | -5.119 |
Primal | -4.981 |
hower | -4.837 |
Token | Alec |
Token ID | 38285 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
KN | +0.636 |
Kem | +0.624 |
pel | +0.612 |
Primal | +0.607 |
Stephenson | +0.582 |
Neg logit contributions | |
wagen | -0.737 |
alore | -0.654 |
thia | -0.644 |
CLASSIFIED | -0.627 |
ciation | -0.615 |
Token | energy |
Token ID | 2568 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
KN | +1.496 |
Kem | +1.472 |
Primal | +1.436 |
pel | +1.423 |
Stephenson | +1.350 |
Neg logit contributions | |
wagen | -2.504 |
alore | -2.261 |
thia | -2.251 |
CLASSIFIED | -2.200 |
ciation | -2.165 |
Token | goals |
Token ID | 4661 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
wagen | +1.969 |
alore | +1.755 |
thia | +1.728 |
CLASSIFIED | +1.681 |
ciation | +1.659 |
Neg logit contributions | |
KN | -1.631 |
Kem | -1.580 |
pel | -1.572 |
Primal | -1.535 |
hower | -1.480 |
Token | . |
Token ID | 13 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
KN | +0.519 |
Kem | +0.506 |
pel | +0.499 |
Primal | +0.493 |
Stephenson | +0.472 |
Neg logit contributions | |
wagen | -0.614 |
alore | -0.547 |
thia | -0.540 |
CLASSIFIED | -0.524 |
ciation | -0.516 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
KN | +1.300 |
Kem | +1.268 |
Primal | +1.237 |
pel | +1.237 |
Stephenson | +1.177 |
Neg logit contributions | |
wagen | -1.786 |
alore | -1.599 |
thia | -1.585 |
CLASSIFIED | -1.539 |
ciation | -1.512 |
Token | Media |
Token ID | 13152 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
wagen | +0.940 |
alore | +0.834 |
thia | +0.825 |
CLASSIFIED | +0.800 |
ciation | +0.787 |
Neg logit contributions | |
KN | -0.826 |
Kem | -0.808 |
pel | -0.796 |
Primal | -0.789 |
Stephenson | -0.757 |
Token | playback |
Token ID | 16388 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wagen | +4.179 |
alore | +3.661 |
thia | +3.654 |
CLASSIFIED | +3.561 |
ciation | +3.477 |
Neg logit contributions | |
KN | -3.218 |
Kem | -3.148 |
pel | -3.098 |
Primal | -3.045 |
Ike | -2.958 |
Token | is |
Token ID | 318 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
wagen | +7.122 |
thia | +6.364 |
alore | +6.155 |
ciation | +5.873 |
Wo | +5.656 |
Neg logit contributions | |
KN | -10.061 |
hower | -9.786 |
pel | -9.508 |
Kem | -9.411 |
Primal | -9.166 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
wagen | +0.868 |
alore | +0.655 |
thia | +0.612 |
CLASSIFIED | +0.560 |
ciation | +0.525 |
Neg logit contributions | |
KN | -2.992 |
Kem | -2.931 |
pel | -2.921 |
Primal | -2.884 |
hower | -2.827 |
Token | on |
Token ID | 319 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
wagen | +4.649 |
thia | +4.216 |
alore | +4.199 |
ciation | +3.929 |
CLASSIFIED | +3.876 |
Neg logit contributions | |
KN | -4.879 |
Kem | -4.747 |
pel | -4.709 |
Primal | -4.603 |
hower | -4.590 |
Token | your |
Token ID | 534 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
wagen | +1.605 |
alore | +1.431 |
thia | +1.414 |
CLASSIFIED | +1.362 |
ciation | +1.346 |
Neg logit contributions | |
KN | -1.386 |
Kem | -1.347 |
pel | -1.330 |
Primal | -1.314 |
Stephenson | -1.264 |
Token | device |
Token ID | 3335 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
wagen | +2.283 |
alore | +1.921 |
thia | +1.918 |
CLASSIFIED | +1.795 |
ciation | +1.764 |
Neg logit contributions | |
KN | -3.475 |
Kem | -3.379 |
pel | -3.347 |
Primal | -3.324 |
hower | -3.237 |
Token | on |
Token ID | 319 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
KN | +1.589 |
Kem | +1.545 |
Primal | +1.522 |
pel | +1.518 |
Stephenson | +1.439 |
Neg logit contributions | |
wagen | -2.142 |
alore | -1.922 |
thia | -1.891 |
CLASSIFIED | -1.845 |
ciation | -1.818 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
KN | +3.649 |
Kem | +3.587 |
Primal | +3.513 |
pel | +3.329 |
Stephenson | +3.310 |
Neg logit contributions | |
wagen | -6.034 |
alore | -5.429 |
thia | -5.305 |
ciation | -5.191 |
CLASSIFIED | -5.138 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
KN | +1.994 |
Kem | +1.929 |
pel | +1.905 |
Primal | +1.896 |
Stephenson | +1.807 |
Neg logit contributions | |
wagen | -2.648 |
alore | -2.369 |
thia | -2.325 |
CLASSIFIED | -2.276 |
ciation | -2.246 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
KN | +0.475 |
Kem | +0.463 |
Primal | +0.452 |
pel | +0.452 |
Stephenson | +0.428 |
Neg logit contributions | |
wagen | -0.724 |
alore | -0.652 |
thia | -0.641 |
CLASSIFIED | -0.627 |
ciation | -0.617 |
Token | Media |
Token ID | 13152 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
wagen | +1.114 |
alore | +0.989 |
thia | +0.978 |
CLASSIFIED | +0.949 |
ciation | +0.933 |
Neg logit contributions | |
KN | -0.979 |
Kem | -0.959 |
pel | -0.944 |
Primal | -0.937 |
Stephenson | -0.899 |
Token | playback |
Token ID | 16388 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wagen | +3.739 |
alore | +3.288 |
thia | +3.278 |
CLASSIFIED | +3.197 |
ciation | +3.121 |
Neg logit contributions | |
KN | -2.837 |
Kem | -2.771 |
pel | -2.722 |
Primal | -2.680 |
hower | -2.594 |
Token | is |
Token ID | 318 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
wagen | +7.197 |
thia | +6.429 |
alore | +6.199 |
ciation | +5.922 |
Wo | +5.697 |
Neg logit contributions | |
KN | -9.935 |
hower | -9.690 |
pel | -9.386 |
Kem | -9.275 |
Primal | -9.041 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
wagen | +0.956 |
alore | +0.711 |
thia | +0.658 |
CLASSIFIED | +0.598 |
ciation | +0.554 |
Neg logit contributions | |
KN | -3.534 |
Kem | -3.458 |
pel | -3.449 |
Primal | -3.403 |
hower | -3.341 |
Token | on |
Token ID | 319 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
wagen | +4.774 |
thia | +4.335 |
alore | +4.315 |
ciation | +4.025 |
CLASSIFIED | +3.966 |
Neg logit contributions | |
KN | -5.089 |
Kem | -4.954 |
pel | -4.911 |
hower | -4.799 |
Primal | -4.795 |
Token | your |
Token ID | 534 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
wagen | +1.561 |
alore | +1.392 |
thia | +1.376 |
CLASSIFIED | +1.326 |
ciation | +1.310 |
Neg logit contributions | |
KN | -1.339 |
Kem | -1.302 |
pel | -1.285 |
Primal | -1.269 |
Stephenson | -1.221 |
Token | device |
Token ID | 3335 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
wagen | +2.377 |
alore | +1.998 |
thia | +1.993 |
CLASSIFIED | +1.868 |
ciation | +1.833 |
Neg logit contributions | |
KN | -3.618 |
Kem | -3.521 |
pel | -3.487 |
Primal | -3.463 |
hower | -3.379 |
Token | - |
Token ID | 12 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
wagen | +2.297 |
alore | +2.039 |
thia | +2.014 |
CLASSIFIED | +1.923 |
ciation | +1.899 |
Neg logit contributions | |
KN | -2.380 |
Kem | -2.319 |
pel | -2.309 |
Primal | -2.274 |
Stephenson | -2.203 |
Token | m |
Token ID | 76 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
wagen | +3.226 |
thia | +2.925 |
alore | +2.908 |
ciation | +2.742 |
CLASSIFIED | +2.708 |
Neg logit contributions | |
KN | -2.593 |
Kem | -2.526 |
Primal | -2.477 |
pel | -2.434 |
Stephenson | -2.394 |
Token | eth |
Token ID | 2788 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
wagen | +4.128 |
thia | +3.692 |
alore | +3.669 |
ciation | +3.365 |
akeru | +3.297 |
Neg logit contributions | |
KN | -4.828 |
Kem | -4.663 |
Primal | -4.623 |
Stephenson | -4.539 |
pel | -4.526 |
Token | ox |
Token ID | 1140 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
wagen | +3.813 |
alore | +3.392 |
thia | +3.360 |
ciation | +3.122 |
CLASSIFIED | +3.067 |
Neg logit contributions | |
KN | -4.344 |
Kem | -4.273 |
Primal | -4.182 |
pel | -4.114 |
Stephenson | -4.028 |
Token | ym |
Token ID | 4948 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
wagen | +3.759 |
alore | +3.373 |
thia | +3.311 |
ciation | +3.057 |
akeru | +3.049 |
Neg logit contributions | |
KN | -4.347 |
Kem | -4.255 |
Primal | -4.167 |
pel | -4.136 |
Stephenson | -4.029 |
Token | ethyl |
Token ID | 21610 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wagen | +4.746 |
thia | +4.240 |
alore | +4.200 |
ciation | +3.904 |
akeru | +3.744 |
Neg logit contributions | |
KN | -5.280 |
Kem | -5.137 |
Primal | -5.027 |
Stephenson | -4.863 |
Emin | -4.856 |
Token | phen |
Token ID | 31024 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
wagen | +8.412 |
thia | +7.438 |
alore | +7.281 |
ciation | +6.898 |
akeru | +6.785 |
Neg logit contributions | |
KN | -8.979 |
Kem | -8.744 |
Primal | -8.564 |
Emin | -8.439 |
pel | -8.351 |
Token | yl |
Token ID | 2645 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
wagen | +8.990 |
thia | +8.542 |
alore | +8.285 |
ciation | +7.826 |
azine | +7.712 |
Neg logit contributions | |
KN | -6.133 |
Primal | -5.826 |
Kem | -5.782 |
pel | -5.482 |
Emin | -5.370 |
Token | )- |
Token ID | 13219 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
wagen | +4.745 |
thia | +4.178 |
alore | +4.130 |
ciation | +3.822 |
akeru | +3.769 |
Neg logit contributions | |
KN | -5.753 |
Kem | -5.609 |
Primal | -5.491 |
pel | -5.466 |
Emin | -5.397 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
wagen | +5.311 |
thia | +4.804 |
alore | +4.770 |
CLASSIFIED | +4.473 |
ciation | +4.463 |
Neg logit contributions | |
KN | -4.718 |
Kem | -4.672 |
Primal | -4.598 |
pel | -4.531 |
Emin | -4.423 |
Token | - |
Token ID | 12 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
wagen | +2.429 |
alore | +2.167 |
thia | +2.133 |
CLASSIFIED | +2.051 |
ciation | +2.024 |
Neg logit contributions | |
KN | -2.289 |
Kem | -2.237 |
pel | -2.223 |
Primal | -2.191 |
hower | -2.112 |
Token | phen |
Token ID | 31024 |
Feature activation | +9.88e+00 |
Pos logit contributions | |
wagen | +8.412 |
thia | +7.438 |
alore | +7.281 |
ciation | +6.898 |
akeru | +6.785 |
Neg logit contributions | |
KN | -8.979 |
Kem | -8.744 |
Primal | -8.564 |
Emin | -8.439 |
pel | -8.351 |
Token | yl |
Token ID | 2645 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
wagen | +8.990 |
thia | +8.542 |
alore | +8.285 |
ciation | +7.826 |
azine | +7.712 |
Neg logit contributions | |
KN | -6.133 |
Primal | -5.826 |
Kem | -5.782 |
pel | -5.482 |
Emin | -5.370 |
Token | )- |
Token ID | 13219 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
wagen | +4.745 |
thia | +4.178 |
alore | +4.130 |
ciation | +3.822 |
akeru | +3.769 |
Neg logit contributions | |
KN | -5.753 |
Kem | -5.609 |
Primal | -5.491 |
pel | -5.466 |
Emin | -5.397 |
Token | 2 |
Token ID | 17 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
wagen | +5.311 |
thia | +4.804 |
alore | +4.770 |
CLASSIFIED | +4.473 |
ciation | +4.463 |
Neg logit contributions | |
KN | -4.718 |
Kem | -4.672 |
Primal | -4.598 |
pel | -4.531 |
Emin | -4.423 |
Token | - |
Token ID | 12 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
wagen | +2.429 |
alore | +2.167 |
thia | +2.133 |
CLASSIFIED | +2.051 |
ciation | +2.024 |
Neg logit contributions | |
KN | -2.289 |
Kem | -2.237 |
pel | -2.223 |
Primal | -2.191 |
hower | -2.112 |
Token | ethyl |
Token ID | 21610 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wagen | +1.825 |
alore | +1.639 |
thia | +1.627 |
CLASSIFIED | +1.554 |
ciation | +1.547 |
Neg logit contributions | |
KN | -1.419 |
Kem | -1.380 |
pel | -1.351 |
Primal | -1.350 |
Stephenson | -1.292 |
Token | - |
Token ID | 12 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
wagen | +9.186 |
thia | +8.356 |
alore | +8.242 |
ciation | +7.761 |
azine | +7.566 |
Neg logit contributions | |
KN | -8.129 |
Kem | -7.802 |
Primal | -7.709 |
hower | -7.515 |
Emin | -7.444 |
Token | N |
Token ID | 45 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
wagen | +5.834 |
thia | +5.327 |
alore | +5.274 |
ciation | +4.912 |
CLASSIFIED | +4.863 |
Neg logit contributions | |
KN | -5.322 |
Kem | -5.237 |
Primal | -5.158 |
pel | -5.043 |
Emin | -4.981 |
Token | -( |
Token ID | 30420 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
wagen | +5.347 |
alore | +4.814 |
thia | +4.693 |
CLASSIFIED | +4.467 |
ciation | +4.357 |
Neg logit contributions | |
KN | -5.974 |
Kem | -5.950 |
Primal | -5.880 |
pel | -5.789 |
hower | -5.689 |
Token | t |
Token ID | 83 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
wagen | +3.988 |
thia | +3.583 |
alore | +3.577 |
CLASSIFIED | +3.391 |
ciation | +3.370 |
Neg logit contributions | |
KN | -3.346 |
Kem | -3.297 |
Primal | -3.215 |
pel | -3.172 |
Emin | -3.087 |
Token | et |
Token ID | 316 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
wagen | +5.046 |
alore | +4.698 |
thia | +4.605 |
akeru | +4.439 |
Wo | +4.424 |
Neg logit contributions | |
KN | -2.444 |
Kem | -2.362 |
Primal | -2.289 |
pel | -2.265 |
Emin | -2.233 |
Token | Ontario |
Token ID | 10553 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
KN | +2.730 |
Kem | +2.668 |
pel | +2.598 |
Primal | +2.583 |
Stephenson | +2.498 |
Neg logit contributions | |
wagen | -3.237 |
alore | -2.911 |
thia | -2.838 |
CLASSIFIED | -2.753 |
ciation | -2.738 |
Token | Ltd |
Token ID | 12052 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
wagen | +1.862 |
alore | +1.640 |
thia | +1.635 |
CLASSIFIED | +1.576 |
ciation | +1.551 |
Neg logit contributions | |
KN | -1.679 |
Kem | -1.622 |
pel | -1.621 |
Primal | -1.591 |
hower | -1.530 |
Token | ., |
Token ID | 1539 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
wagen | +0.725 |
alore | +0.645 |
thia | +0.640 |
CLASSIFIED | +0.620 |
ciation | +0.611 |
Neg logit contributions | |
KN | -0.569 |
Kem | -0.552 |
pel | -0.547 |
Primal | -0.540 |
Emin | -0.514 |
Token | a |
Token ID | 257 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
KN | +0.437 |
Kem | +0.427 |
pel | +0.419 |
Primal | +0.415 |
Stephenson | +0.397 |
Neg logit contributions | |
wagen | -0.580 |
alore | -0.520 |
thia | -0.514 |
CLASSIFIED | -0.500 |
ciation | -0.492 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
wagen | +3.378 |
alore | +2.994 |
thia | +2.977 |
CLASSIFIED | +2.852 |
ciation | +2.830 |
Neg logit contributions | |
KN | -2.676 |
pel | -2.569 |
Kem | -2.526 |
Primal | -2.495 |
hower | -2.438 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
wagen | +4.226 |
alore | +3.665 |
thia | +3.644 |
CLASSIFIED | +3.503 |
ciation | +3.454 |
Neg logit contributions | |
KN | -4.059 |
pel | -3.943 |
Kem | -3.885 |
Primal | -3.832 |
hower | -3.733 |
Token | based |
Token ID | 3106 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
wagen | +7.509 |
alore | +6.435 |
thia | +6.257 |
ciation | +6.002 |
CLASSIFIED | +5.980 |
Neg logit contributions | |
KN | -9.521 |
Primal | -9.480 |
Kem | -9.260 |
hower | -9.165 |
Emin | -9.052 |
Token | holding |
Token ID | 4769 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
wagen | +5.462 |
alore | +4.796 |
thia | +4.749 |
ciation | +4.562 |
CLASSIFIED | +4.537 |
Neg logit contributions | |
KN | -4.540 |
pel | -4.360 |
Primal | -4.185 |
Kem | -4.182 |
hower | -4.165 |
Token | company |
Token ID | 1664 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
KN | +0.077 |
Kem | +0.075 |
pel | +0.074 |
Primal | +0.073 |
Stephenson | +0.071 |
Neg logit contributions | |
wagen | -0.085 |
alore | -0.076 |
thia | -0.075 |
CLASSIFIED | -0.072 |
ciation | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
wagen | +1.137 |
alore | +1.014 |
thia | +1.000 |
CLASSIFIED | +0.970 |
ciation | +0.960 |
Neg logit contributions | |
KN | -0.909 |
Kem | -0.878 |
pel | -0.874 |
Primal | -0.862 |
hower | -0.824 |
Token | which |
Token ID | 543 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
wagen | +1.131 |
alore | +1.010 |
thia | +0.998 |
CLASSIFIED | +0.968 |
ciation | +0.958 |
Neg logit contributions | |
KN | -0.874 |
Kem | -0.844 |
pel | -0.840 |
Primal | -0.826 |
hower | -0.793 |
Token |
|
Token ID | 198 |
Feature activation | +1.25e+01 |
Pos logit contributions | |
wagen | +1.493 |
alore | +1.339 |
thia | +1.324 |
CLASSIFIED | +1.285 |
ciation | +1.268 |
Neg logit contributions | |
KN | -1.111 |
Kem | -1.081 |
pel | -1.066 |
Primal | -1.053 |
Stephenson | -1.004 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
wagen | +6.066 |
CLASSIFIED | +5.365 |
thia | +5.300 |
Wo | +5.083 |
alore | +4.862 |
Neg logit contributions | |
Primal | -11.973 |
Kem | -11.819 |
Stephenson | -11.689 |
KN | -11.591 |
hower | -11.552 |
Token | Lee |
Token ID | 5741 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
wagen | +3.335 |
thia | +3.026 |
alore | +2.996 |
ciation | +2.859 |
CLASSIFIED | +2.846 |
Neg logit contributions | |
KN | -2.758 |
pel | -2.677 |
Kem | -2.599 |
Primal | -2.572 |
hower | -2.532 |
Token | Pace |
Token ID | 44111 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Kem | +1.714 |
KN | +1.685 |
Primal | +1.606 |
pel | +1.604 |
Stephenson | +1.562 |
Neg logit contributions | |
wagen | -3.130 |
alore | -2.837 |
CLASSIFIED | -2.809 |
thia | -2.777 |
ciation | -2.706 |
Token |
|
Token ID | 198 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
wagen | +1.674 |
alore | +1.486 |
thia | +1.483 |
CLASSIFIED | +1.422 |
ciation | +1.418 |
Neg logit contributions | |
KN | -1.374 |
Kem | -1.326 |
pel | -1.319 |
Primal | -1.298 |
Emin | -1.234 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
KN | +0.275 |
Kem | +0.267 |
pel | +0.263 |
Primal | +0.259 |
Ike | +0.247 |
Neg logit contributions | |
wagen | -0.413 |
alore | -0.372 |
thia | -0.364 |
CLASSIFIED | -0.363 |
ciation | -0.351 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
wagen | +5.922 |
CLASSIFIED | +5.195 |
thia | +5.155 |
Wo | +4.911 |
alore | +4.874 |
Neg logit contributions | |
Primal | -10.998 |
Kem | -10.836 |
Stephenson | -10.718 |
KN | -10.697 |
hower | -10.605 |
Token | Tony |
Token ID | 8832 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
wagen | +3.054 |
thia | +2.762 |
alore | +2.739 |
ciation | +2.617 |
CLASSIFIED | +2.608 |
Neg logit contributions | |
KN | -2.464 |
pel | -2.384 |
Kem | -2.318 |
Primal | -2.297 |
hower | -2.253 |
Token | Shal |
Token ID | 47974 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
wagen | +1.588 |
alore | +1.367 |
thia | +1.357 |
CLASSIFIED | +1.281 |
ciation | +1.266 |
Neg logit contributions | |
KN | -2.283 |
Kem | -2.225 |
pel | -2.215 |
Primal | -2.181 |
hower | -2.119 |
Token | h |
Token ID | 71 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
wagen | +0.068 |
alore | +0.060 |
CLASSIFIED | +0.059 |
thia | +0.059 |
ciation | +0.056 |
Neg logit contributions | |
KN | -0.067 |
pel | -0.065 |
Kem | -0.065 |
Primal | -0.064 |
hower | -0.061 |
Token | oub |
Token ID | 12944 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
wagen | +1.563 |
alore | +1.409 |
thia | +1.395 |
CLASSIFIED | +1.354 |
ciation | +1.338 |
Neg logit contributions | |
KN | -1.038 |
Kem | -1.008 |
pel | -0.992 |
Primal | -0.980 |
Stephenson | -0.931 |
Token | United |
Token ID | 1578 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
KN | +0.716 |
Kem | +0.703 |
pel | +0.689 |
Primal | +0.686 |
Stephenson | +0.658 |
Neg logit contributions | |
wagen | -0.780 |
alore | -0.691 |
thia | -0.683 |
CLASSIFIED | -0.662 |
ciation | -0.650 |
Token | Nations |
Token ID | 7973 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
wagen | +3.106 |
thia | +2.745 |
alore | +2.737 |
CLASSIFIED | +2.647 |
ciation | +2.639 |
Neg logit contributions | |
KN | -2.572 |
pel | -2.465 |
Kem | -2.455 |
Primal | -2.397 |
hower | -2.351 |
Token | Development |
Token ID | 7712 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
wagen | +3.619 |
alore | +3.147 |
thia | +3.135 |
CLASSIFIED | +3.075 |
ciation | +3.028 |
Neg logit contributions | |
KN | -3.101 |
pel | -3.014 |
Kem | -2.989 |
Primal | -2.919 |
hower | -2.815 |
Token | Programme |
Token ID | 35232 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
wagen | +0.793 |
alore | +0.673 |
thia | +0.663 |
CLASSIFIED | +0.638 |
ciation | +0.623 |
Neg logit contributions | |
KN | -1.143 |
