Token | who |
Token ID | 508 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ippi | +0.433 |
Beir | +0.433 |
nton | +0.428 |
Gad | +0.405 |
Sas | +0.403 |
Neg logit contributions | |
ILCS | -0.492 |
機 | -0.396 |
(_ | -0.381 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.379 |
belts | -0.374 |
Token | has |
Token ID | 468 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
ILCS | +0.165 |
機 | +0.135 |
(_ | +0.131 |
belts | +0.131 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.130 |
Neg logit contributions | |
ippi | -0.126 |
Beir | -0.126 |
nton | -0.124 |
Gad | -0.116 |
spons | -0.115 |
Token | just |
Token ID | 655 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILCS | +0.652 |
機 | +0.529 |
(_ | +0.512 |
belts | +0.511 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.510 |
Neg logit contributions | |
ippi | -0.540 |
Beir | -0.536 |
nton | -0.533 |
Gad | -0.497 |
spons | -0.494 |
Token | felt |
Token ID | 2936 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
ILCS | +1.034 |
機 | +0.843 |
belts | +0.820 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.818 |
(_ | +0.818 |
Neg logit contributions | |
ippi | -0.792 |
Beir | -0.785 |
nton | -0.780 |
Gad | -0.725 |
spons | -0.724 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ILCS | +2.838 |
機 | +2.257 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.204 |
(_ | +2.197 |
belts | +2.185 |
Neg logit contributions | |
ippi | -2.813 |
nton | -2.780 |
Beir | -2.777 |
lished | -2.587 |
spons | -2.562 |
Token | sun |
Token ID | 4252 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
ILCS | +0.788 |
機 | +0.628 |
(_ | +0.607 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.603 |
belts | +0.602 |
Neg logit contributions | |
ippi | -0.756 |
Beir | -0.752 |
nton | -0.748 |
Gad | -0.702 |
spons | -0.700 |
Token | 's |
Token ID | 338 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
ILCS | +5.007 |
belts | +3.926 |
(_ | +3.874 |
機 | +3.863 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.821 |
Neg logit contributions | |
ippi | -5.194 |
Beir | -5.070 |
nton | -4.856 |
lished | -4.796 |
Gad | -4.741 |
Token | warmth |
Token ID | 23125 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ippi | +0.171 |
Beir | +0.171 |
nton | +0.169 |
Gad | +0.160 |
Sas | +0.160 |
Neg logit contributions | |
ILCS | -0.177 |
機 | -0.141 |
(_ | -0.136 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.135 |
belts | -0.133 |
Token | on |
Token ID | 319 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ILCS | +1.559 |
機 | +1.240 |
(_ | +1.211 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.201 |
belts | +1.198 |
Neg logit contributions | |
ippi | -1.416 |
Beir | -1.406 |
nton | -1.386 |
Gad | -1.314 |
Sas | -1.301 |
Token | his |
Token ID | 465 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
ippi | +0.375 |
Beir | +0.374 |
nton | +0.371 |
Gad | +0.348 |
spons | +0.347 |
Neg logit contributions | |
ILCS | -0.414 |
機 | -0.330 |
(_ | -0.322 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.319 |
belts | -0.317 |
Token | back |
Token ID | 736 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
ILCS | +0.320 |
機 | +0.262 |
(_ | +0.256 |
belts | +0.253 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.252 |
Neg logit contributions | |
ippi | -0.227 |
Beir | -0.225 |
nton | -0.224 |
Gad | -0.208 |
Sas | -0.206 |
Token | take |
Token ID | 1011 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Beir | +1.852 |
ippi | +1.847 |
nton | +1.832 |
Gad | +1.742 |
Sas | +1.739 |
Neg logit contributions | |
ILCS | -1.860 |
機 | -1.474 |
(_ | -1.411 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.405 |
belts | -1.376 |
Token | on |
Token ID | 319 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
ippi | +0.995 |
Beir | +0.987 |
nton | +0.986 |
Sas | +0.930 |
Gad | +0.928 |
Neg logit contributions | |
ILCS | -1.201 |
機 | -0.972 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.926 |
(_ | -0.924 |
belts | -0.907 |
Token | it |
Token ID | 340 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
ippi | +0.591 |
Beir | +0.589 |
nton | +0.584 |
Gad | +0.552 |
Sas | +0.550 |
Neg logit contributions | |
ILCS | -0.619 |
機 | -0.493 |
(_ | -0.474 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.471 |
belts | -0.465 |
Token | : |
Token ID | 25 |
Feature activation | +7.79e-02 |
Pos logit contributions | |
ippi | +0.413 |
Beir | +0.413 |
nton | +0.409 |
Gad | +0.387 |
Sas | +0.386 |
Neg logit contributions | |
ILCS | -0.471 |
機 | -0.380 |
(_ | -0.364 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.363 |
belts | -0.357 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ILCS | +0.063 |
機 | +0.051 |
(_ | +0.050 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.049 |
belts | +0.049 |
Neg logit contributions | |
ippi | -0.049 |
Beir | -0.049 |
nton | -0.048 |
Gad | -0.045 |
Sas | -0.045 |
Token | sun |
Token ID | 4252 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
ILCS | +0.976 |
機 | +0.780 |
(_ | +0.750 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.744 |
belts | +0.737 |
Neg logit contributions | |
ippi | -0.912 |
Beir | -0.908 |
nton | -0.902 |
Gad | -0.847 |
Sas | -0.844 |
Token | will |
Token ID | 481 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
ILCS | +5.397 |
belts | +4.407 |
機 | +4.330 |
(_ | +4.291 |
ñ | +4.211 |
Neg logit contributions | |
ippi | -4.579 |
Beir | -4.488 |
nton | -4.275 |
lished | -4.135 |
Gad | -4.118 |
Token | rise |
Token ID | 4485 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ippi | +0.286 |
Beir | +0.286 |
nton | +0.283 |
Gad | +0.269 |
Sas | +0.268 |
Neg logit contributions | |
ILCS | -0.277 |
機 | -0.219 |
(_ | -0.210 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.208 |
belts | -0.205 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ILCS | +0.599 |
機 | +0.473 |
(_ | +0.462 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.456 |
belts | +0.452 |
Neg logit contributions | |
ippi | -0.552 |
Beir | -0.549 |
nton | -0.544 |
Gad | -0.511 |
Sas | -0.510 |
Token | , |
Token ID | 11 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
ippi | +0.212 |
Beir | +0.212 |
nton | +0.210 |
Gad | +0.198 |
Sas | +0.197 |
Neg logit contributions | |
ILCS | -0.262 |
機 | -0.213 |
(_ | -0.206 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.204 |
belts | -0.202 |
Token | I |
Token ID | 314 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
ippi | +0.388 |
Beir | +0.387 |
nton | +0.384 |
Gad | +0.359 |
Sas | +0.358 |
Neg logit contributions | |
ILCS | -0.506 |
機 | -0.412 |
(_ | -0.398 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.397 |
belts | -0.392 |
Token | ] |
Token ID | 60 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
ILCS | +0.411 |
機 | +0.339 |
(_ | +0.332 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.329 |
belts | +0.325 |
Neg logit contributions | |
ippi | -0.263 |
Beir | -0.263 |
nton | -0.261 |
Gad | -0.244 |
Sas | -0.242 |
Token | stay |
Token ID | 2652 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ippi | +1.492 |
Beir | +1.490 |
nton | +1.476 |
Gad | +1.394 |
Sas | +1.391 |
Neg logit contributions | |
ILCS | -1.728 |
機 | -1.396 |
(_ | -1.339 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.334 |
belts | -1.312 |
Token | out |
Token ID | 503 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ILCS | +0.728 |
機 | +0.582 |
(_ | +0.572 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.563 |
belts | +0.559 |
Neg logit contributions | |
ippi | -0.652 |
nton | -0.644 |
Beir | -0.643 |
Wonders | -0.608 |
Gad | -0.599 |
Token | of |
Token ID | 286 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
ippi | +0.198 |
Beir | +0.198 |
nton | +0.196 |
Gad | +0.185 |
Sas | +0.185 |
Neg logit contributions | |
ILCS | -0.220 |
機 | -0.177 |
(_ | -0.170 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.169 |
belts | -0.166 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ippi | +0.636 |
Beir | +0.636 |
nton | +0.634 |
Gad | +0.593 |
Sas | +0.590 |
Neg logit contributions | |
ILCS | -0.759 |
機 | -0.615 |
(_ | -0.593 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.589 |
belts | -0.587 |
Token | sun |
Token ID | 4252 |
Feature activation | +7.00e+00 |
Pos logit contributions | |
ippi | +0.075 |
Beir | +0.075 |
nton | +0.075 |
Sas | +0.070 |
Gad | +0.070 |
Neg logit contributions | |
ILCS | -0.079 |
機 | -0.064 |
(_ | -0.061 |
belts | -0.060 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
ILCS | +5.008 |
機 | +3.901 |
(_ | +3.872 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.841 |
belts | +3.839 |
Neg logit contributions | |
ippi | -4.890 |
Beir | -4.820 |
nton | -4.760 |
Gad | -4.615 |
lished | -4.521 |
Token | � |
Token ID | 447 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ippi | +0.113 |
nton | +0.111 |
Beir | +0.111 |
spons | +0.107 |
lished | +0.104 |
Neg logit contributions | |
ILCS | -0.144 |
機 | -0.117 |
(_ | -0.114 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.114 |
Send | -0.111 |
Token | � |
Token ID | 251 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ippi | +1.099 |
Beir | +1.096 |
nton | +1.088 |
Gad | +1.035 |
Sas | +1.032 |
Neg logit contributions | |
ILCS | -0.978 |
機 | -0.761 |
(_ | -0.722 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.721 |
belts | -0.712 |
Token |
|
Token ID | 198 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
ippi | +0.685 |
Beir | +0.681 |
nton | +0.675 |
spons | +0.635 |
Gad | +0.629 |
Neg logit contributions | |
ILCS | -0.942 |
機 | -0.773 |
(_ | -0.750 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.745 |
belts | -0.729 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Beir | +0.244 |
ippi | +0.243 |
nton | +0.236 |
spons | +0.228 |
lished | +0.223 |
Neg logit contributions | |
ILCS | -0.361 |
機 | -0.298 |
(_ | -0.294 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.289 |
Send | -0.285 |
Token | the |
Token ID | 262 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ILCS | +0.470 |
機 | +0.377 |
(_ | +0.366 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.364 |
belts | +0.361 |
Neg logit contributions | |
ippi | -0.419 |
Beir | -0.417 |
nton | -0.413 |
Gad | -0.389 |
Sas | -0.385 |
Token | low |
Token ID | 1877 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ILCS | +0.193 |
機 | +0.155 |
(_ | +0.149 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.149 |
belts | +0.147 |
Neg logit contributions | |
ippi | -0.174 |
Beir | -0.174 |
nton | -0.173 |
Gad | -0.163 |
Sas | -0.162 |
Token | - |
Token ID | 12 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
ILCS | +0.312 |
機 | +0.251 |
(_ | +0.242 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.241 |
belts | +0.238 |
Neg logit contributions | |
ippi | -0.276 |
Beir | -0.275 |
nton | -0.272 |
Gad | -0.258 |
Sas | -0.257 |
Token | sl |
Token ID | 6649 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
Beir | +0.517 |
ippi | +0.516 |
nton | +0.509 |
Gad | +0.481 |
Sas | +0.480 |
Neg logit contributions | |
ILCS | -0.634 |
機 | -0.516 |
(_ | -0.497 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.493 |
belts | -0.486 |
Token | ung |
Token ID | 2150 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Beir | +0.371 |
ippi | +0.362 |
nton | +0.359 |
Sas | +0.348 |
Gad | +0.347 |
Neg logit contributions | |
ILCS | -0.325 |
機 | -0.257 |
(_ | -0.246 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.242 |
umann | -0.237 |
Token | sun |
Token ID | 4252 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
ILCS | +1.626 |
機 | +1.320 |
(_ | +1.272 |
belts | +1.268 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.263 |
Neg logit contributions | |
ippi | -1.403 |
Beir | -1.391 |
nton | -1.387 |
Gad | -1.300 |
lished | -1.295 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ILCS | +5.220 |
belts | +4.323 |
機 | +4.219 |
(_ | +4.201 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +4.161 |
Neg logit contributions | |
ippi | -4.513 |
Beir | -4.462 |
nton | -4.267 |
lished | -4.185 |
Gad | -4.180 |
Token | still |
Token ID | 991 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
ILCS | +0.810 |
機 | +0.652 |
(_ | +0.628 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.627 |
belts | +0.622 |
Neg logit contributions | |
ippi | -0.697 |
Beir | -0.692 |
nton | -0.688 |
Gad | -0.648 |
Sas | -0.642 |
Token | creeping |
Token ID | 38598 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
ILCS | +0.572 |
機 | +0.461 |
(_ | +0.446 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.445 |
belts | +0.440 |
Neg logit contributions | |
ippi | -0.492 |
Beir | -0.489 |
nton | -0.483 |
Gad | -0.457 |
Sas | -0.453 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ILCS | +0.033 |
機 | +0.026 |
(_ | +0.026 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.025 |
belts | +0.025 |
Neg logit contributions | |
ippi | -0.033 |
Beir | -0.033 |
nton | -0.033 |
Gad | -0.031 |
Sas | -0.031 |
Token | ward |
Token ID | 904 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
ILCS | +1.349 |
機 | +1.087 |
(_ | +1.043 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.042 |
belts | +1.030 |
Neg logit contributions | |
ippi | -1.290 |
Beir | -1.287 |
nton | -1.262 |
Gad | -1.212 |
Sas | -1.199 |
Token | , |
Token ID | 11 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ILCS | +0.495 |
機 | +0.399 |
(_ | +0.385 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.381 |
belts | +0.378 |
Neg logit contributions | |
Beir | -0.442 |
ippi | -0.442 |
nton | -0.435 |
Gad | -0.412 |
Sas | -0.410 |
Token | which |
Token ID | 543 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ILCS | +0.409 |
機 | +0.332 |
(_ | +0.321 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.319 |
belts | +0.315 |
Neg logit contributions | |
ippi | -0.336 |
Beir | -0.335 |
nton | -0.332 |
Gad | -0.312 |
Sas | -0.310 |
Token | is |
Token ID | 318 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
ILCS | +0.253 |
機 | +0.206 |
(_ | +0.198 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.197 |
belts | +0.195 |
Neg logit contributions | |
ippi | -0.207 |
Beir | -0.207 |
nton | -0.205 |
Gad | -0.192 |
Sas | -0.192 |
Token | used |
Token ID | 973 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
ILCS | +0.572 |
機 | +0.460 |
(_ | +0.445 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.443 |
belts | +0.439 |
Neg logit contributions | |
ippi | -0.503 |
Beir | -0.495 |
nton | -0.494 |
Gad | -0.462 |
Sas | -0.462 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
ILCS | +1.827 |
機 | +1.471 |
(_ | +1.421 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.406 |
belts | +1.402 |
Neg logit contributions | |
Beir | -1.668 |
ippi | -1.663 |
nton | -1.646 |
Sas | -1.548 |
Gad | -1.543 |
Token | treat |
Token ID | 2190 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
ILCS | +1.087 |
機 | +0.830 |
(_ | +0.797 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.789 |
belts | +0.782 |
Neg logit contributions | |
ippi | -1.333 |
Beir | -1.332 |
nton | -1.309 |
Gad | -1.240 |
Sas | -1.239 |
Token | th |
Token ID | 294 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
ILCS | +4.502 |
belts | +3.555 |
(_ | +3.469 |
機 | +3.441 |
Leone | +3.342 |
Neg logit contributions | |
ippi | -4.643 |
nton | -4.537 |
Beir | -4.502 |
lished | -4.399 |
Wonders | -4.167 |
Token | al |
Token ID | 282 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
ILCS | +0.652 |
機 | +0.536 |
(_ | +0.528 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.518 |
umann | +0.512 |
Neg logit contributions | |
Beir | -0.459 |
ippi | -0.449 |
nton | -0.447 |
Sas | -0.420 |
Gad | -0.417 |
Token | asse |
Token ID | 21612 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Beir | +0.271 |
ippi | +0.268 |
nton | +0.264 |
Gad | +0.238 |
Sas | +0.238 |
Neg logit contributions | |
ILCS | -0.647 |
機 | -0.549 |
(_ | -0.537 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.535 |
belts | -0.532 |
Token | mia |
Token ID | 20730 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ippi | +0.804 |
Beir | +0.803 |
nton | +0.798 |
Sas | +0.768 |
Gad | +0.763 |
Neg logit contributions | |
ILCS | -0.665 |
機 | -0.509 |
(_ | -0.476 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.472 |
ÃÂ | -0.464 |
Token | . |
Token ID | 13 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
ILCS | +0.697 |
機 | +0.562 |
(_ | +0.543 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.537 |
belts | +0.534 |
Neg logit contributions | |
ippi | -0.610 |
Beir | -0.610 |
nton | -0.604 |
Gad | -0.567 |
Sas | -0.565 |
Token | sometimes |
Token ID | 3360 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
ILCS | +0.005 |
機 | +0.004 |
(_ | +0.004 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.004 |
belts | +0.004 |
Neg logit contributions | |
ippi | -0.005 |
Beir | -0.005 |
nton | -0.005 |
Gad | -0.005 |
spons | -0.005 |
Token | also |
Token ID | 635 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
ILCS | +1.607 |
機 | +1.273 |
(_ | +1.245 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.230 |
belts | +1.225 |
Neg logit contributions | |
ippi | -1.547 |
nton | -1.511 |
Beir | -1.511 |
lished | -1.423 |
spons | -1.422 |
Token | used |
Token ID | 973 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
ILCS | +0.753 |
機 | +0.602 |
(_ | +0.589 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.584 |
belts | +0.579 |
Neg logit contributions | |
ippi | -0.665 |
nton | -0.655 |
Beir | -0.652 |
Gad | -0.610 |
Wonders | -0.609 |
Token | as |
Token ID | 355 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ILCS | +2.239 |
機 | +1.752 |
(_ | +1.721 |
belts | +1.689 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.689 |
Neg logit contributions | |
ippi | -2.308 |
Beir | -2.301 |
nton | -2.278 |
Gad | -2.157 |
Sas | -2.149 |
Token | an |
Token ID | 281 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ILCS | +0.944 |
機 | +0.765 |
(_ | +0.741 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.739 |
belts | +0.730 |
Neg logit contributions | |
ippi | -0.759 |
Beir | -0.753 |
nton | -0.750 |
Gad | -0.702 |
Sas | -0.698 |
Token | umbrella |
Token ID | 25510 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
ILCS | +1.614 |
機 | +1.258 |
(_ | +1.220 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.211 |
belts | +1.189 |
Neg logit contributions | |
ippi | -1.549 |
nton | -1.538 |
Beir | -1.538 |
Gad | -1.446 |
Wonders | -1.434 |
Token | term |
Token ID | 3381 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ILCS | +4.001 |
(_ | +3.006 |
機 | +2.979 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.884 |
belts | +2.875 |
Neg logit contributions | |
ippi | -5.211 |
nton | -5.133 |
Beir | -5.026 |
lished | -4.822 |
Gad | -4.817 |
Token | that |
Token ID | 326 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ILCS | +2.634 |
機 | +2.016 |
(_ | +1.975 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.924 |
belts | +1.907 |
Neg logit contributions | |
ippi | -3.150 |
nton | -3.135 |
Beir | -3.135 |
Gad | -2.968 |
Wonders | -2.956 |
Token | encompasses |
Token ID | 38932 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ILCS | +1.609 |
機 | +1.295 |
(_ | +1.248 |
belts | +1.246 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.237 |
Neg logit contributions | |
ippi | -1.457 |
Beir | -1.436 |
nton | -1.426 |
lished | -1.338 |
spons | -1.337 |
Token | those |
Token ID | 883 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +0.401 |
機 | +0.319 |
(_ | +0.310 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.307 |
belts | +0.306 |
Neg logit contributions | |
ippi | -0.372 |
Beir | -0.369 |
nton | -0.367 |
Gad | -0.344 |
spons | -0.344 |
Token | who |
Token ID | 508 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
ILCS | +0.872 |
機 | +0.671 |
(_ | +0.654 |
belts | +0.645 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.643 |
Neg logit contributions | |
ippi | -0.995 |
Beir | -0.982 |
nton | -0.980 |
spons | -0.924 |
Gad | -0.923 |
Token |
|
Token ID | 198 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ippi | +0.416 |
Beir | +0.415 |
nton | +0.410 |
Gad | +0.383 |
Sas | +0.380 |
Neg logit contributions | |
ILCS | -0.675 |
機 | -0.563 |