Kem | -1.121 |
pel | -1.110 |
Primal | -1.097 |
Stephenson | -1.064 |
Token | ( |
Token ID | 357 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
wagen | +1.443 |
alore | +1.282 |
thia | +1.264 |
CLASSIFIED | +1.227 |
ciation | +1.214 |
Neg logit contributions | |
KN | -1.266 |
Kem | -1.234 |
pel | -1.229 |
Primal | -1.205 |
Stephenson | -1.152 |
Token | UN |
Token ID | 4944 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
KN | +2.786 |
pel | +2.673 |
Kem | +2.655 |
Primal | +2.625 |
hower | +2.533 |
Neg logit contributions | |
wagen | -2.109 |
alore | -1.826 |
thia | -1.809 |
ciation | -1.701 |
CLASSIFIED | -1.690 |
Token | DP |
Token ID | 6322 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
wagen | +5.821 |
CLASSIFIED | +4.986 |
Wo | +4.710 |
thia | +4.696 |
PASS | +4.542 |
Neg logit contributions | |
Kem | -10.910 |
Primal | -10.816 |
pel | -10.767 |
Stephenson | -10.738 |
KN | -10.355 |
Token | ), |
Token ID | 828 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
wagen | +2.952 |
alore | +2.595 |
thia | +2.573 |
CLASSIFIED | +2.464 |
ciation | +2.461 |
Neg logit contributions | |
KN | -2.964 |
Kem | -2.933 |
pel | -2.912 |
Primal | -2.882 |
Emin | -2.773 |
Token | the |
Token ID | 262 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
wagen | +1.310 |
alore | +1.170 |
thia | +1.156 |
CLASSIFIED | +1.120 |
ciation | +1.107 |
Neg logit contributions | |
KN | -1.084 |
Kem | -1.047 |
pel | -1.043 |
Primal | -1.022 |
hower | -0.983 |
Token | Global |
Token ID | 8060 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
wagen | +0.818 |
alore | +0.727 |
thia | +0.718 |
CLASSIFIED | +0.694 |
ciation | +0.685 |
Neg logit contributions | |
KN | -0.730 |
Kem | -0.706 |
pel | -0.704 |
Primal | -0.691 |
hower | -0.664 |
Token | Environment |
Token ID | 9344 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
KN | +0.738 |
Kem | +0.728 |
pel | +0.713 |
Primal | +0.711 |
Stephenson | +0.680 |
Neg logit contributions | |
wagen | -0.804 |
alore | -0.718 |
thia | -0.706 |
CLASSIFIED | -0.685 |
ciation | -0.668 |
Token | e |
Token ID | 304 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
wagen | +1.694 |
alore | +1.504 |
thia | +1.489 |
CLASSIFIED | +1.432 |
ciation | +1.423 |
Neg logit contributions | |
KN | -1.483 |
Kem | -1.443 |
pel | -1.425 |
Primal | -1.408 |
Stephenson | -1.352 |
Token | . |
Token ID | 13 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
KN | +0.456 |
Kem | +0.441 |
pel | +0.440 |
Primal | +0.431 |
Stephenson | +0.411 |
Neg logit contributions | |
wagen | -0.557 |
alore | -0.497 |
thia | -0.487 |
CLASSIFIED | -0.485 |
ciation | -0.467 |
Token | g |
Token ID | 70 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
KN | +2.485 |
pel | +2.429 |
Primal | +2.249 |
Kem | +2.241 |
Emin | +2.046 |
Neg logit contributions | |
wagen | -7.029 |
CLASSIFIED | -6.534 |
alore | -6.453 |
thia | -6.303 |
ciation | -6.140 |
Token | .: |
Token ID | 11207 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
wagen | +0.991 |
alore | +0.848 |
thia | +0.834 |
CLASSIFIED | +0.796 |
ciation | +0.786 |
Neg logit contributions | |
KN | -1.412 |
Kem | -1.383 |
pel | -1.369 |
Primal | -1.355 |
Stephenson | -1.314 |
Token |
|
Token ID | 198 |
Feature activation | +8.00e+00 |
Pos logit contributions | |
wagen | +4.817 |
alore | +4.256 |
thia | +4.212 |
CLASSIFIED | +4.061 |
ciation | +4.050 |
Neg logit contributions | |
KN | -4.424 |
Kem | -4.346 |
pel | -4.224 |
Primal | -4.180 |
Stephenson | -4.072 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
wagen | +5.909 |
thia | +5.288 |
alore | +5.157 |
ciation | +4.973 |
Wo | +4.906 |
Neg logit contributions | |
KN | -6.141 |
Kem | -6.045 |
hower | -5.970 |
pel | -5.955 |
Primal | -5.911 |
Token | ruby |
Token ID | 49137 |
Feature activation | +9.07e+00 |
Pos logit contributions | |
wagen | +7.461 |
alore | +6.352 |
thia | +6.307 |
CLASSIFIED | +6.129 |
ciation | +5.894 |
Neg logit contributions | |
Kem | -9.607 |
KN | -9.387 |
Stephenson | -9.285 |
Primal | -9.176 |
Ike | -8.930 |
Token | print |
Token ID | 3601 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
wagen | +6.194 |
alore | +5.458 |
thia | +5.256 |
CLASSIFIED | +5.085 |
ciation | +5.065 |
Neg logit contributions | |
KN | -7.465 |
Kem | -7.211 |
pel | -7.098 |
Stephenson | -6.906 |
Primal | -6.888 |
Token | [ |
Token ID | 685 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
wagen | +3.940 |
alore | +3.405 |
thia | +3.380 |
CLASSIFIED | +3.281 |
ciation | +3.270 |
Neg logit contributions | |
KN | -4.079 |
Kem | -3.976 |
pel | -3.944 |
Primal | -3.831 |
Stephenson | -3.751 |
Token | 1 |
Token ID | 16 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
wagen | +1.247 |
alore | +1.101 |
thia | +1.095 |
CLASSIFIED | +1.064 |
ciation | +1.047 |
Neg logit contributions | |
KN | -1.092 |
Kem | -1.074 |
pel | -1.051 |
Primal | -1.042 |
Stephenson | -1.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
wagen | +0.266 |
alore | +0.237 |
thia | +0.234 |
CLASSIFIED | +0.227 |
ciation | +0.224 |
Neg logit contributions | |
KN | -0.226 |
Kem | -0.221 |
pel | -0.218 |
Primal | -0.215 |
Stephenson | -0.206 |
Token | Irvine |
Token ID | 37277 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
wagen | +1.527 |
alore | +1.362 |
thia | +1.353 |
CLASSIFIED | +1.300 |
ciation | +1.285 |
Neg logit contributions | |
KN | -1.307 |
Kem | -1.264 |
pel | -1.256 |
Primal | -1.237 |
Stephenson | -1.180 |
Token | , |
Token ID | 11 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
KN | +0.157 |
Kem | +0.153 |
pel | +0.151 |
Primal | +0.149 |
Stephenson | +0.143 |
Neg logit contributions | |
wagen | -0.191 |
alore | -0.170 |
thia | -0.168 |
CLASSIFIED | -0.163 |
ciation | -0.161 |
Token | California |
Token ID | 3442 |
Feature activation | +9.42e-01 |
Pos logit contributions | |
wagen | +0.651 |
alore | +0.585 |
thia | +0.579 |
CLASSIFIED | +0.561 |
ciation | +0.554 |
Neg logit contributions | |
KN | -0.480 |
Kem | -0.466 |
pel | -0.460 |
Primal | -0.454 |
Stephenson | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
wagen | +0.773 |
alore | +0.680 |
thia | +0.677 |
CLASSIFIED | +0.650 |
ciation | +0.642 |
Neg logit contributions | |
KN | -0.721 |
Kem | -0.699 |
pel | -0.692 |
Primal | -0.683 |
Emin | -0.656 |
Token | Hide |
Token ID | 10415 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
wagen | +4.447 |
thia | +4.026 |
alore | +3.995 |
ciation | +3.819 |
CLASSIFIED | +3.805 |
Neg logit contributions | |
KN | -3.319 |
pel | -3.202 |
Kem | -3.120 |
hower | -3.025 |
Primal | -3.014 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
wagen | +2.961 |
alore | +2.720 |
thia | +2.719 |
CLASSIFIED | +2.649 |
ciation | +2.627 |
Neg logit contributions | |
KN | -1.006 |
Kem | -0.946 |
pel | -0.935 |
Primal | -0.906 |
hower | -0.837 |
Token | 10 |
Token ID | 838 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
wagen | +7.276 |
thia | +6.993 |
Wo | +6.407 |
ciation | +6.348 |
alore | +6.291 |
Neg logit contributions | |
KN | -9.448 |
hower | -9.019 |
pel | -8.591 |
Kem | -8.171 |
ohyd | -8.171 |
Token | of |
Token ID | 286 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
KN | +0.152 |
Kem | +0.148 |
pel | +0.146 |
Primal | +0.144 |
Ike | +0.137 |
Neg logit contributions | |
wagen | -0.211 |
alore | -0.190 |
thia | -0.186 |
CLASSIFIED | -0.184 |
ciation | -0.179 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
KN | +1.428 |
Kem | +1.397 |
pel | +1.368 |
Primal | +1.351 |
Stephenson | +1.297 |
Neg logit contributions | |
wagen | -2.469 |
alore | -2.231 |
CLASSIFIED | -2.163 |
thia | -2.159 |
akeru | -2.082 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
KN | +0.637 |
Kem | +0.623 |
pel | +0.608 |
Primal | +0.607 |
Ike | +0.569 |
Neg logit contributions | |
wagen | -1.211 |
alore | -1.105 |
thia | -1.078 |
CLASSIFIED | -1.072 |
ciation | -1.040 |
Token | : |
Token ID | 25 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
wagen | +2.820 |
thia | +2.505 |
alore | +2.490 |
ciation | +2.367 |
CLASSIFIED | +2.341 |
Neg logit contributions | |
KN | -2.892 |
Kem | -2.819 |
pel | -2.796 |
Primal | -2.752 |
hower | -2.698 |
Token | Ocean |
Token ID | 10692 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
wagen | +2.195 |
alore | +1.941 |
thia | +1.927 |
CLASSIFIED | +1.855 |
ciation | +1.824 |
Neg logit contributions | |
KN | -2.215 |
Kem | -2.135 |
pel | -2.132 |
Primal | -2.082 |
hower | -2.028 |
Token | : |
Token ID | 25 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
wagen | +1.519 |
alore | +1.351 |
thia | +1.338 |
CLASSIFIED | +1.291 |
ciation | +1.272 |
Neg logit contributions | |
KN | -1.337 |
Kem | -1.291 |
pel | -1.283 |
Primal | -1.264 |
Stephenson | -1.214 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
wagen | +1.411 |
alore | +1.258 |
thia | +1.251 |
CLASSIFIED | +1.211 |
ciation | +1.197 |
Neg logit contributions | |
KN | -1.132 |
Kem | -1.094 |
pel | -1.090 |
Primal | -1.067 |
hower | -1.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
wagen | +3.114 |
thia | +2.783 |
alore | +2.771 |
ciation | +2.647 |
CLASSIFIED | +2.625 |
Neg logit contributions | |
KN | -2.599 |
Kem | -2.536 |
pel | -2.512 |
Primal | -2.476 |
hower | -2.416 |
Token | " |
Token ID | 1 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
wagen | +1.447 |
alore | +1.279 |
thia | +1.269 |
CLASSIFIED | +1.231 |
ciation | +1.209 |
Neg logit contributions | |
KN | -1.318 |
Kem | -1.296 |
pel | -1.275 |
Primal | -1.267 |
Stephenson | -1.216 |
Token | ' |
Token ID | 705 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
wagen | +4.156 |
thia | +3.650 |
alore | +3.626 |
CLASSIFIED | +3.558 |
ciation | +3.486 |
Neg logit contributions | |
Kem | -4.164 |
KN | -4.164 |
pel | -4.090 |
Primal | -4.063 |
hower | -3.991 |
Token | Never |
Token ID | 12295 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
wagen | +8.091 |
thia | +7.336 |
Wo | +7.275 |
CLASSIFIED | +7.149 |
alore | +7.082 |
Neg logit contributions | |
Kem | -8.143 |
KN | -8.143 |
hower | -8.046 |
pel | -8.003 |
Primal | -7.928 |
Token | ,' |
Token ID | 4032 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
wagen | +1.329 |
alore | +1.183 |
thia | +1.177 |
CLASSIFIED | +1.139 |
ciation | +1.130 |
Neg logit contributions | |
KN | -1.038 |
Kem | -1.005 |
pel | -0.992 |
Primal | -0.983 |
Stephenson | -0.940 |
Token | said |
Token ID | 531 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
wagen | +0.125 |
alore | +0.112 |
thia | +0.110 |
CLASSIFIED | +0.107 |
ciation | +0.106 |
Neg logit contributions | |
KN | -0.103 |
Kem | -0.101 |
pel | -0.100 |
Primal | -0.098 |
hower | -0.094 |
Token | Jack |
Token ID | 3619 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
wagen | +0.850 |
alore | +0.754 |
thia | +0.751 |
CLASSIFIED | +0.723 |
ciation | +0.716 |
Neg logit contributions | |
KN | -0.725 |
Kem | -0.700 |
pel | -0.698 |
Primal | -0.685 |
hower | -0.657 |
Token | . |
Token ID | 13 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
KN | +0.287 |
Kem | +0.280 |
pel | +0.276 |
Primal | +0.273 |
Stephenson | +0.261 |
Neg logit contributions | |
wagen | -0.349 |
alore | -0.311 |
thia | -0.308 |
CLASSIFIED | -0.298 |
ciation | -0.294 |
Token | the |
Token ID | 262 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
wagen | +0.757 |
alore | +0.666 |
thia | +0.657 |
CLASSIFIED | +0.635 |
ciation | +0.624 |
Neg logit contributions | |
KN | -0.775 |
Kem | -0.757 |
pel | -0.748 |
Primal | -0.741 |
Stephenson | -0.712 |
Token | thicker |
Token ID | 29175 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
wagen | +1.906 |
alore | +1.716 |
thia | +1.700 |
CLASSIFIED | +1.648 |
ciation | +1.632 |
Neg logit contributions | |
KN | -1.267 |
Kem | -1.226 |
pel | -1.213 |
Primal | -1.192 |
Stephenson | -1.134 |
Token | ring |
Token ID | 5858 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
wagen | +1.838 |
alore | +1.654 |
thia | +1.637 |
CLASSIFIED | +1.589 |
ciation | +1.568 |
Neg logit contributions | |
KN | -1.288 |
Kem | -1.250 |
pel | -1.234 |
Primal | -1.216 |
Stephenson | -1.158 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
wagen | +1.716 |
alore | +1.526 |
thia | +1.510 |
CLASSIFIED | +1.450 |
ciation | +1.433 |
Neg logit contributions | |
KN | -1.584 |
Kem | -1.543 |
pel | -1.528 |
Primal | -1.505 |
Stephenson | -1.452 |
Token | the |
Token ID | 262 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
wagen | +1.130 |
alore | +1.009 |
thia | +0.997 |
CLASSIFIED | +0.968 |
ciation | +0.952 |
Neg logit contributions | |
KN | -0.916 |
Kem | -0.892 |
pel | -0.882 |
Primal | -0.870 |
Stephenson | -0.832 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
wagen | +2.106 |
alore | +1.889 |
thia | +1.871 |
CLASSIFIED | +1.812 |
ciation | +1.788 |
Neg logit contributions | |
KN | -1.556 |
Kem | -1.512 |
pel | -1.499 |
Primal | -1.471 |
Stephenson | -1.407 |
Token | indicates |
Token ID | 9217 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
wagen | +7.795 |
thia | +7.080 |
alore | +6.853 |
ciation | +6.559 |
CLASSIFIED | +6.263 |
Neg logit contributions | |
KN | -8.497 |
Kem | -8.358 |
pel | -8.294 |
hower | -8.208 |
Stephenson | -8.124 |
Token | hours |
Token ID | 2250 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
wagen | +2.510 |
alore | +2.220 |
thia | +2.190 |
CLASSIFIED | +2.120 |
ciation | +2.089 |
Neg logit contributions | |
KN | -2.419 |
Kem | -2.346 |
pel | -2.341 |
Primal | -2.296 |
Stephenson | -2.207 |
Token | . |
Token ID | 13 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
wagen | +4.322 |
thia | +3.775 |
alore | +3.768 |
ciation | +3.712 |
CLASSIFIED | +3.645 |
Neg logit contributions | |
KN | -4.567 |
Kem | -4.460 |
pel | -4.430 |
Primal | -4.299 |
Stephenson | -4.239 |
Token | Cool |
Token ID | 15226 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
KN | +0.694 |
Kem | +0.680 |
Primal | +0.665 |
pel | +0.663 |
Stephenson | +0.633 |
Neg logit contributions | |
wagen | -0.863 |
alore | -0.776 |
thia | -0.760 |
CLASSIFIED | -0.740 |
ciation | -0.723 |
Token | LED |
Token ID | 12365 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
KN | +2.029 |
Kem | +1.984 |
Primal | +1.948 |
pel | +1.948 |
Emin | +1.855 |
Neg logit contributions | |
wagen | -2.458 |
alore | -2.203 |
thia | -2.187 |
CLASSIFIED | -2.121 |
ciation | -2.088 |
Token | appearing |
Token ID | 12655 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
KN | +1.174 |
Kem | +1.144 |
pel | +1.124 |
Primal | +1.115 |
Stephenson | +1.063 |
Neg logit contributions | |
wagen | -1.617 |
alore | -1.451 |
thia | -1.437 |
CLASSIFIED | -1.399 |
ciation | -1.381 |
Token | very |
Token ID | 845 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
KN | +1.521 |
Kem | +1.484 |
pel | +1.453 |
Primal | +1.451 |
Ike | +1.375 |
Neg logit contributions | |
wagen | -2.232 |
alore | -1.995 |
thia | -1.982 |
CLASSIFIED | -1.942 |
ciation | -1.906 |
Token | skinny |
Token ID | 29494 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
KN | +1.496 |
Kem | +1.463 |
pel | +1.433 |
Primal | +1.424 |
Stephenson | +1.346 |
Neg logit contributions | |
wagen | -2.367 |
alore | -2.129 |
thia | -2.104 |
CLASSIFIED | -2.073 |
ciation | -2.029 |
Token | , |
Token ID | 11 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
KN | +0.018 |
Kem | +0.018 |
pel | +0.017 |
Primal | +0.017 |
hower | +0.016 |
Neg logit contributions | |
wagen | -0.022 |
alore | -0.019 |
thia | -0.019 |
CLASSIFIED | -0.019 |
ciation | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -5.99e+00 |
Pos logit contributions | |
KN | +2.650 |
Kem | +2.605 |
pel | +2.535 |
Primal | +2.527 |
Ike | +2.398 |
Neg logit contributions | |
wagen | -4.075 |
alore | -3.647 |
thia | -3.645 |
CLASSIFIED | -3.606 |
ciation | -3.516 |
Token | his |
Token ID | 465 |
Feature activation | -1.27e+01 |
Pos logit contributions | |
KN | +3.558 |
Kem | +3.476 |
Primal | +3.401 |
pel | +3.399 |
Ike | +3.199 |
Neg logit contributions | |
wagen | -5.793 |
alore | -5.231 |
CLASSIFIED | -5.197 |
thia | -5.156 |
ciation | -5.135 |
Token | 30 |
Token ID | 1542 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
Kem | +5.658 |
Primal | +5.654 |
KN | +5.649 |
Isaac | +5.341 |
Emin | +5.338 |
Neg logit contributions | |
wagen | -13.454 |
CLASSIFIED | -12.325 |
alore | -12.250 |
thia | -12.034 |
akeru | -11.982 |
Token | s |
Token ID | 82 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
KN | +3.428 |
Kem | +3.304 |
pel | +3.253 |
Primal | +3.249 |
Emin | +3.107 |
Neg logit contributions | |
wagen | -4.282 |
alore | -3.858 |
thia | -3.761 |
CLASSIFIED | -3.689 |
ciation | -3.587 |
Token | , |
Token ID | 11 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
KN | +4.196 |
Kem | +4.130 |
pel | +4.042 |
Primal | +3.966 |
Ike | +3.832 |
Neg logit contributions | |
wagen | -6.311 |
alore | -5.710 |
thia | -5.594 |
CLASSIFIED | -5.547 |
ciation | -5.441 |
Token | standing |
Token ID | 5055 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
KN | +2.824 |
Kem | +2.775 |
Primal | +2.698 |
pel | +2.697 |
Ike | +2.569 |
Neg logit contributions | |
wagen | -4.127 |
alore | -3.698 |
thia | -3.688 |
CLASSIFIED | -3.647 |
ciation | -3.563 |
Token | 5 |
Token ID | 642 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
KN | +0.462 |
Kem | +0.450 |
pel | +0.442 |
Primal | +0.438 |
Stephenson | +0.416 |
Neg logit contributions | |
wagen | -0.667 |
alore | -0.601 |
thia | -0.594 |
CLASSIFIED | -0.579 |
ciation | -0.571 |
Token | 11 |
Token ID | 1367 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
wagen | +1.473 |
alore | +1.311 |
thia | +1.293 |
CLASSIFIED | +1.248 |
ciation | +1.234 |
Neg logit contributions | |
KN | -1.277 |
Kem | -1.240 |
pel | -1.225 |
Primal | -1.208 |
hower | -1.161 |
Token | : |
Token ID | 25 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
KN | +2.962 |
Kem | +2.889 |
pel | +2.816 |
Primal | +2.772 |
Ike | +2.676 |
Neg logit contributions | |
wagen | -3.566 |
alore | -3.257 |
thia | -3.153 |
CLASSIFIED | -3.108 |
ciation | -3.067 |
Token | 50 |
Token ID | 1120 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
KN | +2.213 |
Kem | +2.114 |
pel | +2.076 |
Primal | +2.064 |
Ike | +1.976 |
Neg logit contributions | |
wagen | -2.910 |
alore | -2.619 |
thia | -2.530 |
CLASSIFIED | -2.510 |
ciation | -2.443 |
Token | AM |
Token ID | 3001 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
KN | +2.204 |
Kem | +2.134 |
pel | +2.054 |
Primal | +2.016 |
Ike | +1.912 |
Neg logit contributions | |
wagen | -4.767 |
alore | -4.401 |
thia | -4.310 |
CLASSIFIED | -4.264 |
ciation | -4.182 |
Token | ET |
Token ID | 12152 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
KN | +1.292 |
Kem | +1.231 |
pel | +1.214 |
Primal | +1.188 |
Ike | +1.132 |
Neg logit contributions | |
wagen | -2.758 |
alore | -2.475 |
thia | -2.446 |
CLASSIFIED | -2.402 |
ciation | -2.392 |
Token | Fri |
Token ID | 19480 |
Feature activation | -1.22e+01 |
Pos logit contributions | |
KN | +2.359 |
Kem | +2.294 |
Primal | +2.232 |
pel | +2.231 |
Hass | +2.157 |
Neg logit contributions | |
wagen | -3.778 |
alore | -3.341 |
thia | -3.223 |
ciation | -3.138 |
CLASSIFIED | -3.121 |
Token | , |
Token ID | 11 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
KN | +6.074 |
Kem | +5.845 |
pel | +5.798 |
Hass | +5.751 |
Isaac | +5.699 |
Neg logit contributions | |
wagen | -12.290 |
alore | -11.285 |
ciation | -10.855 |
thia | -10.837 |
akeru | -10.768 |
Token | 28 |
Token ID | 2579 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
KN | +3.555 |
Kem | +3.550 |
Primal | +3.424 |
pel | +3.304 |
Ike | +3.298 |
Neg logit contributions | |
wagen | -6.551 |
alore | -5.957 |
thia | -5.708 |
CLASSIFIED | -5.666 |
akeru | -5.620 |
Token | July |
Token ID | 2901 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
KN | +3.059 |
Kem | +2.991 |
Primal | +2.916 |
pel | +2.903 |
Ike | +2.815 |
Neg logit contributions | |
wagen | -3.821 |
alore | -3.476 |
thia | -3.259 |
CLASSIFIED | -3.258 |
akeru | -3.221 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -6.78e+00 |
Pos logit contributions | |
KN | +2.044 |
Kem | +2.028 |
pel | +1.995 |
Primal | +1.967 |
Ike | +1.889 |
Neg logit contributions | |
wagen | -2.795 |
alore | -2.527 |
CLASSIFIED | -2.429 |
thia | -2.428 |
ciation | -2.378 |
Token | | |
Token ID | 930 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
KN | +4.004 |
Kem | +3.980 |
Primal | +3.811 |
pel | +3.767 |
Ike | +3.665 |
Neg logit contributions | |
wagen | -6.756 |
alore | -6.267 |
thia | -5.867 |
CLASSIFIED | -5.765 |
ciation | -5.747 |
Token | a |
Token ID | 257 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
wagen | +0.120 |
alore | +0.106 |
thia | +0.105 |
CLASSIFIED | +0.102 |
ciation | +0.101 |
Neg logit contributions | |
KN | -0.098 |
Kem | -0.095 |
pel | -0.094 |
Primal | -0.093 |
hower | -0.088 |
Token | time |
Token ID | 640 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
KN | +1.549 |
Kem | +1.511 |
pel | +1.487 |
Primal | +1.469 |
Stephenson | +1.388 |
Neg logit contributions | |
wagen | -2.836 |
alore | -2.590 |
thia | -2.569 |
CLASSIFIED | -2.493 |
ciation | -2.463 |
Token | ), |
Token ID | 828 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
KN | +1.603 |
Kem | +1.569 |
pel | +1.555 |
Primal | +1.534 |
Stephenson | +1.467 |
Neg logit contributions | |
wagen | -1.744 |
alore | -1.546 |
thia | -1.524 |
CLASSIFIED | -1.483 |
ciation | -1.452 |
Token | reduce |
Token ID | 4646 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
KN | +2.464 |
Kem | +2.414 |
pel | +2.391 |
Primal | +2.363 |
Stephenson | +2.250 |
Neg logit contributions | |
wagen | -3.015 |
alore | -2.700 |
thia | -2.671 |
CLASSIFIED | -2.589 |
ciation | -2.549 |
Token | heat |
Token ID | 4894 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
KN | +1.332 |
Kem | +1.313 |
pel | +1.286 |
Primal | +1.282 |
Stephenson | +1.218 |
Neg logit contributions | |
wagen | -1.768 |
alore | -1.585 |
thia | -1.568 |
CLASSIFIED | -1.536 |
ciation | -1.497 |
Token | to |
Token ID | 284 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
KN | +0.790 |
Kem | +0.770 |
pel | +0.759 |
Primal | +0.753 |
Stephenson | +0.714 |
Neg logit contributions | |
wagen | -1.107 |
alore | -0.996 |
thia | -0.986 |
CLASSIFIED | -0.961 |
ciation | -0.940 |
Token | low |
Token ID | 1877 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Kem | +4.289 |
pel | +4.197 |
KN | +4.162 |
Primal | +4.083 |
Ike | +3.681 |
Neg logit contributions | |
wagen | -13.355 |
alore | -12.812 |
thia | -12.697 |
akeru | -12.280 |
CLASSIFIED | -12.200 |
Token | and |
Token ID | 290 |
Feature activation | -7.37e+00 |
Pos logit contributions | |
KN | +2.764 |
Kem | +2.696 |
Primal | +2.659 |
pel | +2.645 |
Stephenson | +2.510 |
Neg logit contributions | |
wagen | -3.729 |
alore | -3.379 |
thia | -3.318 |
CLASSIFIED | -3.230 |
ciation | -3.176 |
Token | cook |
Token ID | 4255 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
KN | +4.831 |
Kem | +4.777 |
pel | +4.702 |
Primal | +4.684 |
Ike | +4.430 |
Neg logit contributions | |
wagen | -6.527 |
alore | -5.918 |
thia | -5.878 |
CLASSIFIED | -5.790 |
ciation | -5.659 |
Token | f |
Token ID | 277 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
KN | +2.285 |
Kem | +2.245 |
pel | +2.231 |
Primal | +2.224 |
Stephenson | +2.098 |
Neg logit contributions | |
wagen | -3.092 |
alore | -2.804 |
thia | -2.791 |
CLASSIFIED | -2.677 |
ciation | -2.628 |
Token | rit |
Token ID | 799 |
Feature activation | -4.25e+00 |
Pos logit contributions | |
KN | +1.277 |
pel | +1.237 |
Kem | +1.221 |
Primal | +1.181 |
Stephenson | +1.099 |
Neg logit contributions | |
wagen | -3.018 |
alore | -2.793 |
thia | -2.756 |
CLASSIFIED | -2.752 |
ciation | -2.672 |
Token | cuts |
Token ID | 6630 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
wagen | +1.630 |
alore | +1.461 |
thia | +1.436 |
CLASSIFIED | +1.393 |
ciation | +1.374 |
Neg logit contributions | |
KN | -1.295 |
Kem | -1.252 |
pel | -1.241 |
Primal | -1.222 |
hower | -1.177 |
Token | . |
Token ID | 13 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
KN | +0.217 |
Kem | +0.211 |
pel | +0.208 |
Primal | +0.206 |
Stephenson | +0.196 |
Neg logit contributions | |
wagen | -0.295 |
alore | -0.265 |
thia | -0.262 |
CLASSIFIED | -0.255 |
ciation | -0.251 |
Token |
|
Token ID | 198 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
KN | +0.252 |
Kem | +0.245 |
pel | +0.242 |
Primal | +0.239 |
Stephenson | +0.228 |
Neg logit contributions | |
wagen | -0.333 |
alore | -0.298 |
thia | -0.295 |
CLASSIFIED | -0.286 |
ciation | -0.282 |
Token |
|
Token ID | 198 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
wagen | +0.054 |
alore | +0.049 |
thia | +0.048 |
CLASSIFIED | +0.047 |
ciation | +0.046 |
Neg logit contributions | |
KN | -0.037 |
Kem | -0.036 |
pel | -0.036 |
Primal | -0.035 |
Ike | -0.033 |
Token | K |
Token ID | 42 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
KN | +0.030 |
Kem | +0.030 |
pel | +0.029 |
Primal | +0.029 |
Stephenson | +0.027 |
Neg logit contributions | |
wagen | -0.035 |
alore | -0.032 |
thia | -0.031 |
CLASSIFIED | -0.030 |
ciation | -0.030 |
Token | el |
Token ID | 417 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
KN | +2.599 |
pel | +2.520 |
Kem | +2.443 |
Primal | +2.317 |
Ike | +2.119 |
Neg logit contributions | |
wagen | -6.132 |
thia | -5.569 |
alore | -5.558 |
CLASSIFIED | -5.555 |
ciation | -5.482 |
Token | vin |
Token ID | 7114 |
Feature activation | -8.40e-01 |
Pos logit contributions | |
pel | +5.401 |
Kem | +5.334 |
KN | +5.062 |
Stephenson | +4.642 |
Primal | +4.280 |
Neg logit contributions | |
CLASSIFIED | -12.896 |
wagen | -12.809 |
ciation | -11.721 |
alore | -11.655 |
akeru | -11.487 |
Token | Shepherd |
Token ID | 30890 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
KN | +0.531 |
Kem | +0.517 |
pel | +0.508 |
Primal | +0.502 |
Stephenson | +0.477 |
Neg logit contributions | |
wagen | -0.800 |
alore | -0.723 |
thia | -0.714 |
CLASSIFIED | -0.695 |
ciation | -0.685 |
Token | says |
Token ID | 1139 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
KN | +0.575 |
Kem | +0.563 |
pel | +0.553 |
Primal | +0.548 |
Stephenson | +0.523 |
Neg logit contributions | |
wagen | -0.748 |
alore | -0.672 |
thia | -0.661 |
CLASSIFIED | -0.645 |
ciation | -0.635 |
Token | cuts |
Token ID | 6630 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
wagen | +0.212 |
alore | +0.190 |
thia | +0.188 |
CLASSIFIED | +0.183 |
ciation | +0.180 |
Neg logit contributions | |
KN | -0.151 |
Kem | -0.147 |
pel | -0.145 |
Primal | -0.143 |
Stephenson | -0.137 |
Token | could |
Token ID | 714 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
wagen | +0.586 |
alore | +0.524 |
thia | +0.518 |
CLASSIFIED | +0.502 |
ciation | +0.497 |
Neg logit contributions | |
KN | -0.446 |
Kem | -0.434 |
pel | -0.428 |
Primal | -0.423 |
Stephenson | -0.403 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
KN | +0.346 |
Kem | +0.339 |
pel | +0.334 |
Primal | +0.330 |
Stephenson | +0.316 |
Neg logit contributions | |
wagen | -0.420 |
alore | -0.375 |
thia | -0.370 |
CLASSIFIED | -0.361 |
ciation | -0.353 |
Token | which |
Token ID | 543 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
wagen | +2.174 |
alore | +1.934 |
thia | +1.900 |
CLASSIFIED | +1.832 |
ciation | +1.831 |
Neg logit contributions | |
KN | -1.889 |
Kem | -1.822 |
pel | -1.814 |
Primal | -1.785 |
hower | -1.725 |
Token | is |
Token ID | 318 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
wagen | +2.548 |
alore | +2.271 |
thia | +2.230 |
CLASSIFIED | +2.144 |
ciation | +2.141 |
Neg logit contributions | |
KN | -2.155 |
Kem | -2.069 |
pel | -2.062 |
Primal | -2.024 |
hower | -1.946 |
Token | the |
Token ID | 262 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
wagen | +1.020 |
alore | +0.910 |
thia | +0.899 |
CLASSIFIED | +0.869 |
ciation | +0.858 |
Neg logit contributions | |
KN | -0.851 |
Kem | -0.826 |
pel | -0.817 |
Primal | -0.806 |
Stephenson | -0.770 |
Token | bread |
Token ID | 8509 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
wagen | +1.751 |
alore | +1.571 |
thia | +1.555 |
CLASSIFIED | +1.499 |
ciation | +1.485 |
Neg logit contributions | |
KN | -1.310 |
Kem | -1.261 |
pel | -1.250 |
Primal | -1.227 |
hower | -1.178 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
KN | +0.548 |
Kem | +0.534 |
pel | +0.529 |
Primal | +0.522 |
Stephenson | +0.500 |
Neg logit contributions | |
wagen | -0.622 |
alore | -0.552 |
thia | -0.547 |
CLASSIFIED | -0.531 |
ciation | -0.519 |
Token | butter |
Token ID | 9215 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
Primal | +2.646 |
Kem | +2.628 |
pel | +2.560 |
Isaac | +2.483 |
KN | +2.413 |
Neg logit contributions | |
wagen | -15.930 |
CLASSIFIED | -14.388 |
alore | -14.298 |
thia | -14.164 |
akeru | -13.795 |
Token | for |
Token ID | 329 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
KN | +1.657 |
Kem | +1.644 |
pel | +1.607 |
Primal | +1.604 |
Stephenson | +1.517 |
Neg logit contributions | |
wagen | -2.330 |
alore | -2.094 |
thia | -2.084 |
CLASSIFIED | -2.056 |
ciation | -1.975 |
Token | these |
Token ID | 777 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
KN | +1.344 |
Kem | +1.336 |
pel | +1.294 |
Primal | +1.293 |
Ike | +1.234 |
Neg logit contributions | |
wagen | -1.901 |
alore | -1.705 |
thia | -1.700 |
CLASSIFIED | -1.664 |
ciation | -1.623 |
Token | guys |
Token ID | 3730 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
KN | +1.120 |
Kem | +1.112 |
pel | +1.085 |
Primal | +1.078 |
Stephenson | +1.035 |
Neg logit contributions | |
wagen | -1.324 |
alore | -1.176 |
thia | -1.172 |
CLASSIFIED | -1.145 |
ciation | -1.119 |
Token | . |
Token ID | 13 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
KN | +0.297 |
Kem | +0.291 |
pel | +0.287 |
Primal | +0.283 |
Stephenson | +0.271 |
Neg logit contributions | |
wagen | -0.345 |
alore | -0.307 |
thia | -0.304 |
CLASSIFIED | -0.295 |
ciation | -0.290 |
Token | favorite |
Token ID | 4004 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
wagen | +1.418 |
alore | +1.262 |
thia | +1.252 |
CLASSIFIED | +1.209 |
ciation | +1.194 |
Neg logit contributions | |
KN | -1.157 |
Kem | -1.117 |
pel | -1.105 |
Primal | -1.091 |
hower | -1.044 |
Token | - |
Token ID | 532 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
wagen | +1.992 |
alore | +1.759 |
thia | +1.745 |
CLASSIFIED | +1.685 |
ciation | +1.662 |
Neg logit contributions | |
KN | -1.811 |
Kem | -1.750 |
pel | -1.734 |
Primal | -1.714 |
hower | -1.639 |
Token | July |
Token ID | 2901 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
wagen | +3.419 |
thia | +3.035 |
alore | +3.012 |
CLASSIFIED | +2.876 |
ciation | +2.829 |
Neg logit contributions | |
KN | -3.546 |
pel | -3.479 |
Kem | -3.407 |
hower | -3.356 |
Primal | -3.340 |
Token | 6 |
Token ID | 718 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
wagen | +0.041 |
alore | +0.037 |
thia | +0.037 |
CLASSIFIED | +0.036 |
ciation | +0.035 |
Neg logit contributions | |
KN | -0.027 |
Kem | -0.026 |
pel | -0.026 |
Primal | -0.025 |
Stephenson | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
wagen | +0.797 |
alore | +0.712 |
thia | +0.699 |
CLASSIFIED | +0.686 |
ciation | +0.670 |
Neg logit contributions | |
KN | -0.634 |
Kem | -0.618 |
pel | -0.609 |
Primal | -0.603 |
Stephenson | -0.574 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
KN | +0.619 |
Kem | +0.602 |
pel | +0.595 |
Primal | +0.588 |
Stephenson | +0.562 |
Neg logit contributions | |
wagen | -0.724 |
alore | -0.644 |
thia | -0.637 |
CLASSIFIED | -0.617 |
ciation | -0.608 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
KN | +5.113 |
Kem | +4.977 |
Primal | +4.799 |
pel | +4.669 |
Ike | +4.568 |
Neg logit contributions | |
wagen | -13.012 |
CLASSIFIED | -12.106 |
alore | -11.810 |
akeru | -11.340 |
thia | -11.156 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
KN | +0.428 |
Kem | +0.415 |
pel | +0.409 |
Primal | +0.404 |
Ike | +0.383 |
Neg logit contributions | |
wagen | -0.649 |
alore | -0.586 |
thia | -0.573 |
CLASSIFIED | -0.572 |
ciation | -0.552 |
Token | Subject |
Token ID | 19776 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
wagen | +1.648 |
alore | +1.427 |
thia | +1.401 |
CLASSIFIED | +1.346 |
ciation | +1.325 |
Neg logit contributions | |
KN | -2.099 |
Kem | -2.050 |
pel | -2.032 |
Primal | -2.011 |
Stephenson | -1.936 |
Token | : |
Token ID | 25 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
wagen | +3.560 |
thia | +3.148 |
alore | +3.096 |
ciation | +2.963 |
CLASSIFIED | +2.893 |
Neg logit contributions | |
KN | -3.794 |
Kem | -3.688 |
pel | -3.639 |
Primal | -3.602 |
hower | -3.522 |
Token | R |
Token ID | 371 |
Feature activation | +5.59e+00 |
Pos logit contributions | |
KN | +0.956 |
Kem | +0.938 |
pel | +0.921 |
Primal | +0.914 |
Stephenson | +0.874 |
Neg logit contributions | |
wagen | -1.152 |
alore | -1.030 |
thia | -1.014 |
CLASSIFIED | -0.983 |
ciation | -0.970 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
wagen | +3.013 |
thia | +2.661 |
alore | +2.654 |
ciation | +2.529 |
CLASSIFIED | +2.491 |
Neg logit contributions | |
KN | -2.948 |
Kem | -2.896 |
pel | -2.850 |
Primal | -2.835 |
hower | -2.742 |
Token | ed |
Token ID | 276 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
KN | +1.120 |
Kem | +1.086 |
pel | +1.085 |
Primal | +1.049 |
hower | +1.017 |
Neg logit contributions | |
wagen | -1.359 |
alore | -1.216 |
thia | -1.199 |
CLASSIFIED | -1.172 |
ciation | -1.147 |
Token | wards |
Token ID | 2017 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
KN | +0.630 |
Kem | +0.615 |
pel | +0.615 |
Primal | +0.603 |
hower | +0.587 |
Neg logit contributions | |
wagen | -0.415 |
alore | -0.352 |
thia | -0.342 |
CLASSIFIED | -0.339 |
ciation | -0.323 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
KN | +3.982 |
pel | +3.899 |
Kem | +3.798 |
hower | +3.686 |
Primal | +3.634 |
Neg logit contributions | |
wagen | -5.316 |
alore | -4.758 |
CLASSIFIED | -4.753 |
thia | -4.705 |
ciation | -4.525 |
Token | af |
Token ID | 1878 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
KN | +2.157 |
pel | +2.088 |
Kem | +2.069 |
Primal | +1.997 |
hower | +1.954 |
Neg logit contributions | |
wagen | -3.122 |
alore | -2.790 |
thia | -2.770 |
CLASSIFIED | -2.728 |
ciation | -2.669 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
wagen | +2.303 |
alore | +2.033 |
thia | +2.025 |
ciation | +1.920 |
CLASSIFIED | +1.907 |
Neg logit contributions | |
KN | -2.185 |
Kem | -2.136 |
pel | -2.100 |
Primal | -2.092 |
Stephenson | -2.013 |
Token | mil |
Token ID | 25433 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
pel | +4.465 |
KN | +4.046 |
Kem | +3.601 |
ohyd | +3.597 |
Primal | +3.530 |
Neg logit contributions | |
wagen | -12.971 |
CLASSIFIED | -12.519 |
alore | -11.732 |
thia | -11.706 |
akeru | -11.547 |
Token | / |
Token ID | 14 |
Feature activation | -6.04e+00 |
Pos logit contributions | |
KN | +0.094 |
Kem | +0.092 |
pel | +0.091 |
Primal | +0.090 |
Stephenson | +0.087 |
Neg logit contributions | |
wagen | -0.091 |
alore | -0.080 |
thia | -0.079 |
CLASSIFIED | -0.076 |
ciation | -0.075 |
Token | gallery |
Token ID | 24460 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
KN | +4.604 |
pel | +4.481 |
Kem | +4.467 |
Primal | +4.255 |
hower | +4.248 |
Neg logit contributions | |
wagen | -4.718 |
alore | -4.237 |
thia | -4.145 |
CLASSIFIED | -4.086 |
ciation | -3.947 |
Token | / |
Token ID | 14 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
KN | +1.398 |
Kem | +1.362 |
pel | +1.347 |
Primal | +1.327 |
Stephenson | +1.281 |
Neg logit contributions | |
wagen | -1.468 |
alore | -1.305 |
thia | -1.284 |
CLASSIFIED | -1.246 |
ciation | -1.220 |
Token | ye |
Token ID | 5948 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
KN | +2.574 |
pel | +2.500 |
Kem | +2.477 |
Primal | +2.388 |
hower | +2.339 |
Neg logit contributions | |
wagen | -2.652 |
alore | -2.382 |
thia | -2.335 |
CLASSIFIED | -2.277 |
ciation | -2.226 |
Token | favorite |
Token ID | 4004 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
wagen | +2.302 |
alore | +2.034 |
thia | +2.019 |
CLASSIFIED | +1.956 |
ciation | +1.929 |
Neg logit contributions | |
KN | -2.023 |
Kem | -1.953 |
pel | -1.930 |
Primal | -1.911 |
hower | -1.827 |
Token | - |
Token ID | 532 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
wagen | +2.198 |
alore | +1.921 |
thia | +1.907 |
CLASSIFIED | +1.839 |
ciation | +1.812 |
Neg logit contributions | |
KN | -2.254 |
Kem | -2.181 |
pel | -2.161 |
Primal | -2.141 |
hower | -2.054 |
Token | January |
Token ID | 3269 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
wagen | +2.366 |
thia | +2.097 |
alore | +2.090 |
CLASSIFIED | +2.004 |
ciation | +1.969 |
Neg logit contributions | |
KN | -2.239 |
pel | -2.177 |
Kem | -2.159 |
Primal | -2.123 |
hower | -2.092 |
Token | 15 |
Token ID | 1315 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
KN | +0.831 |
Kem | +0.817 |
Primal | +0.791 |
pel | +0.790 |
Stephenson | +0.751 |
Neg logit contributions | |
wagen | -1.347 |
alore | -1.217 |
thia | -1.192 |
CLASSIFIED | -1.181 |
ciation | -1.153 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
wagen | +0.970 |
alore | +0.866 |
thia | +0.853 |
CLASSIFIED | +0.833 |
ciation | +0.816 |
Neg logit contributions | |
KN | -0.785 |
Kem | -0.765 |
pel | -0.754 |
Primal | -0.746 |
Stephenson | -0.711 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
KN | +0.840 |
Kem | +0.819 |
pel | +0.809 |
Primal | +0.800 |
Stephenson | +0.766 |
Neg logit contributions | |
wagen | -0.964 |
alore | -0.857 |
thia | -0.847 |
CLASSIFIED | -0.820 |
ciation | -0.808 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
KN | +5.146 |
Kem | +4.989 |
Primal | +4.815 |
pel | +4.600 |
Ike | +4.585 |
Neg logit contributions | |
wagen | -12.838 |
CLASSIFIED | -11.878 |
alore | -11.655 |
akeru | -11.145 |
thia | -10.993 |
Token |
|
Token ID | 198 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
KN | +0.804 |
Kem | +0.779 |
pel | +0.765 |
Primal | +0.758 |
Ike | +0.718 |
Neg logit contributions | |
wagen | -1.259 |
alore | -1.137 |
CLASSIFIED | -1.116 |
thia | -1.109 |
ciation | -1.071 |
Token | Subject |
Token ID | 19776 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
wagen | +1.956 |
alore | +1.688 |
thia | +1.665 |
CLASSIFIED | +1.599 |
ciation | +1.565 |
Neg logit contributions | |
KN | -2.578 |
Kem | -2.530 |
pel | -2.502 |
Primal | -2.480 |
Stephenson | -2.398 |
Token | : |
Token ID | 25 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
wagen | +3.544 |
thia | +3.138 |
alore | +3.089 |
ciation | +2.956 |
CLASSIFIED | +2.881 |
Neg logit contributions | |
KN | -3.792 |
Kem | -3.694 |
pel | -3.640 |
Primal | -3.604 |
hower | -3.524 |
Token | Que |
Token ID | 4670 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
KN | +1.243 |
Kem | +1.220 |
pel | +1.196 |
Primal | +1.190 |
Stephenson | +1.136 |
Neg logit contributions | |
wagen | -1.484 |
alore | -1.325 |
thia | -1.303 |
CLASSIFIED | -1.264 |
ciation | -1.247 |
Token | 00 |
Token ID | 405 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
wagen | +0.327 |
alore | +0.290 |
thia | +0.286 |
CLASSIFIED | +0.277 |
ciation | +0.272 |
Neg logit contributions | |
KN | -0.300 |
Kem | -0.292 |
pel | -0.289 |
Primal | -0.286 |
Stephenson | -0.273 |
Token | 96 |
Token ID | 4846 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
wagen | +0.125 |
alore | +0.112 |
thia | +0.110 |
CLASSIFIED | +0.107 |
ciation | +0.106 |
Neg logit contributions | |