(_ | -0.545 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.543 |
belts | -0.535 |
Token | Faith |
Token ID | 45536 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Beir | +0.262 |
ippi | +0.260 |
nton | +0.257 |
Gad | +0.244 |
Sas | +0.243 |
Neg logit contributions | |
ILCS | -0.292 |
機 | -0.235 |
(_ | -0.228 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.226 |
Send | -0.222 |
Token | 's |
Token ID | 338 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Beir | +1.451 |
ippi | +1.451 |
nton | +1.434 |
Gad | +1.345 |
Sas | +1.340 |
Neg logit contributions | |
ILCS | -2.134 |
機 | -1.764 |
(_ | -1.703 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.697 |
belts | -1.671 |
Token | two |
Token ID | 734 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ippi | +0.914 |
Beir | +0.912 |
nton | +0.903 |
Gad | +0.852 |
Sas | +0.849 |
Neg logit contributions | |
ILCS | -1.050 |
機 | -0.845 |
(_ | -0.814 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.810 |
belts | -0.799 |
Token | male |
Token ID | 4257 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
ippi | +0.855 |
Beir | +0.853 |
nton | +0.846 |
Gad | +0.801 |
Sas | +0.799 |
Neg logit contributions | |
ILCS | -0.864 |
機 | -0.685 |
(_ | -0.657 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.653 |
belts | -0.644 |
Token | cub |
Token ID | 13617 |
Feature activation | +6.41e+00 |
Pos logit contributions | |
ILCS | +0.609 |
機 | +0.474 |
belts | +0.461 |
(_ | +0.459 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.456 |
Neg logit contributions | |
ippi | -0.655 |
Beir | -0.646 |
nton | -0.640 |
lished | -0.604 |
Gad | -0.603 |
Token | s |
Token ID | 82 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
ILCS | +4.437 |
機 | +3.558 |
(_ | +3.463 |
belts | +3.461 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.413 |
Neg logit contributions | |
ippi | -4.499 |
Beir | -4.480 |
nton | -4.433 |
lished | -4.173 |
course | -4.169 |
Token | - |
Token ID | 532 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
ILCS | +0.402 |
機 | +0.328 |
(_ | +0.320 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.317 |
belts | +0.315 |
Neg logit contributions | |
ippi | -0.292 |
Beir | -0.291 |
nton | -0.289 |
Gad | -0.270 |
spons | -0.267 |
Token | 8 |
Token ID | 807 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
ILCS | +0.064 |
機 | +0.053 |
(_ | +0.051 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.051 |
belts | +0.051 |
Neg logit contributions | |
ippi | -0.044 |
Beir | -0.044 |
nton | -0.043 |
Gad | -0.040 |
Sas | -0.040 |
Token | / |
Token ID | 14 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Beir | +0.330 |
ippi | +0.330 |
nton | +0.327 |
Gad | +0.308 |
Sas | +0.306 |
Neg logit contributions | |
ILCS | -0.428 |
機 | -0.349 |
(_ | -0.336 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.335 |
belts | -0.331 |
Token | 10 |
Token ID | 940 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
ippi | +0.578 |
Beir | +0.578 |
nton | +0.570 |
Gad | +0.532 |
Sas | +0.529 |
Neg logit contributions | |
ILCS | -0.956 |
機 | -0.797 |
(_ | -0.772 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.768 |
belts | -0.758 |
Token | Castle |
Token ID | 11312 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
ippi | +0.393 |
Beir | +0.391 |
nton | +0.387 |
Sas | +0.364 |
spons | +0.364 |
Neg logit contributions | |
ILCS | -0.483 |
機 | -0.391 |
(_ | -0.378 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.377 |
belts | -0.372 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ippi | +1.091 |
Beir | +1.086 |
nton | +1.083 |
Gad | +1.009 |
Sas | +1.000 |
Neg logit contributions | |
ILCS | -1.665 |
機 | -1.388 |
(_ | -1.333 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.331 |
belts | -1.308 |
Token | some |
Token ID | 617 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
ILCS | +0.990 |
機 | +0.791 |
(_ | +0.764 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.762 |
belts | +0.761 |
Neg logit contributions | |
ippi | -0.828 |
Beir | -0.828 |
nton | -0.821 |
Gad | -0.769 |
spons | -0.768 |
Token | see |
Token ID | 766 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ILCS | +2.518 |
機 | +1.977 |
belts | +1.965 |
(_ | +1.948 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.928 |
Neg logit contributions | |
ippi | -2.070 |
nton | -2.060 |
Beir | -2.050 |
lished | -1.945 |
spons | -1.898 |
Token | " |
Token ID | 366 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ILCS | +0.772 |
機 | +0.618 |
(_ | +0.599 |
belts | +0.594 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.591 |
Neg logit contributions | |
ippi | -0.681 |
Beir | -0.678 |
nton | -0.671 |
spons | -0.630 |
lished | -0.629 |
Token | Pokémon |
Token ID | 46602 |
Feature activation | +6.38e+00 |
Pos logit contributions | |
ILCS | +0.936 |
機 | +0.758 |
(_ | +0.731 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.726 |
belts | +0.715 |
Neg logit contributions | |
Beir | -0.775 |
ippi | -0.772 |
nton | -0.759 |
Gad | -0.720 |
Sas | -0.718 |
Token | people |
Token ID | 661 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
ILCS | +3.926 |
機 | +2.973 |
belts | +2.910 |
Send | +2.882 |
(_ | +2.866 |
Neg logit contributions | |
ippi | -4.981 |
Beir | -4.956 |
nton | -4.941 |
lished | -4.761 |
spons | -4.685 |
Token | " |
Token ID | 1 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
ILCS | +0.505 |
機 | +0.412 |
(_ | +0.398 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.397 |
belts | +0.391 |
Neg logit contributions | |
ippi | -0.386 |
Beir | -0.385 |
nton | -0.382 |
Gad | -0.359 |
Sas | -0.357 |
Token | as |
Token ID | 355 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
ippi | +0.297 |
Beir | +0.297 |
nton | +0.294 |
Gad | +0.278 |
Sas | +0.277 |
Neg logit contributions | |
ILCS | -0.326 |
機 | -0.261 |
(_ | -0.251 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.250 |
belts | -0.246 |
Token | an |
Token ID | 281 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
ippi | +0.424 |
Beir | +0.424 |
nton | +0.420 |
Gad | +0.397 |
Sas | +0.395 |
Neg logit contributions | |
ILCS | -0.482 |
機 | -0.388 |
(_ | -0.373 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.372 |
belts | -0.366 |
Token | invasive |
Token ID | 27376 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
ippi | +0.046 |
Beir | +0.046 |
nton | +0.046 |
Gad | +0.043 |
Sas | +0.043 |
Neg logit contributions | |
ILCS | -0.050 |
機 | -0.040 |
(_ | -0.038 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.038 |
belts | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ippi | +0.361 |
Beir | +0.360 |
nton | +0.353 |
spons | +0.336 |
Gad | +0.329 |
Neg logit contributions | |
ILCS | -0.560 |
機 | -0.465 |
(_ | -0.454 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.450 |
Send | -0.444 |
Token | Apparently |
Token ID | 30402 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Beir | +0.249 |
ippi | +0.249 |
nton | +0.245 |
Gad | +0.233 |
Sas | +0.232 |
Neg logit contributions | |
ILCS | -0.257 |
機 | -0.205 |
(_ | -0.198 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.196 |
Send | -0.192 |
Token | they |
Token ID | 484 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ILCS | +0.164 |
機 | +0.133 |
(_ | +0.128 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.127 |
belts | +0.126 |
Neg logit contributions | |
ippi | -0.140 |
Beir | -0.139 |
nton | -0.138 |
Gad | -0.130 |
Sas | -0.129 |
Token | feel |
Token ID | 1254 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
ILCS | +1.152 |
機 | +0.928 |
(_ | +0.908 |
belts | +0.901 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.895 |
Neg logit contributions | |
ippi | -1.073 |
Beir | -1.065 |
nton | -1.056 |
Gad | -1.010 |
lished | -1.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ILCS | +2.777 |
機 | +2.238 |
(_ | +2.148 |
belts | +2.132 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.131 |
Neg logit contributions | |
ippi | -2.729 |
nton | -2.714 |
Beir | -2.668 |
lished | -2.521 |
Wonders | -2.508 |
Token | same |
Token ID | 976 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
ILCS | +0.803 |
機 | +0.628 |
(_ | +0.599 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.596 |
belts | +0.588 |
Neg logit contributions | |
ippi | -0.907 |
Beir | -0.902 |
nton | -0.900 |
Gad | -0.851 |
Sas | -0.850 |
Token | way |
Token ID | 835 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ILCS | +3.784 |
機 | +2.958 |
belts | +2.899 |
(_ | +2.838 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.805 |
Neg logit contributions | |
ippi | -5.070 |
nton | -4.914 |
Beir | -4.869 |
lished | -4.779 |
Wonders | -4.590 |
Token | about |
Token ID | 546 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
ILCS | +1.350 |
機 | +1.104 |
(_ | +1.074 |
belts | +1.063 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.062 |
Neg logit contributions | |
ippi | -0.965 |
nton | -0.952 |
Beir | -0.947 |
Gad | -0.879 |
spons | -0.876 |
Token | the |
Token ID | 262 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
ILCS | +2.538 |
機 | +2.054 |
(_ | +2.023 |
belts | +2.007 |
Send | +1.968 |
Neg logit contributions | |
ippi | -2.160 |
nton | -2.137 |
Beir | -2.124 |
lished | -2.006 |
spons | -1.995 |
Token | Trump |
Token ID | 1301 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
ILCS | +0.300 |
機 | +0.242 |
(_ | +0.233 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.231 |
belts | +0.229 |
Neg logit contributions | |
ippi | -0.261 |
Beir | -0.260 |
nton | -0.258 |
Gad | -0.243 |
Sas | -0.242 |
Token | Free |
Token ID | 3232 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
ILCS | +0.014 |
機 | +0.012 |
(_ | +0.011 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.011 |
belts | +0.011 |
Neg logit contributions | |
ippi | -0.012 |
Beir | -0.012 |
nton | -0.012 |
Gad | -0.011 |
Sas | -0.011 |
Token | just |
Token ID | 655 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
ILCS | +0.299 |
機 | +0.242 |
(_ | +0.232 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.232 |
belts | +0.229 |
Neg logit contributions | |
ippi | -0.266 |
Beir | -0.266 |
nton | -0.264 |
Gad | -0.251 |