KN | -0.097 |
Kem | -0.094 |
pel | -0.093 |
Primal | -0.092 |
Stephenson | -0.087 |
Token | 275 |
Token ID | 23195 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
wagen | +3.151 |
thia | +2.797 |
alore | +2.792 |
ciation | +2.684 |
CLASSIFIED | +2.680 |
Neg logit contributions | |
KN | -2.592 |
Kem | -2.562 |
pel | -2.536 |
Primal | -2.513 |
Stephenson | -2.395 |
Token | . |
Token ID | 13 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
wagen | +0.470 |
alore | +0.421 |
thia | +0.413 |
CLASSIFIED | +0.403 |
ciation | +0.395 |
Neg logit contributions | |
KN | -0.398 |
Kem | -0.388 |
pel | -0.381 |
Primal | -0.379 |
Stephenson | -0.362 |
Token | g |
Token ID | 70 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
KN | +2.258 |
pel | +2.213 |
Kem | +2.203 |
Primal | +2.162 |
Stephenson | +1.952 |
Neg logit contributions | |
wagen | -6.613 |
alore | -6.285 |
CLASSIFIED | -6.018 |
thia | -6.016 |
ciation | -5.862 |
Token | 001 |
Token ID | 8298 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
KN | +2.300 |
pel | +2.152 |
Kem | +2.108 |
Primal | +2.085 |
Ike | +1.973 |
Neg logit contributions | |
wagen | -4.182 |
alore | -3.924 |
thia | -3.780 |
CLASSIFIED | -3.760 |
akeru | -3.614 |
Token | Pre |
Token ID | 3771 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Kem | +7.516 |
Primal | +7.423 |
KN | +7.257 |
pel | +6.916 |
Emin | +6.876 |
Neg logit contributions | |
wagen | -9.648 |
alore | -9.157 |
CLASSIFIED | -8.729 |
thia | -8.637 |
akeru | -8.385 |
Token | - |
Token ID | 12 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
KN | +0.849 |
Kem | +0.830 |
pel | +0.824 |
Primal | +0.806 |
Stephenson | +0.770 |
Neg logit contributions | |
wagen | -0.997 |
alore | -0.891 |
thia | -0.877 |
CLASSIFIED | -0.853 |
ciation | -0.832 |
Token | training |
Token ID | 34409 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
wagen | +2.206 |
alore | +1.947 |
thia | +1.925 |
CLASSIFIED | +1.872 |
ciation | +1.848 |
Neg logit contributions | |
KN | -2.013 |
Kem | -1.972 |
Primal | -1.935 |
pel | -1.932 |
Stephenson | -1.867 |
Token | . |
Token ID | 13 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
KN | +2.826 |
Kem | +2.823 |
Primal | +2.766 |
pel | +2.743 |
Emin | +2.588 |
Neg logit contributions | |
wagen | -3.666 |
alore | -3.320 |
thia | -3.250 |
CLASSIFIED | -3.172 |
ciation | -3.093 |
Token | In |
Token ID | 554 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Kem | +4.276 |
KN | +4.222 |
Primal | +4.216 |
pel | +4.066 |
Emin | +3.908 |
Neg logit contributions | |
wagen | -5.892 |
alore | -5.351 |
thia | -5.171 |
CLASSIFIED | -5.071 |
akeru | -4.964 |
Token | loses |
Token ID | 14754 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
KN | +0.213 |
Kem | +0.207 |
pel | +0.205 |
Primal | +0.203 |
Stephenson | +0.195 |
Neg logit contributions | |
wagen | -0.230 |
alore | -0.204 |
thia | -0.202 |
CLASSIFIED | -0.194 |
ciation | -0.191 |
Token | , |
Token ID | 11 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
KN | +1.626 |
Kem | +1.598 |
pel | +1.565 |
Primal | +1.548 |
Stephenson | +1.478 |
Neg logit contributions | |
wagen | -2.092 |
alore | -1.875 |
thia | -1.851 |
CLASSIFIED | -1.803 |
ciation | -1.778 |
Token | expect |
Token ID | 1607 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
KN | +0.416 |
Kem | +0.406 |
pel | +0.399 |
Primal | +0.395 |
Stephenson | +0.377 |
Neg logit contributions | |
wagen | -0.545 |
alore | -0.488 |
thia | -0.482 |
CLASSIFIED | -0.469 |
ciation | -0.462 |
Token | the |
Token ID | 262 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
KN | +0.255 |
Kem | +0.249 |
pel | +0.245 |
Primal | +0.242 |
Stephenson | +0.231 |
Neg logit contributions | |
wagen | -0.343 |
alore | -0.307 |
thia | -0.304 |
CLASSIFIED | -0.295 |
ciation | -0.291 |
Token | liberal |
Token ID | 7270 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
KN | +2.476 |
Kem | +2.476 |
Primal | +2.380 |
pel | +2.377 |
Ike | +2.281 |
Neg logit contributions | |
wagen | -3.420 |
alore | -3.057 |
thia | -3.026 |
CLASSIFIED | -2.979 |
ciation | -2.937 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
wagen | +1.317 |
alore | +1.180 |
thia | +1.167 |
CLASSIFIED | +1.129 |
ciation | +1.116 |
Neg logit contributions | |
KN | -1.020 |
Kem | -0.988 |
pel | -0.980 |
Primal | -0.967 |
hower | -0.924 |
Token | w |
Token ID | 86 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
KN | +7.459 |
pel | +7.276 |
Kem | +6.995 |
Primal | +6.615 |
Ike | +6.553 |
Neg logit contributions | |
wagen | -9.825 |
CLASSIFIED | -8.823 |
thia | -8.733 |
alore | -8.703 |
ciation | -8.458 |
Token | ring |
Token ID | 1806 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
pel | +4.504 |
KN | +4.442 |
Kem | +4.299 |
Primal | +4.243 |
Emin | +4.110 |
Neg logit contributions | |
wagen | -4.627 |
CLASSIFIED | -4.169 |
alore | -4.011 |
thia | -4.000 |
ciation | -3.884 |
Token | ing |
Token ID | 278 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
wagen | +0.175 |
alore | +0.152 |
thia | +0.150 |
CLASSIFIED | +0.144 |
ciation | +0.141 |
Neg logit contributions | |
KN | -0.215 |
Kem | -0.210 |
pel | -0.208 |
Primal | -0.206 |
Stephenson | -0.199 |
Token | about |
Token ID | 546 |
Feature activation | -3.64e+00 |
Pos logit contributions | |
KN | +1.005 |
Kem | +0.986 |
pel | +0.965 |
Primal | +0.954 |
Stephenson | +0.913 |
Neg logit contributions | |
wagen | -1.430 |
alore | -1.276 |
thia | -1.269 |
CLASSIFIED | -1.240 |
ciation | -1.218 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
KN | +2.354 |
Kem | +2.343 |
pel | +2.272 |
Primal | +2.254 |
Ike | +2.180 |
Neg logit contributions | |
wagen | -3.400 |
thia | -3.020 |
alore | -3.015 |
CLASSIFIED | -2.930 |
ciation | -2.908 |
Token | : |
Token ID | 25 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
KN | +0.584 |
Kem | +0.568 |
pel | +0.561 |
Primal | +0.554 |
Ike | +0.531 |
Neg logit contributions | |
wagen | -0.721 |
alore | -0.642 |
thia | -0.627 |
CLASSIFIED | -0.624 |
ciation | -0.601 |
Token | 47 |
Token ID | 2857 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
KN | +1.980 |
Kem | +1.914 |
pel | +1.881 |
Primal | +1.852 |
Ike | +1.775 |
Neg logit contributions | |
wagen | -2.548 |
alore | -2.303 |
thia | -2.262 |
CLASSIFIED | -2.201 |
ciation | -2.168 |
Token | ] |
Token ID | 60 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
wagen | +2.794 |
thia | +2.465 |
alore | +2.453 |
ciation | +2.313 |
CLASSIFIED | +2.304 |
Neg logit contributions | |
KN | -3.003 |
Kem | -2.932 |
pel | -2.906 |
Primal | -2.876 |
hower | -2.801 |
Token | < |
Token ID | 1279 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
KN | +0.809 |
Kem | +0.786 |
pel | +0.775 |
Primal | +0.764 |
Stephenson | +0.728 |
Neg logit contributions | |
wagen | -1.127 |
alore | -1.012 |
thia | -1.001 |
CLASSIFIED | -0.972 |
ciation | -0.959 |
Token | p |
Token ID | 79 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
KN | +0.180 |
Kem | +0.175 |
pel | +0.173 |
Primal | +0.171 |
Stephenson | +0.164 |
Neg logit contributions | |
wagen | -0.212 |
alore | -0.188 |
thia | -0.186 |
CLASSIFIED | -0.181 |
ciation | -0.178 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
KN | +2.256 |
pel | +2.173 |
Kem | +2.159 |
Primal | +2.077 |
hower | +2.021 |
Neg logit contributions | |
wagen | -2.606 |
alore | -2.304 |
CLASSIFIED | -2.272 |
thia | -2.271 |
ciation | -2.191 |
Token | e |
Token ID | 68 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
KN | +8.427 |
pel | +8.367 |
Kem | +7.849 |
hower | +7.721 |
Primal | +7.659 |
Neg logit contributions | |
wagen | -8.163 |
CLASSIFIED | -7.306 |
alore | -7.244 |
thia | -7.204 |
ciation | -6.947 |
Token | ater |
Token ID | 729 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
KN | +4.811 |
pel | +4.594 |
Kem | +4.496 |
Primal | +4.341 |
hower | +4.256 |
Neg logit contributions | |
wagen | -5.361 |
alore | -4.762 |
CLASSIFIED | -4.702 |
thia | -4.667 |
ciation | -4.509 |
Token | > |
Token ID | 29 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
KN | +1.643 |
pel | +1.587 |
Kem | +1.580 |
Primal | +1.540 |
hower | +1.480 |
Neg logit contributions | |
wagen | -1.955 |
alore | -1.747 |
thia | -1.723 |
CLASSIFIED | -1.694 |
ciation | -1.659 |
Token | lol |
Token ID | 19462 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
wagen | +0.154 |
alore | +0.137 |
thia | +0.135 |
CLASSIFIED | +0.131 |
ciation | +0.129 |
Neg logit contributions | |
KN | -0.133 |
Kem | -0.130 |
pel | -0.128 |
Primal | -0.127 |
Stephenson | -0.121 |
Token | m |
Token ID | 285 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
wagen | +1.687 |
alore | +1.483 |
thia | +1.458 |
CLASSIFIED | +1.396 |
ciation | +1.382 |
Neg logit contributions | |
KN | -1.809 |
Kem | -1.762 |
pel | -1.746 |
Primal | -1.736 |
Stephenson | -1.668 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
wagen | +0.928 |
alore | +0.824 |
thia | +0.816 |
CLASSIFIED | +0.790 |
ciation | +0.779 |
Neg logit contributions | |
KN | -0.793 |
Kem | -0.769 |
pel | -0.760 |
Primal | -0.752 |
Stephenson | -0.717 |
Token | - |
Token ID | 532 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
wagen | +0.804 |
alore | +0.709 |
thia | +0.702 |
CLASSIFIED | +0.678 |
ciation | +0.668 |
Neg logit contributions | |
KN | -0.782 |
Kem | -0.761 |
pel | -0.753 |
Primal | -0.745 |
hower | -0.712 |
Token | February |
Token ID | 3945 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
wagen | +1.954 |
alore | +1.723 |
thia | +1.722 |
CLASSIFIED | +1.651 |
ciation | +1.618 |
Neg logit contributions | |
KN | -1.897 |
pel | -1.840 |
Kem | -1.837 |
Primal | -1.799 |
hower | -1.759 |
Token | 9 |
Token ID | 860 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
KN | +0.681 |
Kem | +0.669 |
pel | +0.649 |
Primal | +0.647 |
Stephenson | +0.616 |
Neg logit contributions | |
wagen | -1.082 |
alore | -0.976 |
thia | -0.957 |
CLASSIFIED | -0.946 |
ciation | -0.925 |
Token | , |
Token ID | 11 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
KN | +0.459 |
Kem | +0.447 |
pel | +0.440 |
Primal | +0.435 |
Ike | +0.415 |
Neg logit contributions | |
wagen | -0.626 |
alore | -0.561 |
CLASSIFIED | -0.545 |
thia | -0.545 |
ciation | -0.525 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
wagen | +0.552 |
alore | +0.489 |
thia | +0.485 |
CLASSIFIED | +0.469 |
ciation | +0.463 |
Neg logit contributions | |
KN | -0.508 |
Kem | -0.491 |
pel | -0.487 |
Primal | -0.480 |
Emin | -0.461 |
Token |
|
Token ID | 198 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
KN | +5.025 |
Kem | +4.890 |
Primal | +4.728 |
pel | +4.528 |
Ike | +4.483 |
Neg logit contributions | |
wagen | -12.377 |
CLASSIFIED | -11.415 |
alore | -11.211 |
akeru | -10.761 |
thia | -10.618 |
Token |
|
Token ID | 198 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
KN | +0.500 |
Kem | +0.485 |
pel | +0.477 |
Primal | +0.472 |
Ike | +0.447 |
Neg logit contributions | |
wagen | -0.761 |
alore | -0.686 |
CLASSIFIED | -0.671 |
thia | -0.671 |
ciation | -0.647 |
Token | Subject |
Token ID | 19776 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
wagen | +2.166 |
alore | +1.869 |
thia | +1.844 |
CLASSIFIED | +1.770 |
ciation | +1.732 |
Neg logit contributions | |
KN | -2.861 |
Kem | -2.808 |
pel | -2.776 |
Primal | -2.753 |
Stephenson | -2.662 |
Token | : |
Token ID | 25 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
wagen | +3.429 |
thia | +3.032 |
alore | +2.990 |
ciation | +2.857 |
CLASSIFIED | +2.795 |
Neg logit contributions | |
KN | -3.619 |
Kem | -3.525 |
pel | -3.474 |
Primal | -3.439 |
hower | -3.356 |
Token | R |
Token ID | 371 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
KN | +1.381 |
Kem | +1.357 |
pel | +1.330 |
Primal | +1.324 |
Stephenson | +1.265 |
Neg logit contributions | |
wagen | -1.648 |
alore | -1.473 |
thia | -1.447 |
CLASSIFIED | -1.403 |
ciation | -1.385 |
Token | COL |
Token ID | 20444 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
KN | +1.048 |
Kem | +1.025 |
Primal | +1.001 |
pel | +0.998 |
Stephenson | +0.943 |
Neg logit contributions | |
wagen | -1.436 |
alore | -1.285 |
thia | -1.271 |
CLASSIFIED | -1.228 |
ciation | -1.221 |
Token | OR |
Token ID | 1581 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
KN | +2.071 |
Kem | +1.855 |
Primal | +1.808 |
pel | +1.771 |
Ike | +1.662 |
Neg logit contributions | |
wagen | -4.817 |
alore | -4.449 |
thia | -4.293 |
ciation | -4.212 |
CLASSIFIED | -4.182 |
Token | _ |
Token ID | 62 |
Feature activation | -6.00e+00 |
Pos logit contributions | |
wagen | +1.383 |
alore | +1.254 |
thia | +1.243 |
CLASSIFIED | +1.211 |
ciation | +1.197 |
Neg logit contributions | |
KN | -0.778 |
Kem | -0.754 |
pel | -0.742 |
Primal | -0.731 |
Stephenson | -0.691 |
Token | B |
Token ID | 33 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
KN | +3.939 |
Kem | +3.506 |
Primal | +3.453 |
pel | +3.394 |
Ike | +3.228 |
Neg logit contributions | |
wagen | -5.873 |
alore | -5.242 |
thia | -5.098 |
ciation | -5.010 |
akeru | -4.897 |
Token | GR |
Token ID | 10761 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
KN | +0.261 |
Kem | +0.224 |
Primal | +0.215 |
pel | +0.215 |
hower | +0.183 |
Neg logit contributions | |
wagen | -1.017 |
alore | -0.945 |
thia | -0.931 |
ciation | -0.914 |
CLASSIFIED | -0.908 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
KN | +2.662 |
Kem | +2.483 |
Primal | +2.436 |
pel | +2.386 |
Ike | +2.303 |
Neg logit contributions | |
wagen | -3.819 |
alore | -3.490 |
thia | -3.355 |
ciation | -3.271 |
CLASSIFIED | -3.242 |
Token | G |
Token ID | 38 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
KN | +5.480 |
Kem | +4.658 |
Primal | +4.485 |
Ike | +4.082 |
pel | +4.018 |
Neg logit contributions | |
wagen | -12.395 |
alore | -11.447 |
thia | -11.005 |
akeru | -10.974 |
ciation | -10.879 |
Token | RAY |
Token ID | 30631 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
KN | +2.384 |
Primal | +2.020 |
Kem | +1.974 |
pel | +1.878 |
Ike | +1.701 |
Neg logit contributions | |
wagen | -7.588 |
alore | -7.034 |
thia | -6.861 |
ciation | -6.641 |
CLASSIFIED | -6.623 |
Token | ) |
Token ID | 1267 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
KN | +1.085 |
Kem | +1.058 |
pel | +1.035 |
Primal | +1.026 |
Ike | +0.986 |
Neg logit contributions | |
wagen | -1.199 |
alore | -1.063 |
thia | -1.033 |
CLASSIFIED | -1.019 |
ciation | -0.992 |
Token | # |
Token ID | 1303 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
wagen | +0.912 |
alore | +0.771 |
thia | +0.757 |
CLASSIFIED | +0.717 |
ciation | +0.698 |
Neg logit contributions | |
KN | -1.450 |
Kem | -1.412 |
pel | -1.410 |
Primal | -1.385 |
Emin | -1.350 |
Token | smooth |
Token ID | 7209 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
KN | +1.865 |
Kem | +1.804 |
pel | +1.782 |
Primal | +1.751 |
Stephenson | +1.686 |
Neg logit contributions | |
wagen | -2.595 |
alore | -2.332 |
thia | -2.305 |
CLASSIFIED | -2.246 |
ciation | -2.226 |
Token | 353 |
Token ID | 33319 |
Feature activation | -7.62e+00 |
Pos logit contributions | |
KN | +2.239 |
Kem | +2.173 |
pel | +2.144 |
Primal | +2.123 |
Stephenson | +2.030 |
Neg logit contributions | |
wagen | -2.725 |
alore | -2.438 |
thia | -2.412 |
CLASSIFIED | -2.347 |
ciation | -2.305 |
Token | ef |
Token ID | 891 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
KN | +5.157 |
Kem | +5.025 |
pel | +4.938 |
Primal | +4.908 |
Emin | +4.728 |
Neg logit contributions | |
wagen | -6.515 |
alore | -5.780 |
thia | -5.766 |
CLASSIFIED | -5.722 |
ciation | -5.529 |
Token | 015 |
Token ID | 25150 |
Feature activation | -7.40e+00 |
Pos logit contributions | |
KN | +1.815 |
Kem | +1.766 |
pel | +1.747 |
Primal | +1.727 |
Stephenson | +1.652 |
Neg logit contributions | |
wagen | -2.183 |
alore | -1.949 |
thia | -1.928 |
CLASSIFIED | -1.884 |
ciation | -1.848 |
Token | 390 |
Token ID | 25964 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
KN | +5.014 |
Kem | +4.863 |
pel | +4.768 |
Primal | +4.735 |
Emin | +4.539 |
Neg logit contributions | |
wagen | -6.365 |
alore | -5.645 |
thia | -5.609 |
CLASSIFIED | -5.591 |
ciation | -5.413 |
Token | b |
Token ID | 65 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
KN | +4.554 |
Kem | +4.389 |
pel | +4.336 |
Primal | +4.306 |
Emin | +4.105 |
Neg logit contributions | |
wagen | -5.809 |
alore | -5.160 |
CLASSIFIED | -5.122 |
thia | -5.107 |
ciation | -4.938 |
Token | 0 |
Token ID | 15 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
KN | +2.237 |
Kem | +2.174 |
pel | +2.145 |
Primal | +2.119 |
Stephenson | +2.028 |
Neg logit contributions | |
wagen | -2.691 |
alore | -2.408 |
thia | -2.373 |
CLASSIFIED | -2.319 |
ciation | -2.279 |
Token | bb |
Token ID | 11848 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
KN | +7.388 |
Kem | +7.235 |
Primal | +7.133 |
pel | +6.926 |
Ike | +6.753 |
Neg logit contributions | |
wagen | -9.077 |
alore | -8.089 |
thia | -7.992 |
CLASSIFIED | -7.884 |
ciation | -7.732 |
Token | 9 |
Token ID | 24 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
KN | +1.362 |
Kem | +1.322 |
pel | +1.309 |
Primal | +1.293 |
Emin | +1.236 |
Neg logit contributions | |
wagen | -1.623 |
alore | -1.447 |
thia | -1.431 |
CLASSIFIED | -1.394 |
ciation | -1.370 |
Token | d |
Token ID | 67 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
KN | +4.661 |
Kem | +4.554 |
Primal | +4.456 |
pel | +4.454 |
Emin | +4.249 |
Neg logit contributions | |
wagen | -5.763 |
alore | -5.172 |
thia | -5.117 |
CLASSIFIED | -5.010 |
ciation | -4.934 |
Token | 970 |
Token ID | 43587 |
Feature activation | -7.31e+00 |
Pos logit contributions | |
KN | +2.097 |
Kem | +2.041 |
pel | +2.012 |
Primal | +1.991 |
Stephenson | +1.906 |
Neg logit contributions | |
wagen | -2.522 |
alore | -2.256 |
thia | -2.230 |
CLASSIFIED | -2.172 |
ciation | -2.133 |
Token | b |
Token ID | 65 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
KN | +4.989 |
Kem | +4.829 |
pel | +4.725 |
Primal | +4.723 |
Stephenson | +4.501 |
Neg logit contributions | |
wagen | -6.256 |
alore | -5.622 |
thia | -5.524 |
CLASSIFIED | -5.473 |
ciation | -5.367 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
wagen | +0.229 |
alore | +0.205 |
thia | +0.202 |
CLASSIFIED | +0.196 |
ciation | +0.194 |
Neg logit contributions | |
KN | -0.176 |
Kem | -0.171 |
pel | -0.169 |
Primal | -0.167 |
Stephenson | -0.159 |
Token | - |
Token ID | 532 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
wagen | +1.120 |
alore | +0.996 |
thia | +0.985 |
CLASSIFIED | +0.953 |
ciation | +0.939 |
Neg logit contributions | |
KN | -0.951 |
Kem | -0.922 |
pel | -0.911 |
Primal | -0.901 |
Stephenson | -0.860 |
Token | December |
Token ID | 3426 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
wagen | +3.538 |
thia | +3.159 |
alore | +3.123 |
CLASSIFIED | +2.997 |
ciation | +2.931 |
Neg logit contributions | |
KN | -3.485 |
pel | -3.369 |
Kem | -3.354 |
Primal | -3.303 |
hower | -3.253 |
Token | 13 |
Token ID | 1511 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
wagen | +0.439 |
alore | +0.395 |
thia | +0.390 |
CLASSIFIED | +0.381 |
ciation | +0.375 |
Neg logit contributions | |
KN | -0.293 |
Kem | -0.285 |
pel | -0.280 |
Primal | -0.277 |
Stephenson | -0.263 |
Token | , |
Token ID | 11 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
wagen | +0.164 |
alore | +0.147 |
thia | +0.144 |
CLASSIFIED | +0.142 |
ciation | +0.138 |
Neg logit contributions | |
KN | -0.129 |
Kem | -0.126 |
pel | -0.124 |
Primal | -0.123 |
Ike | -0.117 |
Token | 2010 |
Token ID | 3050 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
wagen | +0.456 |
alore | +0.406 |
thia | +0.401 |
CLASSIFIED | +0.389 |
ciation | +0.383 |
Neg logit contributions | |
KN | -0.388 |
Kem | -0.378 |
pel | -0.374 |
Primal | -0.369 |
Stephenson | -0.353 |
Token |
|
Token ID | 198 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Kem | +5.031 |
KN | +5.005 |
Primal | +4.866 |
Ike | +4.645 |
pel | +4.537 |
Neg logit contributions | |
wagen | -12.250 |
CLASSIFIED | -11.192 |
alore | -11.039 |
akeru | -10.647 |
thia | -10.519 |
Token |
|
Token ID | 198 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
wagen | +0.613 |
alore | +0.552 |
thia | +0.543 |
CLASSIFIED | +0.534 |
ciation | +0.522 |
Neg logit contributions | |
KN | -0.432 |
Kem | -0.420 |
pel | -0.414 |
Primal | -0.409 |
Stephenson | -0.388 |
Token | Subject |
Token ID | 19776 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
wagen | +1.559 |
alore | +1.350 |
thia | +1.326 |
CLASSIFIED | +1.275 |
ciation | +1.254 |
Neg logit contributions | |
KN | -1.992 |
Kem | -1.947 |
pel | -1.930 |
Primal | -1.910 |
Stephenson | -1.840 |
Token | : |
Token ID | 25 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
wagen | +3.915 |
thia | +3.461 |
alore | +3.387 |
ciation | +3.237 |
CLASSIFIED | +3.164 |
Neg logit contributions | |
KN | -4.265 |
Kem | -4.120 |
pel | -4.081 |
Primal | -4.026 |
hower | -3.964 |
Token | boys |
Token ID | 6510 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
KN | +0.898 |
Kem | +0.882 |
pel | +0.865 |
Primal | +0.860 |
Stephenson | +0.822 |
Neg logit contributions | |
wagen | -1.070 |
alore | -0.956 |
thia | -0.940 |
CLASSIFIED | -0.911 |
ciation | -0.900 |
Token | 's |
Token ID | 338 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
wagen | +0.311 |
alore | +0.278 |
thia | +0.274 |
CLASSIFIED | +0.266 |
ciation | +0.262 |
Neg logit contributions | |
KN | -0.262 |
Kem | -0.256 |
pel | -0.252 |
Primal | -0.250 |
Stephenson | -0.239 |
Token | not |
Token ID | 407 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
KN | +1.728 |
Kem | +1.704 |
pel | +1.664 |
Primal | +1.661 |
Stephenson | +1.581 |
Neg logit contributions | |
wagen | -2.470 |
alore | -2.227 |
thia | -2.202 |
CLASSIFIED | -2.158 |
ciation | -2.115 |
Token | much |
Token ID | 881 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
KN | +3.200 |
Kem | +3.158 |
Primal | +3.103 |
pel | +3.014 |
Stephenson | +2.939 |
Neg logit contributions | |
wagen | -4.913 |
alore | -4.407 |
thia | -4.402 |
CLASSIFIED | -4.299 |
ciation | -4.209 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
KN | +1.874 |
Kem | +1.845 |
pel | +1.791 |
Primal | +1.780 |
Ike | +1.689 |
Neg logit contributions | |
wagen | -2.710 |
alore | -2.440 |
thia | -2.391 |
CLASSIFIED | -2.362 |
ciation | -2.283 |
Token | a |
Token ID | 257 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
KN | +1.081 |
Kem | +1.060 |
pel | +1.040 |
Primal | +1.031 |
Stephenson | +0.982 |
Neg logit contributions | |
wagen | -1.436 |
alore | -1.286 |
thia | -1.268 |
CLASSIFIED | -1.240 |
ciation | -1.215 |
Token | knock |
Token ID | 10643 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
KN | +2.575 |
Kem | +2.550 |
Primal | +2.491 |
pel | +2.475 |
Stephenson | +2.362 |
Neg logit contributions | |
wagen | -3.410 |
alore | -3.064 |
thia | -3.024 |
CLASSIFIED | -2.976 |
ciation | -2.904 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
KN | +6.332 |
Kem | +6.331 |
pel | +6.322 |
Primal | +6.110 |
Isaac | +5.869 |
Neg logit contributions | |
wagen | -10.261 |
CLASSIFIED | -9.127 |
alore | -9.068 |
thia | -9.010 |
ciation | -8.536 |
Token | It |
Token ID | 632 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
KN | +0.135 |
Kem | +0.132 |
pel | +0.129 |
Primal | +0.128 |
Stephenson | +0.122 |
Neg logit contributions | |
wagen | -0.174 |
alore | -0.156 |
thia | -0.153 |
CLASSIFIED | -0.149 |
ciation | -0.147 |
Token | 's |
Token ID | 338 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
wagen | +1.527 |
alore | +1.362 |
thia | +1.346 |
CLASSIFIED | +1.286 |
ciation | +1.283 |
Neg logit contributions | |
KN | -1.350 |
Kem | -1.313 |
pel | -1.297 |
Primal | -1.279 |
Stephenson | -1.227 |
Token | a |
Token ID | 257 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
wagen | +2.313 |
alore | +2.072 |
thia | +2.049 |
CLASSIFIED | +1.962 |
ciation | +1.950 |
Neg logit contributions | |
KN | -1.801 |
Kem | -1.731 |
pel | -1.717 |
Primal | -1.673 |
hower | -1.631 |
Token | bit |
Token ID | 1643 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
wagen | +1.488 |
alore | +1.330 |
thia | +1.318 |
CLASSIFIED | +1.269 |
ciation | +1.257 |
Neg logit contributions | |
KN | -1.134 |
Kem | -1.096 |
pel | -1.085 |
Primal | -1.064 |
hower | -1.022 |
Token | The |
Token ID | 383 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
KN | +1.435 |
Kem | +1.425 |
Primal | +1.396 |
pel | +1.390 |
Ike | +1.334 |
Neg logit contributions | |
wagen | -1.766 |
alore | -1.584 |
thia | -1.531 |
CLASSIFIED | -1.522 |
ciation | -1.484 |
Token | Nation |
Token ID | 8741 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
KN | +0.382 |
Kem | +0.378 |
pel | +0.369 |
Primal | +0.368 |
Stephenson | +0.356 |
Neg logit contributions | |
wagen | -0.329 |
alore | -0.289 |
thia | -0.281 |
CLASSIFIED | -0.273 |
ciation | -0.266 |
Token | Be |
Token ID | 1355 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
KN | +0.983 |
Kem | +0.982 |
pel | +0.939 |
Primal | +0.931 |
Ike | +0.894 |
Neg logit contributions | |
wagen | -1.821 |
alore | -1.667 |
CLASSIFIED | -1.627 |
thia | -1.614 |
ciation | -1.598 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
Kem | +3.224 |
Primal | +3.154 |
KN | +3.137 |
pel | +3.110 |
Stephenson | +2.958 |
Neg logit contributions | |
wagen | -5.922 |
alore | -5.351 |
CLASSIFIED | -5.234 |
thia | -5.175 |
ciation | -5.130 |
Token | first |
Token ID | 717 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
KN | +2.063 |
Primal | +2.054 |
Kem | +2.052 |
pel | +1.986 |
Ike | +1.899 |
Neg logit contributions | |
wagen | -3.146 |
alore | -2.866 |
thia | -2.768 |
CLASSIFIED | -2.730 |
ciation | -2.669 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
KN | +2.298 |
Kem | +2.265 |
Primal | +2.222 |
pel | +2.219 |
Ike | +2.109 |
Neg logit contributions | |
wagen | -4.028 |
alore | -3.631 |
CLASSIFIED | -3.556 |
thia | -3.534 |
ciation | -3.426 |
Token | hear |
Token ID | 3285 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
KN | +5.054 |
pel | +4.674 |
Primal | +4.672 |
Ike | +4.518 |
Kem | +4.376 |
Neg logit contributions | |
wagen | -11.922 |
CLASSIFIED | -10.982 |
alore | -10.448 |
thia | -10.336 |
rama | -9.941 |
Token | about |
Token ID | 546 |
Feature activation | +9.00e-02 |
Pos logit contributions | |
KN | +1.671 |
Primal | +1.641 |
pel | +1.624 |
Kem | +1.624 |
Emin | +1.525 |
Neg logit contributions | |
wagen | -2.985 |
alore | -2.664 |
thia | -2.603 |
CLASSIFIED | -2.572 |
ciation | -2.537 |
Token | Nation |
Token ID | 8741 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
wagen | +0.072 |
alore | +0.064 |
thia | +0.062 |
CLASSIFIED | +0.060 |
ciation | +0.059 |
Neg logit contributions | |
Kem | -0.071 |
Primal | -0.070 |
KN | -0.070 |
pel | -0.068 |
Emin | -0.067 |
Token | Travels |
Token ID | 48899 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
KN | +0.196 |
Kem | +0.190 |
pel | +0.189 |
Primal | +0.186 |
Stephenson | +0.177 |
Neg logit contributions | |
wagen | -0.278 |
alore | -0.251 |
thia | -0.247 |
CLASSIFIED | -0.241 |
ciation | -0.237 |
Token | destinations |
Token ID | 23982 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
wagen | +3.391 |
alore | +2.965 |
thia | +2.903 |
CLASSIFIED | +2.821 |
ciation | +2.817 |
Neg logit contributions | |
KN | -3.157 |
Kem | -3.057 |
pel | -3.015 |
Primal | -2.987 |
hower | -2.868 |
Token | it |
Token ID | 340 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
wagen | +1.739 |
alore | +1.558 |
thia | +1.535 |
CLASSIFIED | +1.491 |
ciation | +1.465 |
Neg logit contributions | |
KN | -1.397 |
Kem | -1.359 |
pel | -1.349 |
Primal | -1.312 |
Stephenson | -1.264 |
Token | necessary |
Token ID | 3306 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
KN | +0.162 |
Kem | +0.157 |
pel | +0.155 |
Primal | +0.152 |
Stephenson | +0.144 |
Neg logit contributions | |
wagen | -0.263 |
alore | -0.238 |
thia | -0.235 |
CLASSIFIED | -0.229 |
ciation | -0.226 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
wagen | +1.397 |
alore | +1.249 |
thia | +1.234 |
CLASSIFIED | +1.201 |
ciation | +1.183 |
Neg logit contributions | |
KN | -1.129 |
Kem | -1.100 |
pel | -1.086 |
Primal | -1.063 |
Emin | -1.022 |
Token | it |
Token ID | 340 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
wagen | +2.624 |
alore | +2.346 |
thia | +2.314 |
CLASSIFIED | +2.252 |
ciation | +2.207 |
Neg logit contributions | |
KN | -2.159 |
Kem | -2.101 |
pel | -2.091 |
Primal | -2.027 |
hower | -1.967 |
Token | will |
Token ID | 481 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
KN | +0.598 |
Kem | +0.583 |
pel | +0.575 |
Primal | +0.568 |
Stephenson | +0.543 |
Neg logit contributions | |
wagen | -0.749 |
alore | -0.670 |
thia | -0.662 |
CLASSIFIED | -0.642 |
ciation | -0.633 |
Token | confisc |
Token ID | 22735 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
KN | +2.077 |
Kem | +2.012 |
pel | +2.000 |
Primal | +1.990 |
Stephenson | +1.880 |
Neg logit contributions | |
wagen | -2.703 |
alore | -2.423 |
thia | -2.407 |
CLASSIFIED | -2.365 |
ciation | -2.306 |
Token | ate |
Token ID | 378 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
pel | +4.591 |
KN | +4.535 |
Kem | +4.264 |
Primal | +4.190 |
Ike | +4.063 |
Neg logit contributions | |
wagen | -11.650 |
CLASSIFIED | -11.014 |
alore | -10.540 |
thia | -10.375 |
ciation | -10.257 |
Token | your |
Token ID | 534 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
KN | +0.335 |
Kem | +0.326 |
pel | +0.321 |
Primal | +0.320 |
Stephenson | +0.304 |
Neg logit contributions | |
wagen | -0.464 |
alore | -0.418 |
thia | -0.413 |
CLASSIFIED | -0.400 |
ciation | -0.397 |
Token | food |
Token ID | 2057 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
KN | +0.306 |
Kem | +0.298 |
pel | +0.292 |
Primal | +0.291 |
Stephenson | +0.277 |
Neg logit contributions | |
wagen | -0.445 |
alore | -0.401 |
thia | -0.397 |
CLASSIFIED | -0.386 |
ciation | -0.383 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
wagen | +2.689 |
alore | +2.382 |
thia | +2.369 |
CLASSIFIED | +2.288 |
ciation | +2.257 |
Neg logit contributions | |
KN | -2.219 |
Kem | -2.175 |
pel | -2.134 |
Primal | -2.102 |
Emin | -2.026 |
Token | To |
Token ID | 1675 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
KN | +0.238 |
Kem | +0.233 |
pel | +0.228 |
Primal | +0.227 |
Stephenson | +0.217 |
Neg logit contributions | |
wagen | -0.294 |
alore | -0.263 |
thia | -0.259 |
CLASSIFIED | -0.251 |
ciation | -0.247 |
Token | columnist |
Token ID | 22309 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
KN | +0.677 |
Kem | +0.663 |
pel | +0.648 |
Primal | +0.643 |
Stephenson | +0.613 |
Neg logit contributions | |
wagen | -0.937 |
alore | -0.842 |
thia | -0.834 |
CLASSIFIED | -0.810 |
ciation | -0.801 |
Token | in |
Token ID | 287 |
Feature activation | -4.86e+00 |
Pos logit contributions | |
KN | +1.525 |
Kem | +1.500 |
pel | +1.468 |
Primal | +1.458 |
Stephenson | +1.384 |
Neg logit contributions | |
wagen | -2.109 |
alore | -1.884 |
thia | -1.874 |
CLASSIFIED | -1.830 |
ciation | -1.799 |
Token | the |
Token ID | 262 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
Kem | +3.121 |
KN | +3.089 |
Primal | +3.000 |
pel | +2.924 |
Emin | +2.877 |
Neg logit contributions | |
wagen | -4.604 |
alore | -4.094 |
thia | -4.026 |
CLASSIFIED | -3.970 |
ciation | -3.918 |
Token | Turkish |
Token ID | 9663 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
Kem | +3.990 |
KN | +3.918 |
Primal | +3.770 |
pel | +3.673 |
Emin | +3.605 |
Neg logit contributions | |
wagen | -6.270 |
alore | -5.541 |
thia | -5.504 |
CLASSIFIED | -5.428 |
ciation | -5.358 |
Token | newspaper |
Token ID | 7533 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
Kem | +3.834 |
KN | +3.807 |
Primal | +3.638 |
pel | +3.564 |
Ike | +3.488 |
Neg logit contributions | |
wagen | -5.964 |
alore | -5.295 |
thia | -5.222 |
CLASSIFIED | -5.107 |
ciation | -5.034 |
Token | H |
Token ID | 367 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
Kem | +5.456 |
KN | +5.228 |
Primal | +5.118 |
Ike | +4.973 |
Emin | +4.942 |
Neg logit contributions | |
wagen | -7.107 |
alore | -6.315 |
thia | -6.175 |
CLASSIFIED | -6.127 |
ciation | -5.980 |
Token | ür |
Token ID | 25151 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
KN | +5.153 |
Kem | +4.548 |
pel | +4.510 |
Ike | +4.074 |
Emin | +4.027 |
Neg logit contributions | |
wagen | -11.522 |
CLASSIFIED | -10.700 |
thia | -10.266 |
alore | -10.184 |
ciation | -10.050 |
Token | ri |
Token ID | 380 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
pel | +4.697 |
KN | +4.660 |
Kem | +4.656 |
Primal | +4.523 |
Emin | +4.429 |
Neg logit contributions | |
wagen | -5.140 |
alore | -4.665 |
CLASSIFIED | -4.589 |
ciation | -4.429 |
thia | -4.397 |
Token | yet |
Token ID | 25907 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
wagen | +1.427 |
alore | +1.283 |
thia | +1.272 |
CLASSIFIED | +1.234 |
ciation | +1.219 |
Neg logit contributions | |
KN | -0.975 |
Kem | -0.944 |
pel | -0.931 |
Primal | -0.920 |
Stephenson | -0.877 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
KN | +2.287 |
Kem | +2.258 |
Primal | +2.181 |
pel | +2.181 |
Emin | +2.087 |
Neg logit contributions | |
wagen | -2.993 |
alore | -2.668 |
thia | -2.645 |
CLASSIFIED | -2.576 |
ciation | -2.534 |
Token | warned |
Token ID | 7728 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
KN | +0.967 |
Kem | +0.948 |
pel | +0.928 |
Primal | +0.922 |
Stephenson | +0.878 |
Neg logit contributions | |
wagen | -1.329 |
alore | -1.190 |
thia | -1.179 |
CLASSIFIED | -1.151 |
ciation | -1.131 |
Token | iants |
Token ID | 17883 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
KN | +1.924 |
Kem | +1.861 |
pel | +1.848 |
Primal | +1.807 |
Ike | +1.737 |
Neg logit contributions | |
wagen | -2.213 |
alore | -1.954 |
thia | -1.934 |
CLASSIFIED | -1.909 |
ciation | -1.860 |
Token | Super |
Token ID | 3115 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
KN | +1.264 |
Kem | +1.242 |
pel | +1.222 |
Primal | +1.214 |
Ike | +1.165 |
Neg logit contributions | |
wagen | -1.408 |
alore | -1.258 |
thia | -1.237 |
CLASSIFIED | -1.202 |
ciation | -1.179 |
Token | bowl |
Token ID | 36859 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
KN | +0.989 |
Kem | +0.968 |
pel | +0.959 |
Primal | +0.950 |
Ike | +0.908 |
Neg logit contributions | |
wagen | -1.052 |
alore | -0.938 |
thia | -0.924 |
CLASSIFIED | -0.896 |
ciation | -0.879 |
Token | - |
Token ID | 12 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
wagen | +3.649 |
alore | +3.208 |
thia | +3.197 |
CLASSIFIED | +3.075 |
ciation | +3.070 |
Neg logit contributions | |
KN | -3.319 |
pel | -3.179 |
Kem | -3.168 |
Primal | -3.110 |
hower | -2.993 |
Token | Italian |
Token ID | 45696 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
KN | +1.345 |
Kem | +1.299 |
pel | +1.287 |
Primal | +1.266 |
Ike | +1.213 |
Neg logit contributions | |
wagen | -1.529 |
alore | -1.364 |
thia | -1.342 |
CLASSIFIED | -1.291 |
ciation | -1.279 |
Token | St |
Token ID | 520 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
wagen | +0.023 |
alore | +0.020 |
thia | +0.020 |
CLASSIFIED | +0.019 |
ciation | +0.019 |
Neg logit contributions | |
KN | -0.018 |
Kem | -0.018 |
pel | -0.018 |
Primal | -0.017 |
Stephenson | -0.017 |
Token | ere |
Token ID | 567 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
KN | +6.696 |
pel | +6.501 |
Kem | +6.490 |
Ike | +6.190 |
Primal | +6.147 |
Neg logit contributions | |
wagen | -9.474 |
CLASSIFIED | -8.517 |
alore | -8.206 |
thia | -8.124 |
ciation | -7.882 |
Token | otypes |
Token ID | 13567 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
KN | +0.336 |
Kem | +0.329 |
pel | +0.325 |
Primal | +0.322 |
Stephenson | +0.310 |
Neg logit contributions | |
wagen | -0.311 |
alore | -0.273 |
thia | -0.269 |
CLASSIFIED | -0.260 |
ciation | -0.255 |
Token | - |
Token ID | 12 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
wagen | +2.070 |
alore | +1.815 |
thia | +1.803 |
CLASSIFIED | +1.730 |
ciation | +1.714 |
Neg logit contributions | |
KN | -2.106 |
Kem | -2.039 |
pel | -2.020 |
Primal | -1.998 |
Stephenson | -1.924 |
Token | Ret |
Token ID | 9781 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
KN | +2.184 |
Kem | +2.096 |
pel | +2.080 |
Primal | +2.041 |
Ike | +1.963 |
Neg logit contributions | |
wagen | -2.464 |
alore | -2.198 |
thia | -2.159 |
CLASSIFIED | -2.068 |
ciation | -2.058 |
Token | ards |
Token ID | 1371 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
wagen | +0.289 |
alore | +0.254 |
thia | +0.250 |
CLASSIFIED | +0.241 |
ciation | +0.237 |
Neg logit contributions | |
KN | -0.311 |
Kem | -0.303 |
pel | -0.300 |
Primal | -0.297 |
Stephenson | -0.286 |
Token | Tony |
Token ID | 8832 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
wagen | +3.054 |
thia | +2.762 |
alore | +2.739 |
ciation | +2.617 |
CLASSIFIED | +2.608 |
Neg logit contributions | |
KN | -2.464 |
pel | -2.384 |
Kem | -2.318 |
Primal | -2.297 |
hower | -2.253 |
Token | Shal |
Token ID | 47974 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
wagen | +1.588 |
alore | +1.367 |
thia | +1.357 |
CLASSIFIED | +1.281 |
ciation | +1.266 |
Neg logit contributions | |
KN | -2.283 |
Kem | -2.225 |
pel | -2.215 |
Primal | -2.181 |
hower | -2.119 |
Token | h |
Token ID | 71 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
wagen | +0.068 |
alore | +0.060 |
CLASSIFIED | +0.059 |
thia | +0.059 |
ciation | +0.056 |
Neg logit contributions | |
KN | -0.067 |
pel | -0.065 |
Kem | -0.065 |
Primal | -0.064 |
hower | -0.061 |
Token | oub |
Token ID | 12944 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
wagen | +1.563 |
alore | +1.409 |
thia | +1.395 |
CLASSIFIED | +1.354 |
ciation | +1.338 |
Neg logit contributions | |
KN | -1.038 |
Kem | -1.008 |
pel | -0.992 |
Primal | -0.980 |
Stephenson | -0.931 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
wagen | +5.000 |
thia | +4.445 |
alore | +4.350 |
ciation | +4.253 |
CLASSIFIED | +4.218 |
Neg logit contributions | |
KN | -4.842 |
pel | -4.594 |
Kem | -4.570 |
Primal | -4.469 |
Emin | -4.306 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+01 |
Pos logit contributions | |
wagen | +0.343 |
alore | +0.308 |
thia | +0.303 |
CLASSIFIED | +0.299 |
ciation | +0.291 |
Neg logit contributions | |
KN | -0.238 |
Kem | -0.232 |
pel | -0.228 |
Primal | -0.225 |
Ike | -0.214 |
Token | 2008 |
Token ID | 11528 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
wagen | +5.961 |
CLASSIFIED | +5.377 |
thia | +5.191 |
Wo | +5.020 |
alore | +4.824 |
Neg logit contributions | |
Primal | -11.554 |
Kem | -11.411 |
Stephenson | -11.274 |
KN | -11.242 |
hower | -11.165 |
Token | Charlie |
Token ID | 11526 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
wagen | +1.536 |
alore | +1.372 |
thia | +1.370 |
CLASSIFIED | +1.313 |
ciation | +1.307 |
Neg logit contributions | |
KN | -1.279 |
pel | -1.234 |
Kem | -1.226 |
Primal | -1.204 |
hower | -1.162 |
Token | Sheen |
Token ID | 50189 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
KN | +0.445 |
Kem | +0.438 |
pel | +0.429 |
Primal | +0.427 |
Stephenson | +0.412 |
Neg logit contributions | |
wagen | -0.442 |
alore | -0.388 |
thia | -0.377 |
CLASSIFIED | -0.373 |
ciation | -0.360 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
wagen | +5.100 |
thia | +4.554 |
alore | +4.438 |
ciation | +4.348 |
CLASSIFIED | +4.254 |
Neg logit contributions | |
KN | -5.420 |
pel | -5.162 |
Kem | -5.119 |
Primal | -4.981 |
hower | -4.837 |
Token | Alec |