Sas | -0.248 |
Token | climbed |
Token ID | 19952 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
ILCS | +0.144 |
機 | +0.117 |
(_ | +0.112 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.112 |
belts | +0.111 |
Neg logit contributions | |
ippi | -0.123 |
Beir | -0.123 |
nton | -0.122 |
Gad | -0.116 |
Sas | -0.114 |
Token | half |
Token ID | 2063 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ILCS | +2.599 |
機 | +2.045 |
(_ | +2.011 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.002 |
belts | +1.989 |
Neg logit contributions | |
nton | -2.500 |
ippi | -2.499 |
Beir | -2.467 |
Gad | -2.316 |
spons | -2.316 |
Token | of |
Token ID | 286 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ILCS | +0.963 |
機 | +0.768 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.746 |
(_ | +0.745 |
belts | +0.734 |
Neg logit contributions | |
Beir | -0.826 |
nton | -0.826 |
ippi | -0.824 |
Gad | -0.768 |
Wonders | -0.764 |
Token | Mount |
Token ID | 5628 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
ippi | +0.117 |
Beir | +0.116 |
nton | +0.116 |
Gad | +0.109 |
Sas | +0.108 |
Neg logit contributions | |
ILCS | -0.142 |
機 | -0.115 |
(_ | -0.111 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.111 |
belts | -0.109 |
Token | Everest |
Token ID | 41336 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
ILCS | +0.173 |
機 | +0.136 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.132 |
(_ | +0.132 |
belts | +0.129 |
Neg logit contributions | |
nton | -0.161 |
ippi | -0.161 |
Beir | -0.160 |
spons | -0.152 |
Gad | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ILCS | +4.435 |
機 | +3.517 |
(_ | +3.434 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.380 |
belts | +3.355 |
Neg logit contributions | |
nton | -4.298 |
Beir | -4.285 |
ippi | -4.261 |
Gad | -4.037 |
spons | -3.975 |
Token | � |
Token ID | 447 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
ILCS | +0.279 |
機 | +0.228 |
(_ | +0.220 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.219 |
belts | +0.215 |
Neg logit contributions | |
ippi | -0.217 |
Beir | -0.216 |
nton | -0.215 |
Gad | -0.201 |
spons | -0.201 |
Token | � |
Token ID | 251 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
ippi | +0.123 |
Beir | +0.122 |
nton | +0.121 |
Gad | +0.115 |
Sas | +0.115 |
Neg logit contributions | |
ILCS | -0.129 |
機 | -0.102 |
(_ | -0.098 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.097 |
belts | -0.096 |
Token |
|
Token ID | 198 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ILCS | +0.299 |
機 | +0.244 |
(_ | +0.236 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.235 |
belts | +0.230 |
Neg logit contributions | |
Beir | -0.228 |
ippi | -0.228 |
nton | -0.227 |
spons | -0.212 |
Gad | -0.211 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
ILCS | +0.120 |
機 | +0.099 |
(_ | +0.098 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.096 |
Send | +0.095 |
Neg logit contributions | |
Beir | -0.085 |
ippi | -0.084 |
nton | -0.082 |
spons | -0.080 |
lished | -0.078 |
Token | NASA |
Token ID | 8884 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
ILCS | +0.071 |
機 | +0.057 |
(_ | +0.055 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.055 |
belts | +0.055 |
Neg logit contributions | |
ippi | -0.057 |
Beir | -0.057 |
nton | -0.056 |
Gad | -0.053 |
spons | -0.053 |
Token | said |
Token ID | 531 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ippi | +0.454 |
Beir | +0.451 |
nton | +0.447 |
Gad | +0.417 |
Sas | +0.416 |
Neg logit contributions | |
ILCS | -0.652 |
機 | -0.537 |
(_ | -0.521 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.517 |
belts | -0.515 |
Token | , |
Token ID | 11 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Beir | +0.929 |
ippi | +0.925 |
nton | +0.919 |
Gad | +0.871 |
Sas | +0.869 |
Neg logit contributions | |
ILCS | -1.112 |
機 | -0.893 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.861 |
(_ | -0.853 |
ーテ | -0.835 |
Token | because |
Token ID | 780 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
ILCS | +0.217 |
機 | +0.172 |
(_ | +0.165 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.165 |
belts | +0.163 |
Neg logit contributions | |
ippi | -0.215 |
Beir | -0.214 |
nton | -0.213 |
Gad | -0.201 |
Sas | -0.200 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ILCS | +2.034 |
機 | +1.624 |
belts | +1.588 |
(_ | +1.564 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.556 |
Neg logit contributions | |
Beir | -1.996 |
ippi | -1.990 |
nton | -1.988 |
lished | -1.835 |
spons | -1.835 |
Token | sun |
Token ID | 4252 |
Feature activation | +6.16e+00 |
Pos logit contributions | |
ILCS | +0.264 |
機 | +0.212 |
(_ | +0.204 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.202 |
belts | +0.201 |
Neg logit contributions | |
Beir | -0.238 |
ippi | -0.238 |
nton | -0.235 |
Gad | -0.222 |
Sas | -0.221 |
Token | and |
Token ID | 290 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ILCS | +4.758 |
belts | +3.930 |
機 | +3.884 |
(_ | +3.802 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.710 |
Neg logit contributions | |
ippi | -3.976 |
Beir | -3.908 |
nton | -3.780 |
lished | -3.592 |
Sas | -3.563 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ILCS | +0.701 |
機 | +0.561 |
(_ | +0.539 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.536 |
belts | +0.528 |
Neg logit contributions | |
ippi | -0.651 |
Beir | -0.651 |
nton | -0.645 |
Gad | -0.610 |
Sas | -0.608 |
Token | moon |
Token ID | 8824 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
ILCS | +0.241 |
機 | +0.191 |
(_ | +0.183 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.182 |
belts | +0.180 |
Neg logit contributions | |
ippi | -0.248 |
Beir | -0.248 |
nton | -0.246 |
Gad | -0.233 |
Sas | -0.232 |
Token | are |
Token ID | 389 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
ILCS | +2.439 |
belts | +1.959 |
機 | +1.953 |
(_ | +1.932 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.892 |
Neg logit contributions | |
ippi | -2.075 |
Beir | -2.069 |
nton | -2.038 |
lished | -1.943 |
Sas | -1.895 |
Token | tug |
Token ID | 27762 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
ILCS | +0.626 |
機 | +0.501 |
(_ | +0.483 |
belts | +0.483 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.482 |
Neg logit contributions | |
ippi | -0.562 |
Beir | -0.560 |
nton | -0.558 |
Sas | -0.520 |
Gad | -0.519 |
Token | , |
Token ID | 11 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
Beir | +0.954 |
ippi | +0.953 |
nton | +0.943 |
Gad | +0.894 |
Sas | +0.892 |
Neg logit contributions | |
ILCS | -1.043 |
機 | -0.834 |
(_ | -0.796 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.795 |
belts | -0.780 |
Token | and |
Token ID | 290 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
ippi | +0.334 |
Beir | +0.333 |
nton | +0.330 |
Gad | +0.311 |
Sas | +0.310 |
Neg logit contributions | |
ILCS | -0.396 |
機 | -0.321 |
(_ | -0.310 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.308 |
belts | -0.304 |
Token | subsequently |
Token ID | 12412 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ippi | +0.530 |
Beir | +0.528 |
nton | +0.525 |
Gad | +0.493 |
Sas | +0.491 |
Neg logit contributions | |
ILCS | -0.613 |
機 | -0.495 |
(_ | -0.478 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.474 |
belts | -0.469 |
Token | promising |
Token ID | 11781 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ippi | +0.304 |
Beir | +0.303 |
nton | +0.300 |
Gad | +0.283 |
Sas | +0.281 |
Neg logit contributions | |
ILCS | -0.340 |
機 | -0.273 |
(_ | -0.264 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.262 |
belts | -0.259 |
Token | the |
Token ID | 262 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
Beir | +1.166 |
ippi | +1.163 |
nton | +1.150 |
Sas | +1.090 |
Gad | +1.090 |
Neg logit contributions | |
ILCS | -1.498 |
機 | -1.221 |
(_ | -1.169 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.167 |
belts | -1.145 |
Token | equivalent |
Token ID | 7548 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
ILCS | +0.688 |
機 | +0.555 |
(_ | +0.541 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.537 |
belts | +0.532 |
Neg logit contributions | |
ippi | -0.620 |
nton | -0.615 |
Beir | -0.613 |
lished | -0.572 |
Gad | -0.570 |
Token | of |
Token ID | 286 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +3.981 |
機 | +3.103 |
(_ | +3.081 |
belts | +3.008 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.997 |
Neg logit contributions | |
ippi | -4.602 |
nton | -4.583 |
Beir | -4.538 |
lished | -4.361 |
Wonders | -4.292 |
Token | $ |
Token ID | 720 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
ILCS | +0.981 |
機 | +0.792 |
(_ | +0.776 |
belts | +0.767 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.767 |
Neg logit contributions | |
ippi | -0.871 |
Beir | -0.859 |
nton | -0.858 |
Gad | -0.797 |
Wonders | -0.796 |
Token | 5 |
Token ID | 20 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
ILCS | +0.610 |
機 | +0.505 |
(_ | +0.489 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.486 |
belts | +0.475 |
Neg logit contributions | |
ippi | -0.418 |
Beir | -0.418 |
nton | -0.412 |
spons | -0.387 |
Gad | -0.385 |
Token | billion |
Token ID | 2997 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ippi | +1.438 |
Beir | +1.427 |
nton | +1.420 |
Sas | +1.341 |
Gad | +1.338 |
Neg logit contributions | |
ILCS | -2.037 |
機 | -1.685 |
(_ | -1.617 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.610 |
belts | -1.590 |
Token | to |
Token ID | 284 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ippi | +1.026 |
Beir | +1.025 |
nton | +1.013 |
Gad | +0.961 |
Sas | +0.960 |
Neg logit contributions | |
ILCS | -1.200 |
機 | -0.971 |
(_ | -0.929 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.927 |
belts | -0.913 |
Token | it |
Token ID | 340 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ILCS | +0.547 |
機 | +0.435 |
(_ | +0.419 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.415 |
belts | +0.411 |
Neg logit contributions | |
ippi | -0.516 |
Beir | -0.516 |
nton | -0.509 |
Gad | -0.480 |
Sas | -0.478 |