Token ID | 38285 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
KN | +0.636 |
Kem | +0.624 |
pel | +0.612 |
Primal | +0.607 |
Stephenson | +0.582 |
Neg logit contributions | |
wagen | -0.737 |
alore | -0.654 |
thia | -0.644 |
CLASSIFIED | -0.627 |
ciation | -0.615 |
Token | Ontario |
Token ID | 10553 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
KN | +2.730 |
Kem | +2.668 |
pel | +2.598 |
Primal | +2.583 |
Stephenson | +2.498 |
Neg logit contributions | |
wagen | -3.237 |
alore | -2.911 |
thia | -2.838 |
CLASSIFIED | -2.753 |
ciation | -2.738 |
Token | Ltd |
Token ID | 12052 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
wagen | +1.862 |
alore | +1.640 |
thia | +1.635 |
CLASSIFIED | +1.576 |
ciation | +1.551 |
Neg logit contributions | |
KN | -1.679 |
Kem | -1.622 |
pel | -1.621 |
Primal | -1.591 |
hower | -1.530 |
Token | ., |
Token ID | 1539 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
wagen | +0.725 |
alore | +0.645 |
thia | +0.640 |
CLASSIFIED | +0.620 |
ciation | +0.611 |
Neg logit contributions | |
KN | -0.569 |
Kem | -0.552 |
pel | -0.547 |
Primal | -0.540 |
Emin | -0.514 |
Token | a |
Token ID | 257 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
KN | +0.437 |
Kem | +0.427 |
pel | +0.419 |
Primal | +0.415 |
Stephenson | +0.397 |
Neg logit contributions | |
wagen | -0.580 |
alore | -0.520 |
thia | -0.514 |
CLASSIFIED | -0.500 |
ciation | -0.492 |
Token | Toronto |
Token ID | 6586 |
Feature activation | +5.30e+00 |
Pos logit contributions | |
wagen | +3.378 |
alore | +2.994 |
thia | +2.977 |
CLASSIFIED | +2.852 |
ciation | +2.830 |
Neg logit contributions | |
KN | -2.676 |
pel | -2.569 |
Kem | -2.526 |
Primal | -2.495 |
hower | -2.438 |
Token | - |
Token ID | 12 |
Feature activation | +1.16e+01 |
Pos logit contributions | |
wagen | +4.226 |
alore | +3.665 |
thia | +3.644 |
CLASSIFIED | +3.503 |
ciation | +3.454 |
Neg logit contributions | |
KN | -4.059 |
pel | -3.943 |
Kem | -3.885 |
Primal | -3.832 |
hower | -3.733 |
Token | based |
Token ID | 3106 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
wagen | +7.509 |
alore | +6.435 |
thia | +6.257 |
ciation | +6.002 |
CLASSIFIED | +5.980 |
Neg logit contributions | |
KN | -9.521 |
Primal | -9.480 |
Kem | -9.260 |
hower | -9.165 |
Emin | -9.052 |
Token | holding |
Token ID | 4769 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
wagen | +5.462 |
alore | +4.796 |
thia | +4.749 |
ciation | +4.562 |
CLASSIFIED | +4.537 |
Neg logit contributions | |
KN | -4.540 |
pel | -4.360 |
Primal | -4.185 |
Kem | -4.182 |
hower | -4.165 |
Token | company |
Token ID | 1664 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
KN | +0.077 |
Kem | +0.075 |
pel | +0.074 |
Primal | +0.073 |
Stephenson | +0.071 |
Neg logit contributions | |
wagen | -0.085 |
alore | -0.076 |
thia | -0.075 |
CLASSIFIED | -0.072 |
ciation | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
wagen | +1.137 |
alore | +1.014 |
thia | +1.000 |
CLASSIFIED | +0.970 |
ciation | +0.960 |
Neg logit contributions | |
KN | -0.909 |
Kem | -0.878 |
pel | -0.874 |
Primal | -0.862 |
hower | -0.824 |
Token | which |
Token ID | 543 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
wagen | +1.131 |
alore | +1.010 |
thia | +0.998 |
CLASSIFIED | +0.968 |
ciation | +0.958 |
Neg logit contributions | |
KN | -0.874 |
Kem | -0.844 |
pel | -0.840 |
Primal | -0.826 |
hower | -0.793 |
Token | of |
Token ID | 286 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
KN | +1.211 |
Kem | +1.181 |
pel | +1.164 |
Primal | +1.151 |
Stephenson | +1.097 |
Neg logit contributions | |
wagen | -1.610 |
alore | -1.443 |
thia | -1.427 |
CLASSIFIED | -1.385 |
ciation | -1.366 |
Token | Pro |
Token ID | 1041 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
wagen | +3.143 |
alore | +2.782 |
thia | +2.735 |
CLASSIFIED | +2.671 |
ciation | +2.618 |
Neg logit contributions | |
KN | -2.792 |
pel | -2.686 |
Kem | -2.679 |
Primal | -2.617 |
hower | -2.550 |
Token | Football |
Token ID | 9957 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
KN | +3.251 |
Kem | +3.165 |
pel | +3.150 |
Primal | +3.093 |
Stephenson | +2.983 |
Neg logit contributions | |
wagen | -3.643 |
alore | -3.274 |
thia | -3.201 |
CLASSIFIED | -3.129 |
ciation | -3.055 |
Token | Focus |
Token ID | 17061 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
wagen | +0.715 |
alore | +0.643 |
thia | +0.633 |
CLASSIFIED | +0.612 |
ciation | +0.608 |
Neg logit contributions | |
KN | -0.560 |
Kem | -0.542 |
pel | -0.537 |
Primal | -0.527 |
hower | -0.508 |
Token | unless |
Token ID | 4556 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
wagen | +0.566 |
alore | +0.503 |
thia | +0.497 |
CLASSIFIED | +0.482 |
ciation | +0.475 |
Neg logit contributions | |
KN | -0.478 |
Kem | -0.465 |
pel | -0.459 |
Primal | -0.454 |
Stephenson | -0.434 |
Token | otherwise |
Token ID | 4306 |
Feature activation | +1.10e+01 |
Pos logit contributions | |
wagen | +1.439 |
alore | +1.288 |
thia | +1.270 |
CLASSIFIED | +1.233 |
ciation | +1.213 |
Neg logit contributions | |
KN | -1.220 |
Kem | -1.190 |
pel | -1.176 |
Primal | -1.153 |
hower | -1.111 |
Token | indicated |
Token ID | 8203 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
wagen | +6.375 |
alore | +5.897 |
thia | +5.644 |
ciation | +5.272 |
Wo | +4.991 |
Neg logit contributions | |
KN | -9.626 |
Kem | -9.491 |
pel | -9.275 |
hower | -8.887 |
ohyd | -8.762 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
wagen | +3.438 |
alore | +2.998 |
thia | +2.987 |
CLASSIFIED | +2.917 |
ciation | +2.854 |
Neg logit contributions | |
KN | -3.483 |
Kem | -3.423 |
pel | -3.358 |
Primal | -3.300 |
hower | -3.231 |
Token | All |
Token ID | 1439 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
wagen | +2.248 |
thia | +2.009 |
alore | +2.003 |
CLASSIFIED | +1.942 |
ciation | +1.912 |
Neg logit contributions | |
KN | -1.774 |
pel | -1.735 |
Kem | -1.735 |
Primal | -1.681 |
hower | -1.634 |
Token | salary |
Token ID | 9588 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
wagen | +0.045 |
alore | +0.040 |
thia | +0.040 |
CLASSIFIED | +0.038 |
ciation | +0.038 |
Neg logit contributions | |
KN | -0.035 |
Kem | -0.034 |
pel | -0.033 |
Primal | -0.033 |
Stephenson | -0.031 |
Token | - |
Token ID | 12 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
KN | +0.944 |
Kem | +0.928 |
pel | +0.907 |
Primal | +0.898 |
Stephenson | +0.862 |
Neg logit contributions | |
wagen | -1.378 |
alore | -1.251 |
thia | -1.237 |
CLASSIFIED | -1.196 |
ciation | -1.181 |
Token | on |
Token ID | 319 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
KN | +1.589 |
Kem | +1.545 |
Primal | +1.522 |
pel | +1.518 |
Stephenson | +1.439 |
Neg logit contributions | |
wagen | -2.142 |
alore | -1.922 |
thia | -1.891 |
CLASSIFIED | -1.845 |
ciation | -1.818 |
Token | Twitter |
Token ID | 3009 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
KN | +3.649 |
Kem | +3.587 |
Primal | +3.513 |
pel | +3.329 |
Stephenson | +3.310 |
Neg logit contributions | |
wagen | -6.034 |
alore | -5.429 |
thia | -5.305 |
ciation | -5.191 |
CLASSIFIED | -5.138 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
KN | +1.994 |
Kem | +1.929 |
pel | +1.905 |
Primal | +1.896 |
Stephenson | +1.807 |
Neg logit contributions | |
wagen | -2.648 |
alore | -2.369 |
thia | -2.325 |
CLASSIFIED | -2.276 |
ciation | -2.246 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
KN | +0.475 |
Kem | +0.463 |
Primal | +0.452 |
pel | +0.452 |
Stephenson | +0.428 |
Neg logit contributions | |
wagen | -0.724 |
alore | -0.652 |
thia | -0.641 |
CLASSIFIED | -0.627 |
ciation | -0.617 |
Token | Media |
Token ID | 13152 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
wagen | +1.114 |
alore | +0.989 |
thia | +0.978 |
CLASSIFIED | +0.949 |
ciation | +0.933 |
Neg logit contributions | |
KN | -0.979 |
Kem | -0.959 |
pel | -0.944 |
Primal | -0.937 |
Stephenson | -0.899 |
Token | playback |
Token ID | 16388 |
Feature activation | +1.17e+01 |
Pos logit contributions | |
wagen | +3.739 |
alore | +3.288 |
thia | +3.278 |
CLASSIFIED | +3.197 |
ciation | +3.121 |
Neg logit contributions | |
KN | -2.837 |
Kem | -2.771 |
pel | -2.722 |
Primal | -2.680 |
hower | -2.594 |
Token | is |
Token ID | 318 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
wagen | +7.197 |
thia | +6.429 |
alore | +6.199 |
ciation | +5.922 |
Wo | +5.697 |
Neg logit contributions | |
KN | -9.935 |
hower | -9.690 |
pel | -9.386 |
Kem | -9.275 |
Primal | -9.041 |
Token | unsupported |
Token ID | 24222 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
wagen | +0.956 |
alore | +0.711 |
thia | +0.658 |
CLASSIFIED | +0.598 |
ciation | +0.554 |
Neg logit contributions | |
KN | -3.534 |
Kem | -3.458 |
pel | -3.449 |
Primal | -3.403 |
hower | -3.341 |
Token | on |
Token ID | 319 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
wagen | +4.774 |
thia | +4.335 |
alore | +4.315 |
ciation | +4.025 |
CLASSIFIED | +3.966 |
Neg logit contributions | |
KN | -5.089 |
Kem | -4.954 |
pel | -4.911 |
hower | -4.799 |
Primal | -4.795 |
Token | your |
Token ID | 534 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
wagen | +1.561 |
alore | +1.392 |
thia | +1.376 |
CLASSIFIED | +1.326 |
ciation | +1.310 |
Neg logit contributions | |
KN | -1.339 |
Kem | -1.302 |
pel | -1.285 |
Primal | -1.269 |
Stephenson | -1.221 |
Token | device |
Token ID | 3335 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
wagen | +2.377 |
alore | +1.998 |
thia | +1.993 |
CLASSIFIED | +1.868 |
ciation | +1.833 |
Neg logit contributions | |
KN | -3.618 |
Kem | -3.521 |
pel | -3.487 |
Primal | -3.463 |
hower | -3.379 |
Token | Pasadena |
Token ID | 41010 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
wagen | +0.556 |
alore | +0.497 |
thia | +0.491 |
CLASSIFIED | +0.476 |
ciation | +0.469 |
Neg logit contributions | |
KN | -0.451 |
Kem | -0.440 |
pel | -0.434 |
Primal | -0.429 |
Stephenson | -0.410 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
wagen | +0.446 |
alore | +0.397 |
thia | +0.393 |
CLASSIFIED | +0.378 |
ciation | +0.374 |
Neg logit contributions | |
KN | -0.387 |
Kem | -0.376 |
pel | -0.372 |
Primal | -0.367 |
Stephenson | -0.351 |
Token | California |
Token ID | 3442 |
Feature activation | +6.51e-03 |
Pos logit contributions | |
KN | +0.930 |
Kem | +0.910 |
pel | +0.891 |
Primal | +0.886 |
Stephenson | +0.841 |
Neg logit contributions | |
wagen | -1.396 |
alore | -1.257 |
thia | -1.244 |
CLASSIFIED | -1.214 |
ciation | -1.196 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
wagen | +0.005 |
alore | +0.005 |
thia | +0.005 |
CLASSIFIED | +0.005 |
ciation | +0.005 |
Neg logit contributions | |
KN | -0.005 |
Kem | -0.005 |
pel | -0.005 |
Primal | -0.005 |
Stephenson | -0.004 |
Token | Hide |
Token ID | 10415 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
wagen | +2.732 |
alore | +2.470 |
thia | +2.465 |
CLASSIFIED | +2.374 |
ciation | +2.357 |
Neg logit contributions | |
KN | -1.855 |
pel | -1.778 |
Kem | -1.777 |
Primal | -1.719 |
hower | -1.666 |
Token | Caption |
Token ID | 11260 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
wagen | +1.371 |
alore | +1.265 |
thia | +1.254 |
CLASSIFIED | +1.228 |
ciation | +1.215 |
Neg logit contributions | |
KN | -0.429 |
Kem | -0.409 |
pel | -0.398 |
Primal | -0.389 |
Stephenson | -0.355 |
Token | 11 |
Token ID | 1367 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
wagen | +7.237 |
thia | +7.157 |
ciation | +6.468 |
alore | +6.309 |
Wo | +6.220 |
Neg logit contributions | |
KN | -9.092 |
hower | -8.630 |
pel | -8.554 |
Kem | -8.111 |
Primal | -7.847 |
Token | of |
Token ID | 286 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
wagen | +1.174 |
alore | +1.050 |
thia | +1.039 |
CLASSIFIED | +1.007 |
ciation | +0.994 |
Neg logit contributions | |
KN | -0.909 |
Kem | -0.885 |
pel | -0.874 |
Primal | -0.863 |
Stephenson | -0.824 |
Token | 15 |
Token ID | 1315 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
KN | +1.772 |
Kem | +1.730 |
pel | +1.692 |
Primal | +1.674 |
Stephenson | +1.607 |
Neg logit contributions | |
wagen | -3.159 |
alore | -2.858 |
CLASSIFIED | -2.773 |
thia | -2.758 |
akeru | -2.674 |
Token | Photos |
Token ID | 9434 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
KN | +0.688 |
Kem | +0.672 |
Primal | +0.656 |
pel | +0.656 |
Ike | +0.614 |
Neg logit contributions | |
wagen | -1.315 |
alore | -1.201 |
thia | -1.172 |
CLASSIFIED | -1.165 |
ciation | -1.130 |
Token | : |
Token ID | 25 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
wagen | +2.671 |
thia | +2.368 |
alore | +2.360 |
ciation | +2.240 |
CLASSIFIED | +2.221 |
Neg logit contributions | |
KN | -2.705 |
Kem | -2.637 |
pel | -2.615 |
Primal | -2.574 |
hower | -2.517 |
Token | character |
Token ID | 2095 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
wagen | +0.219 |
alore | +0.196 |
thia | +0.193 |
CLASSIFIED | +0.188 |
ciation | +0.185 |
Neg logit contributions | |
KN | -0.170 |
Kem | -0.165 |
pel | -0.163 |
Primal | -0.161 |
Stephenson | -0.154 |
Token | was |
Token ID | 373 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
wagen | +4.885 |
alore | +4.420 |
thia | +4.344 |
ciation | +4.170 |
CLASSIFIED | +4.145 |
Neg logit contributions | |
KN | -3.985 |
pel | -3.855 |
Kem | -3.729 |
Primal | -3.698 |
hower | -3.586 |
Token | retired |
Token ID | 9880 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
wagen | +1.816 |
alore | +1.639 |
thia | +1.616 |
CLASSIFIED | +1.568 |
ciation | +1.547 |
Neg logit contributions | |
KN | -1.297 |
Kem | -1.251 |
pel | -1.243 |
Primal | -1.219 |
hower | -1.171 |
Token | out |
Token ID | 503 |
Feature activation | +4.50e+00 |
Pos logit contributions | |
wagen | +0.076 |
alore | +0.068 |
thia | +0.067 |
CLASSIFIED | +0.065 |
ciation | +0.064 |
Neg logit contributions | |
KN | -0.060 |
Kem | -0.059 |
pel | -0.058 |
Primal | -0.057 |
Stephenson | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
wagen | +3.709 |
alore | +3.268 |
thia | +3.248 |
CLASSIFIED | +3.130 |
ciation | +3.111 |
Neg logit contributions | |
KN | -3.281 |
Kem | -3.236 |
pel | -3.209 |
Primal | -3.177 |
Emin | -3.071 |
Token | def |
Token ID | 825 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
wagen | +4.320 |
alore | +3.877 |
thia | +3.810 |
ciation | +3.646 |
CLASSIFIED | +3.641 |
Neg logit contributions | |
KN | -3.577 |
pel | -3.478 |
Kem | -3.426 |
Primal | -3.375 |
hower | -3.280 |
Token | erence |
Token ID | 1945 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
wagen | +3.960 |
alore | +3.329 |
thia | +3.226 |
ciation | +2.956 |
CLASSIFIED | +2.840 |
Neg logit contributions | |
KN | -6.397 |
Primal | -6.281 |
Kem | -6.268 |
pel | -6.216 |
Stephenson | -6.077 |
Token | to |
Token ID | 284 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
KN | +0.164 |
Kem | +0.159 |
pel | +0.157 |
Primal | +0.155 |
Stephenson | +0.148 |
Neg logit contributions | |
wagen | -0.222 |
alore | -0.199 |
thia | -0.197 |
CLASSIFIED | -0.191 |
ciation | -0.189 |
Token | H |
Token ID | 367 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
KN | +1.324 |
Kem | +1.302 |
pel | +1.267 |
Primal | +1.260 |
Stephenson | +1.206 |
Neg logit contributions | |
wagen | -1.825 |
alore | -1.639 |
thia | -1.619 |
CLASSIFIED | -1.576 |
ciation | -1.555 |
Token | enson |
Token ID | 19069 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
wagen | +1.730 |
alore | +1.524 |
thia | +1.505 |
CLASSIFIED | +1.443 |
ciation | +1.429 |
Neg logit contributions | |
KN | -1.760 |
Kem | -1.730 |
pel | -1.706 |
Primal | -1.698 |
Stephenson | -1.626 |
Token | 's |
Token ID | 338 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
KN | +1.243 |
Kem | +1.222 |
pel | +1.193 |
Primal | +1.189 |
Stephenson | +1.137 |
Neg logit contributions | |
wagen | -1.522 |
alore | -1.356 |
thia | -1.344 |
CLASSIFIED | -1.306 |
ciation | -1.281 |
Token | used |
Token ID | 973 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
wagen | +4.279 |
alore | +3.865 |
thia | +3.841 |
CLASSIFIED | +3.649 |
ciation | +3.620 |
Neg logit contributions | |
KN | -3.256 |
pel | -3.113 |
Kem | -3.090 |
Primal | -3.034 |
hower | -2.977 |
Token | DNA |
Token ID | 7446 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
wagen | +1.314 |
alore | +1.172 |
thia | +1.160 |
CLASSIFIED | +1.124 |
ciation | +1.107 |
Neg logit contributions | |
KN | -1.064 |
Kem | -1.034 |
pel | -1.023 |
Primal | -1.011 |
Stephenson | -0.964 |
Token | evidence |
Token ID | 2370 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
wagen | +0.685 |
alore | +0.610 |
thia | +0.599 |
CLASSIFIED | +0.582 |
ciation | +0.573 |
Neg logit contributions | |
KN | -0.612 |
Kem | -0.599 |
pel | -0.591 |
Primal | -0.582 |
Stephenson | -0.560 |
Token | to |
Token ID | 284 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
wagen | +1.770 |
alore | +1.586 |
thia | +1.574 |
CLASSIFIED | +1.522 |
ciation | +1.502 |
Neg logit contributions | |
KN | -1.340 |
Kem | -1.294 |
pel | -1.282 |
Primal | -1.272 |
hower | -1.209 |
Token | discover |
Token ID | 7073 |
Feature activation | +5.07e+00 |
Pos logit contributions | |
wagen | +3.411 |
alore | +3.062 |
thia | +3.049 |
CLASSIFIED | +2.880 |
ciation | +2.862 |
Neg logit contributions | |
KN | -2.768 |
Kem | -2.685 |
pel | -2.647 |
Primal | -2.623 |
hower | -2.558 |
Token | the |
Token ID | 262 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
wagen | +4.215 |
thia | +3.799 |
alore | +3.718 |
CLASSIFIED | +3.602 |
ciation | +3.520 |
Neg logit contributions | |
KN | -3.634 |
pel | -3.494 |
Primal | -3.462 |
Kem | -3.430 |
hower | -3.386 |
Token | identity |
Token ID | 5369 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
wagen | +3.650 |
thia | +3.260 |
alore | +3.249 |
CLASSIFIED | +3.085 |
ciation | +3.052 |
Neg logit contributions | |
KN | -3.322 |
pel | -3.223 |
Kem | -3.157 |
Primal | -3.136 |
hower | -3.111 |
Token | of |
Token ID | 286 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
wagen | +1.415 |
alore | +1.256 |
thia | +1.254 |
CLASSIFIED | +1.216 |
ciation | +1.196 |
Neg logit contributions | |
KN | -1.185 |
pel | -1.141 |
Kem | -1.141 |
Primal | -1.128 |
hower | -1.080 |
Token | the |
Token ID | 262 |
Feature activation | +4.81e+00 |
Pos logit contributions | |
wagen | +3.796 |
thia | +3.454 |
alore | +3.365 |
CLASSIFIED | +3.234 |
ciation | +3.184 |
Neg logit contributions | |
KN | -3.273 |
pel | -3.157 |
Primal | -3.096 |
Kem | -3.053 |
hower | -3.030 |
Token | killer |
Token ID | 11868 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
wagen | +4.088 |
thia | +3.685 |
alore | +3.667 |
CLASSIFIED | +3.476 |
ciation | +3.436 |
Neg logit contributions | |
KN | -3.345 |
pel | -3.245 |
Primal | -3.148 |
hower | -3.145 |
Kem | -3.137 |
Token | of |
Token ID | 286 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
wagen | +2.208 |
alore | +1.953 |
thia | +1.951 |
CLASSIFIED | +1.874 |
ciation | +1.851 |
Neg logit contributions | |
KN | -1.828 |
pel | -1.765 |
Kem | -1.757 |
Primal | -1.740 |
hower | -1.670 |
Token | on |
Token ID | 319 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
KN | +1.332 |
Kem | +1.306 |
pel | +1.272 |
Primal | +1.264 |
Ike | +1.201 |
Neg logit contributions | |
wagen | -1.973 |
alore | -1.783 |
thia | -1.755 |
CLASSIFIED | -1.716 |
ciation | -1.699 |
Token | the |
Token ID | 262 |
Feature activation | -6.18e+00 |
Pos logit contributions | |
KN | +1.583 |
Kem | +1.558 |
pel | +1.516 |
Primal | +1.507 |
Stephenson | +1.443 |
Neg logit contributions | |
wagen | -2.246 |
alore | -2.006 |
thia | -1.997 |
CLASSIFIED | -1.936 |
ciation | -1.919 |
Token | court |
Token ID | 2184 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
Kem | +2.918 |
KN | +2.896 |
pel | +2.810 |
Primal | +2.779 |
Stephenson | +2.577 |
Neg logit contributions | |