Token | the |
Token ID | 262 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
ippi | +0.657 |
Beir | +0.657 |
nton | +0.651 |
Gad | +0.616 |
Sas | +0.615 |
Neg logit contributions | |
ILCS | -0.781 |
機 | -0.634 |
(_ | -0.609 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.604 |
belts | -0.594 |
Token | financial |
Token ID | 3176 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
ILCS | +0.411 |
機 | +0.330 |
(_ | +0.318 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.317 |
belts | +0.313 |
Neg logit contributions | |
ippi | -0.364 |
Beir | -0.363 |
nton | -0.360 |
Gad | -0.340 |
Sas | -0.338 |
Token | means |
Token ID | 1724 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ILCS | +0.110 |
機 | +0.088 |
(_ | +0.085 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.084 |
belts | +0.083 |
Neg logit contributions | |
ippi | -0.100 |
Beir | -0.100 |
nton | -0.099 |
Gad | -0.093 |
Sas | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ippi | +0.993 |
Beir | +0.983 |
nton | +0.977 |
Gad | +0.921 |
Sas | +0.920 |
Neg logit contributions | |
ILCS | -1.367 |
機 | -1.121 |
(_ | -1.078 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.068 |
belts | -1.060 |
Token | incentiv |
Token ID | 39678 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
ILCS | +0.212 |
機 | +0.164 |
(_ | +0.158 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.158 |
belts | +0.155 |
Neg logit contributions | |
ippi | -0.243 |
Beir | -0.242 |
nton | -0.239 |
Gad | -0.227 |
Sas | -0.226 |
Token | ise |
Token ID | 786 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ILCS | +4.210 |
機 | +3.325 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.241 |
(_ | +3.240 |
Send | +3.181 |
Neg logit contributions | |
Beir | -4.438 |
ippi | -4.418 |
nton | -4.384 |
lished | -4.113 |
Gad | -4.100 |
Token | States |
Token ID | 1829 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
ILCS | +1.212 |
機 | +0.958 |
(_ | +0.928 |
belts | +0.916 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.915 |
Neg logit contributions | |
ippi | -1.143 |
Beir | -1.138 |
nton | -1.125 |
Gad | -1.057 |
Sas | -1.052 |
Token | to |
Token ID | 284 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
ippi | +0.208 |
Beir | +0.208 |
nton | +0.206 |
Gad | +0.194 |
Sas | +0.193 |
Neg logit contributions | |
ILCS | -0.260 |
機 | -0.211 |
(_ | -0.204 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.203 |
belts | -0.200 |
Token | pursue |
Token ID | 10660 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ILCS | +0.054 |
機 | +0.043 |
(_ | +0.041 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.041 |
belts | +0.040 |
Neg logit contributions | |
ippi | -0.057 |
Beir | -0.056 |
nton | -0.056 |
Gad | -0.053 |
Sas | -0.052 |
Token | specific |
Token ID | 2176 |
Feature activation | +9.83e-01 |
Pos logit contributions | |
ILCS | +1.191 |
機 | +0.927 |
(_ | +0.902 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.889 |
belts | +0.884 |
Neg logit contributions | |
ippi | -1.259 |
Beir | -1.254 |
nton | -1.239 |
Gad | -1.166 |
Sas | -1.163 |
Token | made |
Token ID | 925 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
Beir | +0.603 |
ippi | +0.603 |
nton | +0.593 |
Gad | +0.561 |
Sas | +0.555 |
Neg logit contributions | |
ILCS | -0.841 |
機 | -0.697 |
(_ | -0.673 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.668 |
belts | -0.666 |
Token | me |
Token ID | 502 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
ippi | +0.449 |
Beir | +0.444 |
nton | +0.443 |
Gad | +0.411 |
Sas | +0.406 |
Neg logit contributions | |
ILCS | -0.684 |
機 | -0.564 |
(_ | -0.552 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.549 |
belts | -0.545 |
Token | wonder |
Token ID | 4240 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
ippi | +0.406 |
Beir | +0.405 |
nton | +0.401 |
Gad | +0.378 |
Sas | +0.374 |
Neg logit contributions | |
ILCS | -0.497 |
機 | -0.402 |
(_ | -0.392 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.390 |
belts | -0.387 |
Token | how |
Token ID | 703 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
Beir | +2.693 |
ippi | +2.683 |
nton | +2.668 |
Sas | +2.543 |
Gad | +2.530 |
Neg logit contributions | |
ILCS | -2.884 |
機 | -2.333 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.203 |
(_ | -2.198 |
ーテ | -2.173 |
Token | many |
Token ID | 867 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
ippi | +0.642 |
Beir | +0.639 |
nton | +0.634 |
Gad | +0.599 |
Sas | +0.595 |
Neg logit contributions | |
ILCS | -0.704 |
機 | -0.563 |
(_ | -0.542 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.540 |
belts | -0.533 |
Token | cub |
Token ID | 13617 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
Beir | +1.726 |
ippi | +1.720 |
nton | +1.701 |
Sas | +1.625 |
Gad | +1.615 |
Neg logit contributions | |
ILCS | -2.131 |
機 | -1.745 |
(_ | -1.674 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.656 |
belts | -1.626 |
Token | s |
Token ID | 82 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ILCS | +4.227 |
機 | +3.313 |
(_ | +3.274 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.255 |
belts | +3.248 |
Neg logit contributions | |
Beir | -4.272 |
ippi | -4.272 |
nton | -4.198 |
Gad | -3.969 |
course | -3.921 |
Token | have |
Token ID | 423 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ILCS | +1.045 |
機 | +0.824 |
(_ | +0.813 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.810 |
belts | +0.804 |
Neg logit contributions | |
ippi | -0.860 |
nton | -0.850 |
Beir | -0.845 |
lished | -0.792 |
Gad | -0.791 |
Token | bonded |
Token ID | 40270 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ILCS | +0.270 |
機 | +0.217 |
(_ | +0.211 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.211 |
belts | +0.210 |
Neg logit contributions | |
ippi | -0.223 |
Beir | -0.221 |
nton | -0.221 |
Gad | -0.206 |
spons | -0.204 |
Token | with |
Token ID | 351 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ILCS | +0.893 |
機 | +0.701 |
(_ | +0.683 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.675 |
belts | +0.673 |
Neg logit contributions | |
ippi | -0.912 |
Beir | -0.906 |
nton | -0.905 |
Gad | -0.852 |
spons | -0.843 |
Token | individuals |
Token ID | 3925 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
ippi | +0.327 |
Beir | +0.324 |
nton | +0.323 |
Gad | +0.301 |
spons | +0.298 |
Neg logit contributions | |
ILCS | -0.413 |
機 | -0.335 |
(_ | -0.325 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.324 |
belts | -0.323 |
Token | Reid |
Token ID | 16095 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
ILCS | +1.440 |
機 | +1.154 |
(_ | +1.119 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.104 |
belts | +1.103 |
Neg logit contributions | |
Beir | -1.162 |
ippi | -1.161 |
nton | -1.146 |
spons | -1.088 |
lished | -1.069 |
Token | spoke |
Token ID | 5158 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ILCS | +0.296 |
機 | +0.241 |
(_ | +0.233 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.230 |
belts | +0.229 |
Neg logit contributions | |
ippi | -0.243 |
Beir | -0.242 |
nton | -0.240 |
Gad | -0.226 |
Sas | -0.225 |
Token | on |
Token ID | 319 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
ILCS | +0.706 |
機 | +0.575 |
(_ | +0.558 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.550 |
belts | +0.546 |
Neg logit contributions | |
ippi | -0.603 |
Beir | -0.602 |
nton | -0.597 |
Gad | -0.561 |
Sas | -0.558 |
Token | the |
Token ID | 262 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ippi | +0.039 |
Beir | +0.039 |
nton | +0.039 |
Gad | +0.036 |
spons | +0.036 |
Neg logit contributions | |
ILCS | -0.055 |
機 | -0.045 |
(_ | -0.044 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.043 |
belts | -0.043 |
Token | Senate |
Token ID | 3845 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
ippi | +0.027 |
Beir | +0.027 |
nton | +0.027 |
Gad | +0.025 |
Sas | +0.025 |
Neg logit contributions | |
ILCS | -0.030 |
機 | -0.024 |
(_ | -0.023 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.023 |
belts | -0.023 |
Token | floor |
Token ID | 4314 |
Feature activation | +6.02e+00 |
Pos logit contributions | |
ILCS | +0.588 |
機 | +0.443 |
(_ | +0.432 |
belts | +0.420 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.419 |
Neg logit contributions | |
ippi | -0.839 |
Beir | -0.836 |
nton | -0.830 |
lished | -0.790 |
spons | -0.789 |
Token | Monday |
Token ID | 3321 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
ILCS | +4.463 |
(_ | +3.659 |
belts | +3.594 |
機 | +3.591 |
Merit | +3.496 |
Neg logit contributions | |
ippi | -3.861 |
Beir | -3.799 |
nton | -3.793 |
lished | -3.685 |
Wonders | -3.523 |
Token | about |
Token ID | 546 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ILCS | +0.460 |
機 | +0.371 |
(_ | +0.362 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.356 |
belts | +0.355 |
Neg logit contributions | |
Beir | -0.408 |
ippi | -0.407 |
nton | -0.402 |
Gad | -0.379 |
Sas | -0.377 |
Token | Republican |
Token ID | 3415 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
ILCS | +1.394 |
機 | +1.119 |
(_ | +1.083 |
belts | +1.074 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.068 |
Neg logit contributions | |
ippi | -1.319 |
Beir | -1.314 |
nton | -1.300 |
spons | -1.222 |
Gad | -1.217 |
Token | support |
Token ID | 1104 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
Beir | +0.527 |
ippi | +0.525 |
nton | +0.520 |
Gad | +0.489 |
Sas | +0.487 |
Neg logit contributions | |
ILCS | -0.643 |
機 | -0.522 |
(_ | -0.504 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.500 |
belts | -0.496 |
Token | of |
Token ID | 286 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
ILCS | +0.440 |
機 | +0.335 |
(_ | +0.319 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.317 |
belts | +0.310 |
Neg logit contributions | |
ippi | -0.568 |
Beir | -0.567 |
nton | -0.563 |
Gad | -0.537 |
Sas | -0.536 |
Token | but |
Token ID | 475 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
ippi | +0.107 |
Beir | +0.106 |
nton | +0.105 |
Gad | +0.100 |
Sas | +0.099 |
Neg logit contributions | |
ILCS | -0.118 |
機 | -0.095 |
(_ | -0.091 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.091 |
belts | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ippi | +0.589 |
Beir | +0.586 |
nton | +0.581 |
Gad | +0.548 |
Sas | +0.545 |
Neg logit contributions | |
ILCS | -0.649 |
機 | -0.519 |
(_ | -0.499 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.497 |
belts | -0.491 |
Token | decisions |
Token ID | 5370 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
ILCS | +0.266 |
機 | +0.212 |
(_ | +0.204 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.204 |
belts | +0.202 |
Neg logit contributions | |
ippi | -0.240 |
Beir | -0.238 |
nton | -0.237 |
Gad | -0.223 |
spons | -0.222 |
Token | made |
Token ID | 925 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
ippi | +1.634 |
Beir | +1.632 |
nton | +1.615 |
Gad | +1.518 |
Sas | +1.513 |
Neg logit contributions | |
ILCS | -2.180 |
機 | -1.785 |
(_ | -1.722 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.714 |
belts | -1.690 |
Token | in |
Token ID | 287 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ippi | +0.409 |
Beir | +0.409 |
nton | +0.405 |
Gad | +0.382 |
Sas | +0.381 |
Neg logit contributions | |
ILCS | -0.468 |
機 | -0.376 |
(_ | -0.363 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.362 |
belts | -0.355 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ILCS | +0.332 |
機 | +0.267 |
(_ | +0.258 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.257 |
belts | +0.253 |
Neg logit contributions | |
ippi | -0.283 |
Beir | -0.281 |
nton | -0.279 |
Gad | -0.262 |
spons | -0.260 |
Token | ` |
Token ID | 63 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
ILCS | +3.352 |
機 | +2.379 |
(_ | +2.320 |
ñ | +2.282 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.273 |
Neg logit contributions | |
Beir | -5.169 |
nton | -5.119 |
ippi | -4.981 |
lished | -4.963 |
spons | -4.929 |
Token | i |
Token ID | 72 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
ILCS | +2.527 |
機 | +1.982 |
(_ | +1.956 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.908 |
ñ | +1.898 |
Neg logit contributions | |
Beir | -2.604 |
nton | -2.501 |
ippi | -2.482 |
lished | -2.444 |
Gad | -2.393 |
Token | in |
Token ID | 287 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
ILCS | +2.087 |
機 | +1.667 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.616 |
(_ | +1.610 |
ñ | +1.586 |
Neg logit contributions | |
Beir | -1.740 |
nton | -1.723 |
ippi | -1.714 |
Gad | -1.617 |
lished | -1.609 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
ILCS | +0.504 |
機 | +0.401 |
(_ | +0.385 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.384 |
belts | +0.377 |
Neg logit contributions | |
ippi | -0.492 |
Beir | -0.487 |
nton | -0.484 |
Gad | -0.456 |
spons | -0.454 |
Token | and |
Token ID | 290 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ILCS | +1.379 |
機 | +1.111 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.075 |
(_ | +1.067 |
ÃÂ | +1.041 |
Neg logit contributions | |
Beir | -1.141 |
ippi | -1.134 |
nton | -1.131 |
Gad | -1.065 |
Sas | -1.056 |
Token | Democrat |
Token ID | 9755 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
ILCS | +0.912 |
機 | +0.721 |
(_ | +0.703 |
belts | +0.690 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.690 |
Neg logit contributions | |
ippi | -0.833 |
Beir | -0.822 |
nton | -0.818 |
Wonders | -0.767 |
spons | -0.764 |
Token | . |
Token ID | 13 |
Feature activation | +7.53e-01 |
Pos logit contributions | |
Beir | +0.041 |
ippi | +0.041 |
nton | +0.040 |
Gad | +0.038 |
Sas | +0.038 |
Neg logit contributions | |
ILCS | -0.043 |
機 | -0.035 |
(_ | -0.033 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.033 |
belts | -0.033 |
Token | Sen |
Token ID | 2311 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ILCS | +0.643 |
機 | +0.524 |
(_ | +0.510 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.505 |
Send | +0.497 |
Neg logit contributions | |
ippi | -0.442 |
nton | -0.436 |
Beir | -0.435 |
spons | -0.416 |
lished | -0.403 |
Token | . |
Token ID | 13 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ILCS | +0.013 |
機 | +0.010 |
(_ | +0.010 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.010 |
belts | +0.009 |
Neg logit contributions | |
ippi | -0.012 |
Beir | -0.012 |
nton | -0.012 |
Gad | -0.011 |
Sas | -0.011 |
Token | Eddie |
Token ID | 19478 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ILCS | +0.540 |
機 | +0.445 |
(_ | +0.434 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.430 |
belts | +0.428 |
Neg logit contributions | |
ippi | -0.329 |
Beir | -0.324 |
nton | -0.323 |
spons | -0.303 |
lished | -0.296 |
Token | Luc |
Token ID | 7598 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
ILCS | +1.457 |
機 | +1.174 |
(_ | +1.153 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.138 |
belts | +1.121 |
Neg logit contributions | |
ippi | -1.113 |
Beir | -1.085 |
nton | -1.075 |
spons | -1.034 |
lished | -1.007 |
Token | io |
Token ID | 952 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
ILCS | +4.690 |
機 | +3.756 |
umann | +3.744 |
(_ | +3.730 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.697 |
Neg logit contributions | |
Beir | -3.619 |
ippi | -3.501 |
nton | -3.359 |
spons | -3.351 |
Wonders | -3.254 |
Token | , |
Token ID | 11 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ILCS | +2.165 |
機 | +1.760 |
(_ | +1.719 |
belts | +1.687 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.687 |
Neg logit contributions | |
ippi | -1.715 |
Beir | -1.707 |
nton | -1.699 |
spons | -1.599 |
Wonders | -1.597 |
Token | a |
Token ID | 257 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ILCS | +1.354 |
機 | +1.084 |
(_ | +1.055 |
belts | +1.039 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.036 |
Neg logit contributions | |
ippi | -1.137 |
Beir | -1.131 |
nton | -1.124 |
Wonders | -1.049 |
Gad | -1.048 |
Token | Browns |
Token ID | 17671 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ILCS | +1.239 |
機 | +0.965 |
(_ | +0.940 |
belts | +0.923 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.922 |
Neg logit contributions | |
ippi | -1.234 |
Beir | -1.221 |
nton | -1.208 |
lished | -1.139 |
Wonders | -1.138 |
Token | ville |
Token ID | 4244 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ILCS | +0.188 |
機 | +0.140 |
(_ | +0.135 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.133 |
belts | +0.131 |
Neg logit contributions | |
Beir | -0.249 |
ippi | -0.246 |
nton | -0.244 |
Gad | -0.236 |
Sas | -0.234 |
Token | voters |
Token ID | 4446 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ILCS | +0.012 |
機 | +0.010 |
(_ | +0.009 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.009 |
belts | +0.009 |
Neg logit contributions | |
ippi | -0.011 |
Beir | -0.011 |
nton | -0.011 |
Gad | -0.010 |
Wonders | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
ILCS | +1.160 |
機 | +0.934 |
(_ | +0.905 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.894 |
belts | +0.888 |
Neg logit contributions | |
ippi | -1.012 |
Beir | -1.004 |
nton | -0.993 |
Gad | -0.937 |
Sas | -0.937 |
Token | than |
Token ID | 621 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ippi | +0.061 |
Beir | +0.060 |
nton | +0.060 |
Gad | +0.056 |
Sas | +0.056 |
Neg logit contributions | |
ILCS | -0.067 |
機 | -0.054 |
(_ | -0.052 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.052 |
belts | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ippi | +0.139 |
Beir | +0.139 |
nton | +0.138 |
Gad | +0.130 |
Sas | +0.130 |
Neg logit contributions | |
ILCS | -0.158 |
機 | -0.127 |
(_ | -0.122 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.122 |
belts | -0.120 |
Token | bully |
Token ID | 27410 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
ILCS | +0.679 |
機 | +0.543 |
(_ | +0.523 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.518 |
belts | +0.514 |
Neg logit contributions | |
ippi | -0.632 |
Beir | -0.627 |
nton | -0.625 |
Gad | -0.589 |
Sas | -0.584 |
Token | pul |
Token ID | 17472 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
ILCS | +2.328 |
機 | +1.894 |
belts | +1.847 |
(_ | +1.837 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.806 |
Neg logit contributions | |
ippi | -1.948 |
Beir | -1.916 |
nton | -1.881 |
Wonders | -1.791 |
Gad | -1.768 |
Token | pit |
Token ID | 15544 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
ILCS | +3.324 |
機 | +2.447 |
(_ | +2.384 |
umann | +2.333 |
Send | +2.317 |
Neg logit contributions | |
Beir | -5.091 |
ippi | -4.951 |
nton | -4.854 |
Gad | -4.770 |
Wonders | -4.764 |
Token | . |
Token ID | 13 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
ILCS | +2.679 |
機 | +2.133 |
(_ | +2.064 |
belts | +2.053 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.037 |
Neg logit contributions | |
ippi | -2.591 |
Beir | -2.564 |
nton | -2.549 |
Gad | -2.409 |
Wonders | -2.394 |
Token | PK |
Token ID | 29673 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
ILCS | +0.624 |
機 | +0.506 |
(_ | +0.489 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.487 |
Send | +0.479 |
Neg logit contributions | |
ippi | -0.517 |
Beir | -0.509 |
nton | -0.507 |
spons | -0.481 |
Gad | -0.476 |
Token | claims |
Token ID | 3667 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ippi | +0.261 |
Beir | +0.261 |
nton | +0.257 |
Gad | +0.242 |
Sas | +0.241 |
Neg logit contributions | |
ILCS | -0.336 |
機 | -0.275 |
(_ | -0.266 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.264 |
belts | -0.261 |
Token | that |
Token ID | 326 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ippi | +0.695 |
Beir | +0.694 |
nton | +0.687 |
Gad | +0.649 |
Sas | +0.647 |
Neg logit contributions | |
ILCS | -0.831 |
機 | -0.673 |
(_ | -0.647 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.645 |
belts | -0.634 |
Token | to |
Token ID | 284 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
ippi | +0.826 |
Beir | +0.825 |
nton | +0.816 |
Gad | +0.772 |
Sas | +0.769 |
Neg logit contributions | |
ILCS | -0.995 |
機 | -0.806 |
(_ | -0.774 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.772 |
belts | -0.759 |
Token | natural |