wagen | -6.763 |
alore | -6.220 |
thia | -6.208 |
CLASSIFIED | -6.173 |
ciation | -6.043 |
Token | at |
Token ID | 379 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
KN | +2.219 |
Kem | +2.198 |
pel | +2.157 |
Primal | +2.119 |
Stephenson | +2.027 |
Neg logit contributions | |
wagen | -3.153 |
alore | -2.866 |
thia | -2.813 |
CLASSIFIED | -2.759 |
ciation | -2.702 |
Token | the |
Token ID | 262 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
KN | +1.669 |
Kem | +1.639 |
Primal | +1.588 |
pel | +1.580 |
Stephenson | +1.523 |
Neg logit contributions | |
wagen | -2.252 |
alore | -2.019 |
thia | -2.004 |
CLASSIFIED | -1.962 |
ciation | -1.918 |
Token | beginning |
Token ID | 3726 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
KN | +3.261 |
Kem | +3.248 |
Primal | +3.131 |
pel | +3.110 |
Stephenson | +3.005 |
Neg logit contributions | |
wagen | -4.096 |
alore | -3.715 |
thia | -3.660 |
CLASSIFIED | -3.568 |
ciation | -3.518 |
Token | of |
Token ID | 286 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
wagen | +3.230 |
alore | +2.864 |
thia | +2.838 |
ciation | +2.749 |
CLASSIFIED | +2.726 |
Neg logit contributions | |
KN | -2.934 |
Kem | -2.832 |
pel | -2.829 |
Primal | -2.784 |
Emin | -2.671 |
Token | this |
Token ID | 428 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
KN | +0.236 |
Kem | +0.230 |
pel | +0.227 |
Primal | +0.224 |
Stephenson | +0.214 |
Neg logit contributions | |
wagen | -0.301 |
alore | -0.269 |
thia | -0.266 |
CLASSIFIED | -0.259 |
ciation | -0.255 |
Token | year |
Token ID | 614 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
KN | +0.795 |
Kem | +0.781 |
pel | +0.763 |
Primal | +0.758 |
Stephenson | +0.724 |
Neg logit contributions | |
wagen | -1.126 |
alore | -1.013 |
thia | -1.005 |
CLASSIFIED | -0.983 |
ciation | -0.964 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
KN | +0.012 |
Kem | +0.012 |
pel | +0.011 |
Primal | +0.011 |
Stephenson | +0.011 |
Neg logit contributions | |
wagen | -0.014 |
alore | -0.013 |
thia | -0.013 |
CLASSIFIED | -0.012 |
ciation | -0.012 |
Token | work |
Token ID | 670 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
KN | +0.991 |
Kem | +0.972 |
pel | +0.952 |
Primal | +0.944 |
Stephenson | +0.903 |
Neg logit contributions | |
wagen | -1.280 |
alore | -1.150 |
thia | -1.133 |
CLASSIFIED | -1.107 |
ciation | -1.088 |
Token | . |
Token ID | 13 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
wagen | +2.889 |
thia | +2.569 |
alore | +2.537 |
ciation | +2.403 |
CLASSIFIED | +2.399 |
Neg logit contributions | |
KN | -2.935 |
Kem | -2.844 |
pel | -2.841 |
Primal | -2.782 |
hower | -2.724 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
wagen | +4.047 |
thia | +3.621 |
alore | +3.596 |
CLASSIFIED | +3.440 |
ciation | +3.430 |
Neg logit contributions | |
KN | -3.472 |
Kem | -3.393 |
pel | -3.390 |
Primal | -3.308 |
hower | -3.250 |
Token |
|
Token ID | 198 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
wagen | +1.283 |
alore | +1.150 |
thia | +1.138 |
CLASSIFIED | +1.105 |
ciation | +1.090 |
Neg logit contributions | |
KN | -0.953 |
Kem | -0.927 |
pel | -0.914 |
Primal | -0.903 |
Stephenson | -0.861 |
Token | Out |
Token ID | 7975 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
wagen | +4.150 |
thia | +3.621 |
alore | +3.611 |
CLASSIFIED | +3.573 |
ciation | +3.467 |
Neg logit contributions | |
Kem | -3.769 |
KN | -3.756 |
Primal | -3.709 |
pel | -3.691 |
hower | -3.585 |
Token | routes |
Token ID | 11926 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
wagen | +2.813 |
alore | +2.474 |
thia | +2.460 |
CLASSIFIED | +2.387 |
ciation | +2.353 |
Neg logit contributions | |
KN | -2.324 |
Kem | -2.259 |
pel | -2.238 |
Primal | -2.200 |
Emin | -2.147 |
Token | were |
Token ID | 547 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
wagen | +2.324 |
alore | +2.067 |
thia | +2.045 |
CLASSIFIED | +1.982 |
ciation | +1.962 |
Neg logit contributions | |
KN | -1.824 |
Kem | -1.763 |
pel | -1.756 |
Primal | -1.726 |
Emin | -1.654 |
Token | the |
Token ID | 262 |
Feature activation | +5.51e+00 |
Pos logit contributions | |
wagen | +3.219 |
alore | +2.884 |
thia | +2.851 |
CLASSIFIED | +2.773 |
ciation | +2.724 |
Neg logit contributions | |
KN | -2.388 |
Kem | -2.293 |
pel | -2.292 |
Primal | -2.234 |
Emin | -2.157 |
Token | b |
Token ID | 275 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
wagen | +4.937 |
alore | +4.377 |
thia | +4.348 |
CLASSIFIED | +4.186 |
ciation | +4.084 |
Neg logit contributions | |
KN | -3.629 |
pel | -3.503 |
Kem | -3.486 |
Primal | -3.371 |
hower | -3.338 |
Token | ane |
Token ID | 1531 |
Feature activation | -4.88e+00 |
Pos logit contributions | |
KN | +1.042 |
Kem | +0.989 |
pel | +0.975 |
Primal | +0.954 |
Stephenson | +0.909 |
Neg logit contributions | |
wagen | -1.961 |
alore | -1.776 |
thia | -1.765 |
CLASSIFIED | -1.757 |
ciation | -1.702 |
Token | of |
Token ID | 286 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
KN | +3.071 |
Kem | +2.986 |
pel | +2.922 |
Primal | +2.914 |
Stephenson | +2.780 |
Neg logit contributions | |
wagen | -4.581 |
alore | -4.145 |
thia | -4.112 |
CLASSIFIED | -4.007 |
ciation | -3.879 |
Token | Wallace |
Token ID | 17161 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
wagen | +1.660 |
alore | +1.466 |
thia | +1.448 |
CLASSIFIED | +1.403 |
ciation | +1.379 |
Neg logit contributions | |
KN | -1.554 |
pel | -1.503 |
Kem | -1.500 |
Primal | -1.471 |
Emin | -1.413 |
Token | reb |
Token ID | 3405 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
wagen | +1.686 |
alore | +1.492 |
thia | +1.474 |
ciation | +1.406 |
CLASSIFIED | +1.404 |
Neg logit contributions | |
KN | -1.494 |
Kem | -1.451 |
pel | -1.435 |
Primal | -1.411 |
hower | -1.362 |
Token | road |
Token ID | 6344 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
wagen | +0.869 |
alore | +0.769 |
thia | +0.761 |
CLASSIFIED | +0.739 |
ciation | +0.725 |
Neg logit contributions | |
KN | -0.797 |
Kem | -0.776 |
pel | -0.769 |
Primal | -0.759 |
Stephenson | -0.727 |
Token | cast |
Token ID | 2701 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
wagen | +0.401 |
alore | +0.349 |
thia | +0.345 |
CLASSIFIED | +0.331 |
ciation | +0.325 |
Neg logit contributions | |
KN | -0.465 |
Kem | -0.454 |
pel | -0.451 |
Primal | -0.446 |
Stephenson | -0.429 |
Token | repeatedly |
Token ID | 7830 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
wagen | +1.031 |
alore | +0.920 |
thia | +0.909 |
CLASSIFIED | +0.883 |
ciation | +0.872 |
Neg logit contributions | |
KN | -0.854 |
Kem | -0.828 |
pel | -0.821 |
Primal | -0.807 |
Stephenson | -0.775 |
Token | afterwards |
Token ID | 12979 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
wagen | +0.930 |
alore | +0.829 |
thia | +0.820 |
CLASSIFIED | +0.793 |
ciation | +0.782 |
Neg logit contributions | |
KN | -0.796 |
Kem | -0.773 |
pel | -0.764 |
Primal | -0.755 |
Stephenson | -0.723 |
Token | !) |
Token ID | 8133 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
wagen | +1.819 |
alore | +1.606 |
thia | +1.591 |
CLASSIFIED | +1.527 |
ciation | +1.511 |
Neg logit contributions | |
KN | -1.799 |
Kem | -1.746 |
pel | -1.730 |
Primal | -1.709 |
Stephenson | -1.643 |
Token |
|
Token ID | 198 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
wagen | +3.514 |
thia | +3.146 |
alore | +3.104 |
CLASSIFIED | +3.003 |
ciation | +2.959 |
Neg logit contributions | |
KN | -2.932 |
pel | -2.819 |
Kem | -2.816 |
Primal | -2.763 |
hower | -2.679 |
Token |
|
Token ID | 198 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
wagen | +2.577 |
thia | +2.301 |
alore | +2.297 |
ciation | +2.191 |
CLASSIFIED | +2.184 |
Neg logit contributions | |
KN | -2.098 |
Kem | -2.050 |
pel | -2.026 |
Primal | -2.000 |
hower | -1.937 |
Token | Format |
Token ID | 26227 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
wagen | +2.574 |
thia | +2.244 |
alore | +2.236 |
CLASSIFIED | +2.155 |
ciation | +2.113 |
Neg logit contributions | |
KN | -2.863 |
Kem | -2.844 |
Primal | -2.794 |
pel | -2.775 |
hower | -2.719 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
KN | +0.247 |
Kem | +0.241 |
pel | +0.238 |
Primal | +0.235 |
Stephenson | +0.225 |
Neg logit contributions | |
wagen | -0.280 |
alore | -0.249 |
thia | -0.245 |
CLASSIFIED | -0.238 |
ciation | -0.234 |
Token |
|
Token ID | 198 |
Feature activation | -3.73e+00 |
Pos logit contributions | |
KN | +1.735 |
Kem | +1.668 |
pel | +1.644 |
Primal | +1.625 |
Ike | +1.537 |
Neg logit contributions | |
wagen | -2.897 |
alore | -2.635 |
CLASSIFIED | -2.598 |
thia | -2.549 |
ciation | -2.476 |
Token | I |
Token ID | 314 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
KN | +0.581 |
Kem | +0.567 |
pel | +0.558 |
Primal | +0.552 |
Stephenson | +0.528 |
Neg logit contributions | |
wagen | -0.734 |
alore | -0.655 |
thia | -0.646 |
CLASSIFIED | -0.631 |
ciation | -0.618 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
KN | +3.031 |
Kem | +2.931 |
pel | +2.902 |
Primal | +2.862 |
Stephenson | +2.708 |
Neg logit contributions | |
wagen | -4.226 |
alore | -3.753 |
CLASSIFIED | -3.742 |
thia | -3.687 |
ciation | -3.550 |
Token | experiencing |
Token ID | 13456 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
KN | +0.730 |
Kem | +0.711 |
pel | +0.700 |
Primal | +0.694 |
Stephenson | +0.661 |
Neg logit contributions | |
wagen | -1.031 |
alore | -0.925 |
thia | -0.918 |
CLASSIFIED | -0.891 |
ciation | -0.880 |
Token | . |
Token ID | 13 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
wagen | +2.899 |
alore | +2.595 |
thia | +2.560 |
CLASSIFIED | +2.448 |
ciation | +2.444 |
Neg logit contributions | |
KN | -2.703 |
Kem | -2.614 |
pel | -2.607 |
Primal | -2.553 |
hower | -2.473 |
Token | It |
Token ID | 632 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
KN | +0.667 |
Kem | +0.652 |
Primal | +0.637 |
pel | +0.636 |
Stephenson | +0.607 |
Neg logit contributions | |
wagen | -0.855 |
alore | -0.767 |
thia | -0.752 |
CLASSIFIED | -0.730 |
ciation | -0.719 |
Token | 's |
Token ID | 338 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
wagen | +1.390 |
alore | +1.240 |
thia | +1.226 |
CLASSIFIED | +1.166 |
ciation | +1.161 |
Neg logit contributions | |
KN | -1.353 |
Kem | -1.318 |
pel | -1.305 |
Primal | -1.285 |
hower | -1.241 |
Token | my |
Token ID | 616 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
wagen | +1.795 |
alore | +1.606 |
thia | +1.589 |
CLASSIFIED | +1.539 |
ciation | +1.511 |
Neg logit contributions | |
KN | -1.427 |
Kem | -1.384 |
pel | -1.372 |
Primal | -1.343 |
hower | -1.298 |
Token | preference |
Token ID | 12741 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
wagen | +2.331 |
alore | +2.088 |
thia | +2.065 |
CLASSIFIED | +2.002 |
ciation | +1.962 |
Neg logit contributions | |
KN | -1.769 |
Kem | -1.711 |
pel | -1.697 |
Primal | -1.655 |
hower | -1.602 |
Token | and |
Token ID | 290 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
wagen | +2.002 |
alore | +1.784 |
thia | +1.761 |
CLASSIFIED | +1.703 |
ciation | +1.690 |
Neg logit contributions | |
KN | -1.696 |
Kem | -1.639 |
pel | -1.628 |
Primal | -1.599 |
hower | -1.532 |
Token | I |
Token ID | 314 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
KN | +1.523 |
Kem | +1.502 |
Primal | +1.468 |
pel | +1.460 |
Stephenson | +1.397 |
Neg logit contributions | |
wagen | -1.951 |
alore | -1.746 |
thia | -1.735 |
CLASSIFIED | -1.678 |
ciation | -1.662 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
KN | +0.685 |
Kem | +0.667 |
pel | +0.658 |
Primal | +0.651 |
Stephenson | +0.620 |
Neg logit contributions | |
wagen | -0.878 |
alore | -0.785 |
thia | -0.774 |
CLASSIFIED | -0.758 |
ciation | -0.740 |
Token | not |
Token ID | 407 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
KN | +1.503 |
Kem | +1.474 |
pel | +1.457 |
Primal | +1.433 |
Ike | +1.367 |
Neg logit contributions | |
wagen | -1.915 |
alore | -1.694 |
thia | -1.684 |
CLASSIFIED | -1.670 |
ciation | -1.612 |
Token | come |
Token ID | 1282 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
KN | +0.603 |
Kem | +0.588 |
pel | +0.581 |
Primal | +0.574 |
Stephenson | +0.547 |
Neg logit contributions | |
wagen | -0.756 |
alore | -0.673 |
thia | -0.666 |
CLASSIFIED | -0.651 |
ciation | -0.638 |
Token | to |
Token ID | 284 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
wagen | +2.076 |
alore | +1.864 |
thia | +1.841 |
CLASSIFIED | +1.778 |
ciation | +1.752 |
Neg logit contributions | |
KN | -1.615 |
pel | -1.555 |
Kem | -1.555 |
Primal | -1.525 |
Emin | -1.463 |
Token | a |
Token ID | 257 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
wagen | +3.215 |
alore | +2.868 |
thia | +2.825 |
CLASSIFIED | +2.754 |
ciation | +2.681 |
Neg logit contributions | |
KN | -2.676 |
pel | -2.592 |
Kem | -2.579 |
Primal | -2.551 |
hower | -2.435 |
Token | head |
Token ID | 1182 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
KN | +0.387 |
Kem | +0.377 |
pel | +0.367 |
Primal | +0.363 |
Stephenson | +0.347 |
Neg logit contributions | |
wagen | -0.638 |
alore | -0.579 |
thia | -0.574 |
CLASSIFIED | -0.557 |
ciation | -0.552 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
KN | +0.009 |
Kem | +0.009 |
pel | +0.009 |
Primal | +0.008 |
Stephenson | +0.008 |
Neg logit contributions | |
wagen | -0.011 |
alore | -0.010 |
thia | -0.010 |
CLASSIFIED | -0.010 |
ciation | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
wagen | +0.492 |
alore | +0.440 |
thia | +0.437 |
CLASSIFIED | +0.424 |
ciation | +0.418 |
Neg logit contributions | |
KN | -0.373 |
Kem | -0.362 |
pel | -0.359 |
Primal | -0.354 |
hower | -0.337 |
Token |
|
Token ID | 198 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
wagen | +0.777 |
alore | +0.698 |
thia | +0.688 |
CLASSIFIED | +0.672 |
ciation | +0.661 |
Neg logit contributions | |
KN | -0.563 |
Kem | -0.548 |
pel | -0.539 |
Primal | -0.533 |
Stephenson | -0.507 |
Token | " |
Token ID | 1 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
wagen | +1.169 |
alore | +1.033 |
thia | +1.021 |
CLASSIFIED | +0.988 |
ciation | +0.971 |
Neg logit contributions | |
KN | -1.122 |
Kem | -1.096 |
pel | -1.083 |
Primal | -1.072 |
Stephenson | -1.029 |
Token | I |
Token ID | 40 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
wagen | +1.282 |
alore | +1.136 |
thia | +1.124 |
CLASSIFIED | +1.089 |
ciation | +1.072 |
Neg logit contributions | |
KN | -1.163 |
Kem | -1.138 |
pel | -1.124 |
Primal | -1.113 |
Stephenson | -1.067 |
Token | don |
Token ID | 836 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
KN | +2.159 |
Kem | +2.102 |
pel | +2.080 |
Primal | +2.038 |
Emin | +1.932 |
Neg logit contributions | |
wagen | -3.036 |
alore | -2.719 |
CLASSIFIED | -2.689 |
thia | -2.674 |
ciation | -2.559 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
wagen | +1.535 |
alore | +1.366 |
thia | +1.342 |
CLASSIFIED | +1.293 |
ciation | +1.291 |
Neg logit contributions | |
KN | -1.244 |
Kem | -1.203 |
pel | -1.192 |
Primal | -1.183 |
Emin | -1.130 |
Token | there |
Token ID | 612 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
KN | +0.840 |
Kem | +0.822 |
pel | +0.807 |
Primal | +0.799 |
Stephenson | +0.763 |
Neg logit contributions | |
wagen | -1.122 |
alore | -1.008 |
thia | -0.997 |
CLASSIFIED | -0.969 |
ciation | -0.953 |
Token | were |
Token ID | 547 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
KN | +0.164 |
Kem | +0.159 |
pel | +0.157 |
Primal | +0.154 |
Stephenson | +0.146 |
Neg logit contributions | |
wagen | -0.262 |
alore | -0.237 |
thia | -0.235 |
CLASSIFIED | -0.228 |
ciation | -0.225 |
Token | a |
Token ID | 257 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
wagen | +0.718 |
alore | +0.642 |
thia | +0.634 |
CLASSIFIED | +0.614 |
ciation | +0.606 |
Neg logit contributions | |
KN | -0.557 |
Kem | -0.540 |
pel | -0.536 |
Primal | -0.528 |
hower | -0.506 |
Token | lot |
Token ID | 1256 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
wagen | +0.088 |
alore | +0.078 |
thia | +0.077 |
CLASSIFIED | +0.075 |
ciation | +0.074 |
Neg logit contributions | |
KN | -0.076 |
Kem | -0.074 |
pel | -0.073 |
Primal | -0.072 |
Stephenson | -0.069 |
Token | of |
Token ID | 286 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
wagen | +3.100 |
alore | +2.722 |
thia | +2.694 |
CLASSIFIED | +2.618 |
ciation | +2.568 |
Neg logit contributions | |
KN | -2.779 |
Kem | -2.683 |
pel | -2.675 |
Primal | -2.652 |
hower | -2.560 |
Token | games |
Token ID | 1830 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
wagen | +1.060 |
alore | +0.946 |
thia | +0.933 |
CLASSIFIED | +0.906 |
ciation | +0.890 |
Neg logit contributions | |
KN | -0.856 |
Kem | -0.827 |
pel | -0.824 |
Primal | -0.812 |
hower | -0.779 |
Token | to |
Token ID | 284 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
wagen | +1.447 |
alore | +1.290 |
thia | +1.270 |
CLASSIFIED | +1.228 |
ciation | +1.223 |
Neg logit contributions | |
KN | -1.200 |
Kem | -1.155 |
pel | -1.147 |
Primal | -1.140 |
hower | -1.088 |
Token | play |
Token ID | 711 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
wagen | +1.894 |
alore | +1.691 |
thia | +1.652 |
CLASSIFIED | +1.592 |
ciation | +1.582 |
Neg logit contributions | |
KN | -1.549 |
Kem | -1.505 |
pel | -1.483 |
Primal | -1.472 |
hower | -1.428 |
Token | because |
Token ID | 780 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
wagen | +1.567 |
alore | +1.389 |
thia | +1.368 |
CLASSIFIED | +1.323 |
ciation | +1.314 |
Neg logit contributions | |
KN | -1.354 |
Kem | -1.304 |
pel | -1.294 |
Primal | -1.286 |
hower | -1.233 |
Token | of |
Token ID | 286 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
KN | +0.391 |
Kem | +0.381 |
pel | +0.375 |
Primal | +0.371 |
Stephenson | +0.354 |
Neg logit contributions | |
wagen | -0.517 |
alore | -0.464 |
thia | -0.458 |
CLASSIFIED | -0.445 |
ciation | -0.439 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
wagen | +1.701 |
alore | +1.520 |
thia | +1.498 |
CLASSIFIED | +1.440 |
ciation | +1.431 |
Neg logit contributions | |
KN | -1.363 |
Kem | -1.328 |
pel | -1.299 |
Primal | -1.296 |
Stephenson | -1.238 |
Token | Because |
Token ID | 4362 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
KN | +2.164 |
Kem | +2.156 |
Primal | +2.088 |
pel | +2.053 |
Ike | +2.001 |
Neg logit contributions | |
wagen | -3.007 |
alore | -2.726 |
thia | -2.666 |
CLASSIFIED | -2.606 |
ciation | -2.535 |
Token | he |
Token ID | 339 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
wagen | +0.236 |
alore | +0.211 |
thia | +0.209 |
CLASSIFIED | +0.203 |
ciation | +0.200 |
Neg logit contributions | |
KN | -0.182 |
Kem | -0.177 |
pel | -0.174 |
Primal | -0.173 |
Stephenson | -0.165 |
Token | did |
Token ID | 750 |
Feature activation | +7.82e-02 |
Pos logit contributions | |
KN | +0.643 |
Kem | +0.628 |
pel | +0.620 |
Primal | +0.613 |
Stephenson | +0.583 |
Neg logit contributions | |
wagen | -0.839 |
alore | -0.750 |
thia | -0.741 |
CLASSIFIED | -0.727 |
ciation | -0.710 |
Token | so |
Token ID | 523 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
wagen | +0.068 |
alore | +0.061 |
thia | +0.060 |
CLASSIFIED | +0.058 |
ciation | +0.058 |
Neg logit contributions | |
KN | -0.055 |
Kem | -0.054 |
pel | -0.053 |
Primal | -0.053 |
Stephenson | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
wagen | +0.777 |
alore | +0.693 |
thia | +0.684 |
CLASSIFIED | +0.663 |
ciation | +0.654 |
Neg logit contributions | |
KN | -0.640 |
Kem | -0.622 |
pel | -0.614 |
Primal | -0.606 |
Stephenson | -0.581 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
KN | +1.814 |
Kem | +1.810 |
pel | +1.751 |
Primal | +1.746 |
Ike | +1.677 |
Neg logit contributions | |
wagen | -2.505 |
alore | -2.251 |
thia | -2.239 |
CLASSIFIED | -2.181 |
ciation | -2.140 |
Token | inside |