Token ID | 3288 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
ippi | +0.639 |
Beir | +0.637 |
nton | +0.632 |
Gad | +0.596 |
Sas | +0.593 |
Neg logit contributions | |
ILCS | -0.702 |
機 | -0.562 |
(_ | -0.542 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.539 |
belts | -0.531 |
Token | gas |
Token ID | 3623 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
ippi | +0.396 |
Beir | +0.396 |
nton | +0.392 |
Gad | +0.372 |
Sas | +0.371 |
Neg logit contributions | |
ILCS | -0.391 |
機 | -0.309 |
(_ | -0.296 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.294 |
belts | -0.290 |
Token | , |
Token ID | 11 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
ippi | +0.386 |
Beir | +0.385 |
nton | +0.382 |
Gad | +0.360 |
Sas | +0.360 |
Neg logit contributions | |
ILCS | -0.432 |
機 | -0.348 |
(_ | -0.335 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.333 |
belts | -0.328 |
Token | but |
Token ID | 475 |
Feature activation | +6.74e-01 |
Pos logit contributions | |
ILCS | +0.677 |
機 | +0.541 |
(_ | +0.521 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.518 |
belts | +0.514 |
Neg logit contributions | |
ippi | -0.613 |
Beir | -0.605 |
nton | -0.603 |
Gad | -0.564 |
lished | -0.564 |
Token | Hawai |
Token ID | 10847 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
ILCS | +0.503 |
機 | +0.402 |
(_ | +0.386 |
belts | +0.384 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.383 |
Neg logit contributions | |
ippi | -0.465 |
nton | -0.459 |
Beir | -0.458 |
lished | -0.430 |
spons | -0.428 |
Token | ` |
Token ID | 63 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
ILCS | +4.561 |
機 | +3.624 |
ñ | +3.544 |
(_ | +3.534 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.485 |
Neg logit contributions | |
Beir | -3.767 |
nton | -3.644 |
ippi | -3.541 |
spons | -3.512 |
lished | -3.455 |
Token | i |
Token ID | 72 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ILCS | +2.092 |
機 | +1.656 |
(_ | +1.634 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.597 |
belts | +1.580 |
Neg logit contributions | |
Beir | -2.014 |
ippi | -1.961 |
nton | -1.939 |
spons | -1.864 |
Gad | -1.859 |
Token | ` |
Token ID | 63 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
ILCS | +2.406 |
機 | +1.951 |
(_ | +1.897 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.877 |
belts | +1.850 |
Neg logit contributions | |
Beir | -1.805 |
ippi | -1.783 |
nton | -1.774 |
spons | -1.683 |
lished | -1.657 |
Token | s |
Token ID | 82 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ILCS | +1.710 |
機 | +1.384 |
(_ | +1.358 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.332 |
belts | +1.328 |
Neg logit contributions | |
Beir | -1.544 |
ippi | -1.500 |
nton | -1.477 |
Gad | -1.424 |
lished | -1.420 |
Token | utilities |
Token ID | 20081 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ILCS | +1.066 |
機 | +0.842 |
(_ | +0.811 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.808 |
belts | +0.803 |
Neg logit contributions | |
Beir | -0.993 |
ippi | -0.992 |
nton | -0.980 |
lished | -0.927 |
spons | -0.919 |
Token | over |
Token ID | 625 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ILCS | +0.814 |
機 | +0.651 |
(_ | +0.634 |
belts | +0.627 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.626 |
Neg logit contributions | |
Beir | -0.757 |
ippi | -0.756 |
nton | -0.749 |
Gad | -0.704 |
Sas | -0.701 |
Token | She |
Token ID | 1375 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
ippi | +1.275 |
Beir | +1.271 |
nton | +1.263 |
Gad | +1.190 |
Sas | +1.189 |
Neg logit contributions | |
ILCS | -1.551 |
機 | -1.265 |
(_ | -1.211 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.210 |
belts | -1.181 |
Token | arer |
Token ID | 11258 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ILCS | +0.134 |
機 | +0.114 |
(_ | +0.111 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.110 |
belts | +0.109 |
Neg logit contributions | |
ippi | -0.058 |
Beir | -0.058 |
nton | -0.056 |
Gad | -0.052 |
Sas | -0.052 |
Token | or |
Token ID | 393 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ILCS | +0.372 |
機 | +0.304 |
(_ | +0.293 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.292 |
belts | +0.288 |
Neg logit contributions | |
ippi | -0.286 |
Beir | -0.286 |
nton | -0.283 |
Gad | -0.267 |
Sas | -0.265 |
Token | Carlos |
Token ID | 17409 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ILCS | +1.125 |
機 | +0.899 |
(_ | +0.881 |
belts | +0.868 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.864 |
Neg logit contributions | |
ippi | -0.928 |
Beir | -0.918 |
nton | -0.915 |
Wonders | -0.852 |
spons | -0.849 |
Token | Te |
Token ID | 1665 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
ILCS | +0.214 |
機 | +0.168 |
(_ | +0.164 |
belts | +0.162 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.161 |
Neg logit contributions | |
ippi | -0.211 |
nton | -0.210 |
Beir | -0.208 |
spons | -0.197 |
Gad | -0.196 |
Token | vez |
Token ID | 33425 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
ILCS | +3.975 |
ñ | +3.112 |
umann | +3.068 |
belts | +2.839 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.821 |
Neg logit contributions | |
Beir | -4.268 |
spons | -4.207 |
lished | -4.134 |
ippi | -4.078 |
nton | -4.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ippi | +0.194 |
Beir | +0.194 |
nton | +0.192 |
Gad | +0.181 |
Sas | +0.181 |
Neg logit contributions | |
ILCS | -0.222 |
機 | -0.180 |
(_ | -0.172 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.172 |
belts | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ILCS | +0.844 |
機 | +0.673 |
(_ | +0.660 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.653 |
Send | +0.643 |
Neg logit contributions | |
ippi | -0.677 |
nton | -0.669 |
Beir | -0.664 |
spons | -0.642 |
lished | -0.630 |
Token |
|
Token ID | 198 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
ILCS | +0.015 |
機 | +0.013 |
(_ | +0.012 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.012 |
Send | +0.012 |
Neg logit contributions | |
Beir | -0.011 |
ippi | -0.011 |
nton | -0.010 |
spons | -0.010 |
lished | -0.010 |
Token | On |
Token ID | 2202 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
ILCS | +0.019 |
機 | +0.015 |
(_ | +0.015 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.015 |
Send | +0.014 |
Neg logit contributions | |
Beir | -0.020 |
ippi | -0.020 |
nton | -0.020 |
Gad | -0.019 |
spons | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ippi | +0.592 |
nton | +0.586 |
Beir | +0.584 |
spons | +0.555 |
Gad | +0.543 |
Neg logit contributions | |
ILCS | -0.679 |
機 | -0.546 |
(_ | -0.526 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.526 |
belts | -0.512 |
Token | are |
Token ID | 389 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
ILCS | +0.723 |
機 | +0.589 |
belts | +0.580 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.578 |
(_ | +0.577 |
Neg logit contributions | |
ippi | -0.556 |
Beir | -0.551 |
nton | -0.548 |
lished | -0.520 |
Gad | -0.512 |
Token | attacked |
Token ID | 7384 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
ILCS | +0.608 |
機 | +0.494 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.480 |
(_ | +0.480 |
belts | +0.476 |
Neg logit contributions | |
ippi | -0.493 |
Beir | -0.482 |
nton | -0.481 |
lished | -0.448 |
spons | -0.447 |
Token | by |
Token ID | 416 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ippi | +0.138 |
Beir | +0.137 |
nton | +0.136 |
Gad | +0.128 |
Sas | +0.127 |
Neg logit contributions | |
ILCS | -0.161 |
機 | -0.130 |
(_ | -0.126 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.126 |
belts | -0.124 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ILCS | +1.022 |
機 | +0.834 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.808 |
(_ | +0.808 |
belts | +0.800 |
Neg logit contributions | |
ippi | -0.848 |
nton | -0.837 |
Beir | -0.826 |
lished | -0.775 |
spons | -0.774 |
Token | Wat |
Token ID | 12242 |
Feature activation | -7.57e+00 |
Pos logit contributions | |
ippi | +0.071 |
nton | +0.070 |
Beir | +0.070 |
spons | +0.065 |
lished | +0.065 |
Neg logit contributions | |
ILCS | -0.095 |
機 | -0.078 |
(_ | -0.076 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.075 |
belts | -0.074 |
Token | cher |
Token ID | 2044 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
nton | +6.078 |
Beir | +6.033 |
ippi | +6.025 |
Gad | +5.812 |
Sas | +5.702 |
Neg logit contributions | |
ILCS | -4.670 |
機 | -3.662 |
ーテ | -3.419 |
(_ | -3.414 |
�� | -3.412 |
Token | in |
Token ID | 287 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ippi | +0.960 |
Beir | +0.959 |
nton | +0.949 |
Gad | +0.895 |
Sas | +0.892 |
Neg logit contributions | |
ILCS | -1.219 |
機 | -0.994 |
(_ | -0.957 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.953 |
belts | -0.939 |
Token | the |
Token ID | 262 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
ILCS | +0.790 |
機 | +0.639 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.619 |
(_ | +0.616 |
belts | +0.613 |
Neg logit contributions | |
ippi | -0.676 |
nton | -0.669 |
Beir | -0.666 |
spons | -0.624 |
Sas | -0.617 |
Token | Water |
Token ID | 5638 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ippi | +0.203 |
Beir | +0.201 |
nton | +0.201 |
spons | +0.186 |
lished | +0.185 |
Neg logit contributions | |
ILCS | -0.282 |
機 | -0.231 |
(_ | -0.224 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.224 |
belts | -0.223 |
Token | before |
Token ID | 878 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
ippi | +0.686 |
Beir | +0.681 |
nton | +0.677 |
spons | +0.635 |
Sas | +0.634 |
Neg logit contributions | |
ILCS | -0.852 |
機 | -0.688 |
(_ | -0.666 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.663 |
belts | -0.656 |
Token | erville |
Token ID | 33487 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
ippi | +3.726 |
nton | +3.704 |
Beir | +3.674 |
Sas | +3.450 |
Gad | +3.432 |
Neg logit contributions | |
ILCS | -4.681 |
機 | -3.833 |
(_ | -3.669 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.650 |
belts | -3.594 |
Token | Hotel |