Token ID | 2641 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
KN | +0.798 |
Kem | +0.787 |
pel | +0.770 |
Primal | +0.766 |
Ike | +0.730 |
Neg logit contributions | |
wagen | -0.988 |
alore | -0.882 |
thia | -0.871 |
CLASSIFIED | -0.852 |
ciation | -0.836 |
Token | of |
Token ID | 286 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
wagen | +5.998 |
alore | +5.461 |
thia | +5.345 |
ciation | +5.096 |
akeru | +4.968 |
Neg logit contributions | |
KN | -5.656 |
Kem | -5.392 |
pel | -5.373 |
Primal | -5.306 |
hower | -5.201 |
Token | the |
Token ID | 262 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
wagen | +0.706 |
alore | +0.631 |
thia | +0.623 |
CLASSIFIED | +0.603 |
ciation | +0.594 |
Neg logit contributions | |
KN | -0.572 |
Kem | -0.555 |
pel | -0.549 |
Primal | -0.542 |
Stephenson | -0.518 |
Token | room |
Token ID | 2119 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
KN | +0.377 |
Kem | +0.370 |
pel | +0.363 |
Primal | +0.360 |
Stephenson | +0.341 |
Neg logit contributions | |
wagen | -0.542 |
alore | -0.488 |
thia | -0.483 |
CLASSIFIED | -0.472 |
ciation | -0.464 |
Token | goal |
Token ID | 3061 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
KN | +1.044 |
Kem | +1.027 |
pel | +1.003 |
Primal | +0.999 |
Stephenson | +0.953 |
Neg logit contributions | |
wagen | -1.421 |
alore | -1.267 |
thia | -1.259 |
CLASSIFIED | -1.226 |
ciation | -1.209 |
Token | of |
Token ID | 286 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
KN | +2.661 |
Kem | +2.615 |
pel | +2.567 |
Primal | +2.545 |
Stephenson | +2.418 |
Neg logit contributions | |
wagen | -3.753 |
alore | -3.383 |
thia | -3.356 |
CLASSIFIED | -3.271 |
ciation | -3.189 |
Token | figuring |
Token ID | 22714 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
KN | +1.870 |
Kem | +1.847 |
Primal | +1.793 |
pel | +1.790 |
Stephenson | +1.696 |
Neg logit contributions | |
wagen | -2.656 |
thia | -2.377 |
alore | -2.374 |
CLASSIFIED | -2.305 |
ciation | -2.276 |
Token | out |
Token ID | 503 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
KN | +1.631 |
Kem | +1.608 |
pel | +1.553 |
Primal | +1.546 |
Stephenson | +1.455 |
Neg logit contributions | |
wagen | -3.135 |
alore | -2.839 |
thia | -2.826 |
CLASSIFIED | -2.759 |
ciation | -2.706 |
Token | why |
Token ID | 1521 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
wagen | +0.027 |
alore | +0.024 |
thia | +0.024 |
CLASSIFIED | +0.023 |
ciation | +0.023 |
Neg logit contributions | |
KN | -0.021 |
Kem | -0.020 |
pel | -0.020 |
Primal | -0.020 |
Stephenson | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
wagen | +1.313 |
alore | +1.174 |
thia | +1.160 |
CLASSIFIED | +1.124 |
ciation | +1.109 |
Neg logit contributions | |
KN | -1.068 |
Kem | -1.033 |
pel | -1.028 |
Primal | -1.010 |
hower | -0.971 |
Token | Muslims |
Token ID | 7045 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
wagen | +0.205 |
alore | +0.183 |
thia | +0.181 |
CLASSIFIED | +0.176 |
ciation | +0.173 |
Neg logit contributions | |
KN | -0.168 |
Kem | -0.164 |
pel | -0.162 |
Primal | -0.160 |
Stephenson | -0.153 |
Token | become |
Token ID | 1716 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
KN | +1.905 |
Kem | +1.869 |
pel | +1.841 |
Primal | +1.821 |
Ike | +1.726 |
Neg logit contributions | |
wagen | -2.560 |
alore | -2.282 |
thia | -2.242 |
CLASSIFIED | -2.230 |
ciation | -2.167 |
Token | terrorists |
Token ID | 10509 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
wagen | +0.020 |
alore | +0.018 |
thia | +0.018 |
CLASSIFIED | +0.017 |
ciation | +0.017 |
Neg logit contributions | |
KN | -0.013 |
Kem | -0.013 |
pel | -0.013 |
Primal | -0.013 |
Stephenson | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
KN | +1.237 |
Kem | +1.211 |
pel | +1.191 |
Primal | +1.178 |
Stephenson | +1.121 |
Neg logit contributions | |
wagen | -1.610 |
alore | -1.444 |
thia | -1.417 |
CLASSIFIED | -1.387 |
ciation | -1.364 |
Token |
|
Token ID | 198 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
KN | +0.968 |
Kem | +0.953 |
Primal | +0.927 |
pel | +0.922 |
Stephenson | +0.887 |
Neg logit contributions | |
wagen | -1.280 |
alore | -1.149 |
thia | -1.123 |
CLASSIFIED | -1.094 |
ciation | -1.075 |
Token | from |
Token ID | 422 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
KN | +1.023 |
Kem | +0.998 |
pel | +0.980 |
Primal | +0.973 |
Stephenson | +0.926 |
Neg logit contributions | |
wagen | -1.338 |
alore | -1.196 |
thia | -1.184 |
CLASSIFIED | -1.157 |
ciation | -1.140 |
Token | a |
Token ID | 257 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
wagen | +0.641 |
alore | +0.573 |
thia | +0.567 |
CLASSIFIED | +0.551 |
ciation | +0.541 |
Neg logit contributions | |
KN | -0.500 |
Kem | -0.485 |
pel | -0.480 |
Primal | -0.474 |
Stephenson | -0.451 |
Token | � |
Token ID | 564 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
KN | +0.253 |
Kem | +0.248 |
pel | +0.243 |
Primal | +0.241 |
Stephenson | +0.229 |
Neg logit contributions | |
wagen | -0.346 |
alore | -0.310 |
thia | -0.307 |
CLASSIFIED | -0.297 |
ciation | -0.295 |
Token | � |
Token ID | 250 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
KN | +1.632 |
pel | +1.570 |
Kem | +1.567 |
Primal | +1.537 |
Emin | +1.456 |
Neg logit contributions | |
wagen | -3.013 |
alore | -2.722 |
thia | -2.699 |
ciation | -2.622 |
CLASSIFIED | -2.621 |
Token | fork |
Token ID | 32523 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
KN | +2.359 |
pel | +2.273 |
Kem | +2.269 |
Primal | +2.193 |
Ike | +2.123 |
Neg logit contributions | |
wagen | -2.507 |
alore | -2.201 |
thia | -2.187 |
ciation | -2.100 |
CLASSIFIED | -2.094 |
Token | ed |
Token ID | 276 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
KN | +1.480 |
Kem | +1.441 |
pel | +1.424 |
Primal | +1.399 |
Stephenson | +1.335 |
Neg logit contributions | |
wagen | -1.988 |
alore | -1.784 |
thia | -1.770 |
CLASSIFIED | -1.720 |
ciation | -1.694 |
Token | tongue |
Token ID | 11880 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
KN | +3.563 |
Kem | +3.529 |
pel | +3.434 |
Primal | +3.374 |
Ike | +3.251 |
Neg logit contributions | |
wagen | -4.760 |
alore | -4.287 |
thia | -4.284 |
CLASSIFIED | -4.133 |
ciation | -4.077 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
KN | +1.903 |
Kem | +1.852 |
pel | +1.825 |
Primal | +1.791 |
Stephenson | +1.689 |
Neg logit contributions | |
wagen | -3.278 |
alore | -2.971 |
thia | -2.942 |
CLASSIFIED | -2.883 |
ciation | -2.823 |
Token | � |
Token ID | 447 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
KN | +1.444 |
Kem | +1.396 |
pel | +1.354 |
Primal | +1.348 |
Stephenson | +1.268 |
Neg logit contributions | |
wagen | -2.803 |
alore | -2.557 |
thia | -2.518 |
CLASSIFIED | -2.449 |
ciation | -2.428 |
Token | � |
Token ID | 251 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
KN | +1.686 |
Kem | +1.625 |
pel | +1.604 |
Primal | +1.586 |
Emin | +1.498 |
Neg logit contributions | |
wagen | -3.499 |
alore | -3.181 |
thia | -3.129 |
CLASSIFIED | -3.056 |
ciation | -3.041 |
Token | � |
Token ID | 447 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
KN | +1.555 |
Kem | +1.512 |
pel | +1.476 |
Primal | +1.465 |
Stephenson | +1.401 |
Neg logit contributions | |
wagen | -2.149 |
alore | -1.940 |
thia | -1.906 |
CLASSIFIED | -1.852 |
ciation | -1.829 |
Token | , |
Token ID | 11 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
wagen | +3.186 |
alore | +2.809 |
thia | +2.766 |
CLASSIFIED | +2.664 |
ciation | +2.615 |
Neg logit contributions | |
KN | -2.859 |
Kem | -2.778 |
pel | -2.741 |
Primal | -2.727 |
hower | -2.632 |
Token | jumps |
Token ID | 18045 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
wagen | +0.055 |
alore | +0.049 |
thia | +0.049 |
CLASSIFIED | +0.047 |
ciation | +0.047 |
Neg logit contributions | |
KN | -0.045 |
Kem | -0.044 |
pel | -0.044 |
Primal | -0.043 |
Stephenson | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
wagen | +1.312 |
alore | +1.159 |
thia | +1.148 |
CLASSIFIED | +1.112 |
ciation | +1.091 |
Neg logit contributions | |
KN | -1.095 |
Kem | -1.064 |
pel | -1.050 |
Primal | -1.038 |
Emin | -0.997 |
Token | land |
Token ID | 1956 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
KN | +2.248 |
Kem | +2.203 |
pel | +2.166 |
Primal | +2.144 |
Stephenson | +2.039 |
Neg logit contributions | |
wagen | -2.793 |
alore | -2.482 |
thia | -2.461 |
CLASSIFIED | -2.417 |
ciation | -2.377 |
Token | ings |
Token ID | 654 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
KN | +1.926 |
Kem | +1.877 |
pel | +1.869 |
Primal | +1.835 |
Emin | +1.754 |
Neg logit contributions | |
wagen | -1.936 |
alore | -1.707 |
thia | -1.687 |
CLASSIFIED | -1.636 |
ciation | -1.612 |
Token | all |
Token ID | 477 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
KN | +2.434 |
Kem | +2.395 |
pel | +2.362 |
Primal | +2.332 |
Ike | +2.205 |
Neg logit contributions | |
wagen | -3.349 |
alore | -3.032 |
thia | -2.990 |
CLASSIFIED | -2.926 |
ciation | -2.881 |
Token | require |
Token ID | 2421 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
KN | +3.387 |
Kem | +3.309 |
pel | +3.267 |
Primal | +3.229 |
hower | +3.054 |
Neg logit contributions | |
wagen | -4.612 |
alore | -4.076 |
CLASSIFIED | -4.057 |
thia | -4.045 |
ciation | -3.905 |
Token | precise |
Token ID | 7141 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
wagen | +0.528 |
alore | +0.473 |
thia | +0.467 |
CLASSIFIED | +0.453 |
ciation | +0.448 |
Neg logit contributions | |
KN | -0.400 |
Kem | -0.388 |
pel | -0.384 |
Primal | -0.378 |
Stephenson | -0.361 |
Token | muscle |
Token ID | 8280 |
Feature activation | +5.87e+00 |
Pos logit contributions | |
wagen | +1.884 |
alore | +1.693 |
thia | +1.665 |
CLASSIFIED | +1.611 |
ciation | +1.602 |
Neg logit contributions | |
KN | -1.414 |
Kem | -1.363 |
pel | -1.355 |
Primal | -1.330 |
hower | -1.285 |
Token | control |
Token ID | 1630 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
wagen | +5.227 |
alore | +4.732 |
thia | +4.661 |
ciation | +4.487 |
CLASSIFIED | +4.460 |
Neg logit contributions | |
KN | -3.846 |
Kem | -3.710 |
pel | -3.673 |
Primal | -3.665 |
hower | -3.591 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
KN | +0.639 |
Kem | +0.622 |
pel | +0.614 |
Primal | +0.606 |
Stephenson | +0.577 |
Neg logit contributions | |
wagen | -0.847 |
alore | -0.759 |
thia | -0.750 |
CLASSIFIED | -0.729 |
ciation | -0.718 |
Token | he |
Token ID | 339 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
KN | +0.689 |
Kem | +0.668 |
pel | +0.662 |
Primal | +0.651 |
Stephenson | +0.622 |
Neg logit contributions | |
wagen | -0.899 |
alore | -0.804 |
thia | -0.795 |
CLASSIFIED | -0.771 |
ciation | -0.762 |
Token | feels |
Token ID | 5300 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
wagen | +0.367 |
alore | +0.328 |
thia | +0.324 |
CLASSIFIED | +0.314 |
ciation | +0.310 |
Neg logit contributions | |
KN | -0.295 |
Kem | -0.287 |
pel | -0.283 |
Primal | -0.280 |
Stephenson | -0.267 |
Token | that |
Token ID | 326 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
wagen | +3.713 |
alore | +3.293 |
thia | +3.254 |
ciation | +3.134 |
CLASSIFIED | +3.132 |
Neg logit contributions | |
KN | -2.994 |
pel | -2.902 |
Kem | -2.795 |
hower | -2.775 |
Primal | -2.760 |
Token | Smash |
Token ID | 18214 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
KN | +1.022 |
Kem | +0.997 |
pel | +0.978 |
Primal | +0.969 |
Stephenson | +0.921 |
Neg logit contributions | |
wagen | -1.510 |
alore | -1.361 |
thia | -1.346 |
CLASSIFIED | -1.310 |
ciation | -1.290 |
Token | and |
Token ID | 290 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
KN | +2.448 |
Kem | +2.401 |
Primal | +2.348 |
pel | +2.344 |
Stephenson | +2.224 |
Neg logit contributions | |
wagen | -3.226 |
alore | -2.901 |
thia | -2.874 |
CLASSIFIED | -2.799 |
ciation | -2.740 |
Token | the |
Token ID | 262 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
Kem | +4.062 |
KN | +4.039 |
Primal | +3.961 |
pel | +3.857 |
Ike | +3.733 |
Neg logit contributions | |
wagen | -6.097 |
alore | -5.538 |
thia | -5.421 |
CLASSIFIED | -5.287 |
ciation | -5.179 |
Token | F |
Token ID | 376 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
KN | +3.044 |
Kem | +3.039 |
Primal | +2.943 |
pel | +2.903 |
Ike | +2.775 |
Neg logit contributions | |
wagen | -5.001 |
alore | -4.557 |
thia | -4.491 |
CLASSIFIED | -4.399 |
ciation | -4.288 |
Token | GC |
Token ID | 15916 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
KN | +4.872 |
Kem | +4.663 |
pel | +4.600 |
Primal | +4.366 |
Ike | +4.334 |
Neg logit contributions | |
wagen | -6.266 |
alore | -5.624 |
thia | -5.494 |
CLASSIFIED | -5.434 |
ciation | -5.219 |
Token | are |
Token ID | 389 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
KN | +1.797 |
Kem | +1.751 |
pel | +1.718 |
Primal | +1.702 |
Stephenson | +1.618 |
Neg logit contributions | |
wagen | -2.515 |
alore | -2.267 |
thia | -2.244 |
CLASSIFIED | -2.184 |
ciation | -2.138 |
Token | already |
Token ID | 1541 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
wagen | +1.227 |
alore | +1.106 |
thia | +1.088 |
CLASSIFIED | +1.055 |
ciation | +1.044 |
Neg logit contributions | |
KN | -0.915 |
Kem | -0.886 |
pel | -0.878 |
Primal | -0.862 |
hower | -0.826 |
Token | united |
Token ID | 16503 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
wagen | +1.420 |
alore | +1.278 |
thia | +1.259 |
CLASSIFIED | +1.220 |
ciation | +1.208 |
Neg logit contributions | |
KN | -1.041 |
Kem | -1.008 |
pel | -1.002 |
Primal | -0.980 |
hower | -0.943 |
Token | : |
Token ID | 1058 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
wagen | +0.978 |
alore | +0.857 |
thia | +0.851 |
CLASSIFIED | +0.815 |
ciation | +0.809 |
Neg logit contributions | |
KN | -1.023 |
Kem | -0.995 |
pel | -0.989 |
Primal | -0.983 |
Ike | -0.938 |
Token | This |
Token ID | 770 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
KN | +0.696 |
Kem | +0.684 |
Primal | +0.668 |
pel | +0.667 |
Stephenson | +0.639 |
Neg logit contributions | |
wagen | -0.865 |
alore | -0.773 |
thia | -0.760 |
CLASSIFIED | -0.739 |
ciation | -0.725 |
Token | is |
Token ID | 318 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
wagen | +1.211 |
alore | +1.081 |
thia | +1.070 |
CLASSIFIED | +1.038 |
ciation | +1.022 |
Neg logit contributions | |
KN | -0.979 |
Kem | -0.949 |
pel | -0.941 |
Primal | -0.926 |
hower | -0.886 |
Token | just |
Token ID | 655 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
wagen | +1.809 |
alore | +1.622 |
thia | +1.602 |
CLASSIFIED | +1.556 |
ciation | +1.537 |
Neg logit contributions | |
KN | -1.454 |
Kem | -1.401 |
pel | -1.397 |
Primal | -1.364 |
hower | -1.320 |
Token | to |
Token ID | 284 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
wagen | +2.190 |
alore | +1.966 |
thia | +1.945 |
CLASSIFIED | +1.877 |
ciation | +1.864 |
Neg logit contributions | |
KN | -1.760 |
Kem | -1.695 |
pel | -1.695 |
Primal | -1.650 |
hower | -1.601 |
Token | Fred |
Token ID | 8559 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
KN | +0.291 |
Kem | +0.283 |
pel | +0.279 |
Primal | +0.276 |
Stephenson | +0.264 |
Neg logit contributions | |
wagen | -0.364 |
alore | -0.325 |
thia | -0.321 |
CLASSIFIED | -0.312 |
ciation | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
KN | +3.956 |
Kem | +3.952 |
pel | +3.806 |
Primal | +3.782 |
Stephenson | +3.725 |
Neg logit contributions | |
wagen | -5.227 |
alore | -4.676 |
CLASSIFIED | -4.550 |
thia | -4.523 |
akeru | -4.390 |
Token | Fred |
Token ID | 8559 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
KN | +2.594 |
Kem | +2.585 |
Primal | +2.518 |
pel | +2.454 |
Stephenson | +2.424 |
Neg logit contributions | |
wagen | -3.532 |
alore | -3.181 |
thia | -3.097 |
CLASSIFIED | -3.037 |
akeru | -2.967 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
KN | +2.519 |
Kem | +2.481 |
pel | +2.406 |
Primal | +2.405 |
Stephenson | +2.328 |
Neg logit contributions | |
wagen | -3.333 |
alore | -2.982 |
thia | -2.927 |
CLASSIFIED | -2.871 |
ciation | -2.808 |
Token | I |
Token ID | 314 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
KN | +0.352 |
Kem | +0.345 |
pel | +0.340 |
Primal | +0.336 |
Stephenson | +0.323 |
Neg logit contributions | |
wagen | -0.380 |
alore | -0.337 |
thia | -0.332 |
CLASSIFIED | -0.322 |
ciation | -0.317 |
Token | probably |
Token ID | 2192 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
KN | +1.810 |
Kem | +1.762 |
pel | +1.734 |
Primal | +1.717 |
Stephenson | +1.631 |
Neg logit contributions | |
wagen | -2.708 |
alore | -2.427 |
thia | -2.403 |
CLASSIFIED | -2.366 |
ciation | -2.310 |
Token | ology |
Token ID | 1435 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
KN | +1.157 |
Kem | +1.123 |
pel | +1.110 |
Primal | +1.093 |
Stephenson | +1.039 |
Neg logit contributions | |
wagen | -1.625 |
alore | -1.460 |
thia | -1.438 |
CLASSIFIED | -1.408 |
ciation | -1.386 |
Token | � |
Token ID | 447 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
KN | +1.467 |
Kem | +1.425 |
pel | +1.400 |
Primal | +1.382 |
Stephenson | +1.306 |
Neg logit contributions | |
wagen | -2.401 |
alore | -2.168 |
thia | -2.143 |
CLASSIFIED | -2.096 |
ciation | -2.067 |
Token | � |
Token ID | 251 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
wagen | +1.096 |
alore | +1.010 |
thia | +1.001 |
CLASSIFIED | +0.979 |
ciation | +0.966 |
Neg logit contributions | |
KN | -0.408 |
Kem | -0.390 |
pel | -0.381 |
Primal | -0.371 |
Stephenson | -0.346 |
Token | is |
Token ID | 318 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
wagen | +1.080 |
alore | +0.969 |
thia | +0.960 |
CLASSIFIED | +0.924 |
ciation | +0.915 |
Neg logit contributions | |
KN | -0.850 |
Kem | -0.825 |
pel | -0.815 |
Primal | -0.805 |
Stephenson | -0.769 |
Token | often |
Token ID | 1690 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
KN | +0.935 |
Kem | +0.913 |
pel | +0.899 |
Primal | +0.891 |
Stephenson | +0.847 |
Neg logit contributions | |
wagen | -1.305 |
alore | -1.172 |
thia | -1.162 |
CLASSIFIED | -1.129 |
ciation | -1.115 |
Token | mistakenly |
Token ID | 33168 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
KN | +0.677 |
Kem | +0.660 |
pel | +0.648 |
Primal | +0.642 |
Stephenson | +0.610 |
Neg logit contributions | |
wagen | -0.999 |
alore | -0.900 |
thia | -0.892 |
CLASSIFIED | -0.868 |
ciation | -0.858 |
Token | treated |
Token ID | 5716 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
KN | +3.033 |
Kem | +3.005 |
Primal | +2.915 |
pel | +2.870 |
Stephenson | +2.743 |
Neg logit contributions | |
wagen | -4.694 |
alore | -4.230 |
thia | -4.169 |
CLASSIFIED | -4.155 |
ciation | -4.084 |
Token | as |
Token ID | 355 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
KN | +2.178 |
Kem | +2.126 |
pel | +2.095 |
Primal | +2.061 |
Stephenson | +1.954 |
Neg logit contributions | |
wagen | -3.294 |
alore | -2.965 |
thia | -2.939 |
CLASSIFIED | -2.873 |
ciation | -2.841 |
Token | a |
Token ID | 257 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
KN | +1.763 |
Kem | +1.736 |
pel | +1.696 |
Primal | +1.694 |
Stephenson | +1.615 |
Neg logit contributions | |
wagen | -2.419 |
alore | -2.169 |
thia | -2.157 |
CLASSIFIED | -2.082 |
ciation | -2.068 |
Token | universal |
Token ID | 10112 |
Feature activation | -6.06e+00 |
Pos logit contributions | |
KN | +1.564 |
Kem | +1.537 |
pel | +1.507 |
Primal | +1.502 |
Stephenson | +1.426 |
Neg logit contributions | |
wagen | -2.238 |
alore | -2.020 |
thia | -1.997 |
CLASSIFIED | -1.945 |
ciation | -1.929 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
KN | +3.885 |
Kem | +3.865 |
pel | +3.768 |
Primal | +3.765 |
Stephenson | +3.597 |
Neg logit contributions | |
wagen | -5.505 |
alore | -4.966 |
thia | -4.945 |
CLASSIFIED | -4.864 |
ciation | -4.753 |