Token ID | 12696 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Beir | +0.342 |
ippi | +0.342 |
nton | +0.338 |
Gad | +0.317 |
spons | +0.315 |
Neg logit contributions | |
ILCS | -0.444 |
機 | -0.362 |
(_ | -0.350 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.348 |
belts | -0.345 |
Token | ( |
Token ID | 357 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
ippi | +0.606 |
Beir | +0.605 |
nton | +0.599 |
Gad | +0.566 |
Sas | +0.564 |
Neg logit contributions | |
ILCS | -0.704 |
機 | -0.569 |
(_ | -0.547 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.544 |
belts | -0.536 |
Token | now |
Token ID | 2197 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ippi | +0.435 |
Beir | +0.435 |
nton | +0.430 |
Gad | +0.405 |
Sas | +0.403 |
Neg logit contributions | |
ILCS | -0.573 |
機 | -0.468 |
(_ | -0.452 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.449 |
belts | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ILCS | +2.125 |
機 | +1.745 |
(_ | +1.677 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.675 |
belts | +1.654 |
Neg logit contributions | |
ippi | -1.741 |
Beir | -1.721 |
nton | -1.715 |
Gad | -1.591 |
spons | -1.587 |
Token | Wat |
Token ID | 12242 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
ippi | +0.150 |
Beir | +0.150 |
nton | +0.149 |
Gad | +0.139 |
Sas | +0.138 |
Neg logit contributions | |
ILCS | -0.208 |
機 | -0.170 |
(_ | -0.164 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.164 |
belts | -0.162 |
Token | erville |
Token ID | 33487 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ippi | +4.023 |
nton | +3.967 |
Beir | +3.882 |
Gad | +3.564 |
Sas | +3.562 |
Neg logit contributions | |
ILCS | -5.470 |
機 | -4.580 |
(_ | -4.339 |
ーテ | -4.314 |
belts | -4.314 |
Token | Tavern |
Token ID | 32693 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
ippi | +1.141 |
Beir | +1.140 |
nton | +1.128 |
Gad | +1.059 |
Sas | +1.056 |
Neg logit contributions | |
ILCS | -1.576 |
機 | -1.295 |
(_ | -1.250 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.244 |
belts | -1.227 |
Token | ) |
Token ID | 8 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ippi | +1.193 |
Beir | +1.189 |
nton | +1.180 |
Gad | +1.110 |
Sas | +1.107 |
Neg logit contributions | |
ILCS | -1.607 |
機 | -1.317 |
(_ | -1.268 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.263 |
belts | -1.244 |
Token | that |
Token ID | 326 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
ippi | +1.234 |
Beir | +1.233 |
nton | +1.221 |
Gad | +1.154 |
Sas | +1.152 |
Neg logit contributions | |
ILCS | -1.458 |
機 | -1.179 |
(_ | -1.133 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.127 |
belts | -1.109 |
Token | had |
Token ID | 550 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ILCS | +0.428 |
機 | +0.351 |
(_ | +0.341 |
belts | +0.339 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.338 |
Neg logit contributions | |
ippi | -0.330 |
Beir | -0.326 |
nton | -0.325 |
Gad | -0.302 |
Sas | -0.300 |
Token | - |
Token ID | 12 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ILCS | +1.302 |
機 | +1.032 |
(_ | +1.025 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.007 |
Send | +0.984 |
Neg logit contributions | |
ippi | -1.243 |
Beir | -1.239 |
nton | -1.209 |
spons | -1.201 |
lished | -1.180 |
Token | 08 |
Token ID | 2919 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
ILCS | +1.172 |
機 | +0.959 |
(_ | +0.927 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.919 |
Send | +0.913 |
Neg logit contributions | |
Beir | -0.974 |
ippi | -0.966 |
nton | -0.954 |
spons | -0.908 |
Gad | -0.900 |
Token | Election |
Token ID | 14219 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
Beir | +0.345 |
ippi | +0.345 |
nton | +0.341 |
Gad | +0.320 |
spons | +0.319 |
Neg logit contributions | |
ILCS | -0.450 |
機 | -0.366 |
(_ | -0.354 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.353 |
belts | -0.347 |
Token | - |
Token ID | 12 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ILCS | +0.692 |
機 | +0.565 |
(_ | +0.548 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.544 |
belts | +0.537 |
Neg logit contributions | |
ippi | -0.515 |
Beir | -0.515 |
nton | -0.509 |
Gad | -0.477 |
Sas | -0.476 |
Token | D |
Token ID | 35 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ILCS | +0.640 |
機 | +0.518 |
(_ | +0.501 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.497 |
Send | +0.489 |
Neg logit contributions | |
Beir | -0.556 |
ippi | -0.553 |
nton | -0.546 |
spons | -0.517 |
Gad | -0.516 |
Token | anger |
Token ID | 2564 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
ILCS | +0.161 |
機 | +0.131 |
(_ | +0.128 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.126 |
belts | +0.125 |
Neg logit contributions | |
Beir | -0.118 |
ippi | -0.117 |
nton | -0.116 |
Sas | -0.109 |
Gad | -0.108 |
Token | ous |
Token ID | 516 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
nton | +3.063 |
ippi | +3.018 |
Beir | +3.003 |
Gad | +2.819 |
Sas | +2.805 |
Neg logit contributions | |
ILCS | -6.073 |
機 | -5.166 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.944 |
(_ | -4.909 |
ーテ | -4.814 |
Token | Vac |
Token ID | 25709 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Beir | +0.229 |
ippi | +0.229 |
nton | +0.227 |
spons | +0.212 |
Gad | +0.212 |
Neg logit contributions | |
ILCS | -0.322 |
機 | -0.264 |
(_ | -0.257 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.255 |
belts | -0.252 |
Token | ations |
Token ID | 602 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
ILCS | +2.760 |
機 | +2.345 |
(_ | +2.300 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.281 |
belts | +2.257 |
Neg logit contributions | |
Beir | -1.195 |
ippi | -1.189 |
nton | -1.167 |
Gad | -1.068 |
spons | -1.067 |
Token | - |
Token ID | 12 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ILCS | +0.529 |
機 | +0.432 |
(_ | +0.416 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.414 |
belts | +0.408 |
Neg logit contributions | |
ippi | -0.409 |
Beir | -0.409 |
nton | -0.404 |
Gad | -0.381 |
Sas | -0.380 |
Token | Who |
Token ID | 8241 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
ILCS | +0.949 |
機 | +0.770 |
(_ | +0.747 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.739 |
Send | +0.732 |
Neg logit contributions | |
Beir | -0.828 |
ippi | -0.821 |
nton | -0.812 |
spons | -0.773 |
Gad | -0.766 |
Token | s |
Token ID | 82 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
ILCS | +0.337 |
機 | +0.273 |
(_ | +0.265 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.263 |
belts | +0.258 |
Neg logit contributions | |
Beir | -0.279 |
ippi | -0.278 |
nton | -0.274 |
Gad | -0.259 |
Sas | -0.258 |
Token | greatness |
Token ID | 27951 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ippi | +0.086 |
Beir | +0.086 |
nton | +0.085 |
Gad | +0.080 |
lished | +0.079 |
Neg logit contributions | |
ILCS | -0.092 |
機 | -0.074 |
(_ | -0.071 |
belts | -0.071 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ippi | +1.012 |
Beir | +1.012 |
nton | +1.005 |
Sas | +0.947 |
Gad | +0.946 |
Neg logit contributions | |
ILCS | -1.207 |
機 | -0.984 |
(_ | -0.939 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.935 |
belts | -0.920 |
Token | secure |
Token ID | 5713 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ippi | +0.464 |
Beir | +0.463 |
nton | +0.459 |
Gad | +0.433 |
Sas | +0.432 |
Neg logit contributions | |
ILCS | -0.507 |
機 | -0.407 |
(_ | -0.391 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.389 |
belts | -0.384 |
Token | his |
Token ID | 465 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
ILCS | +0.304 |
機 | +0.242 |
(_ | +0.234 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.232 |
belts | +0.230 |
Neg logit contributions | |
ippi | -0.290 |
Beir | -0.289 |
nton | -0.287 |
Gad | -0.270 |
Sas | -0.269 |
Token | rule |
Token ID | 3896 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
ippi | +0.303 |
Beir | +0.302 |
nton | +0.299 |
Gad | +0.282 |
Sas | +0.281 |
Neg logit contributions | |
ILCS | -0.334 |
機 | -0.268 |
(_ | -0.259 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.258 |
belts | -0.255 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
nton | +3.779 |
Beir | +3.735 |
ippi | +3.718 |
Sas | +3.610 |
Gad | +3.525 |
Neg logit contributions | |
ILCS | -5.018 |
機 | -4.198 |
(_ | -3.885 |
Send | -3.864 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.849 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
ILCS | +0.085 |
機 | +0.068 |
(_ | +0.066 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.065 |
Send | +0.064 |
Neg logit contributions | |
ippi | -0.073 |
nton | -0.072 |
Beir | -0.072 |
spons | -0.069 |
lished | -0.067 |
Token | their |
Token ID | 511 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ILCS | +0.027 |
機 | +0.021 |
(_ | +0.021 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.020 |
belts | +0.020 |
Neg logit contributions | |
ippi | -0.025 |
Beir | -0.025 |
nton | -0.025 |
Gad | -0.023 |
Sas | -0.023 |
Token | calls |
Token ID | 3848 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
ILCS | +1.164 |
機 | +0.926 |
(_ | +0.893 |
belts | +0.892 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.891 |
Neg logit contributions | |
ippi | -1.133 |
Beir | -1.124 |
nton | -1.117 |
lished | -1.053 |
Gad | -1.045 |
Token | will |
Token ID | 481 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ILCS | +0.390 |
機 | +0.316 |
(_ | +0.306 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.303 |
belts | +0.301 |
Neg logit contributions | |
Beir | -0.334 |
ippi | -0.333 |
nton | -0.331 |
Gad | -0.314 |
Sas | -0.311 |
Token | Car |
Token ID | 1879 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Beir | +1.356 |
ippi | +1.351 |
nton | +1.337 |
Gad | +1.258 |
Sas | +1.254 |
Neg logit contributions | |
ILCS | -2.045 |
機 | -1.695 |
(_ | -1.634 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.629 |
belts | -1.609 |
Token | rick |
Token ID | 5557 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ILCS | +0.874 |
機 | +0.719 |
(_ | +0.700 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.698 |
belts | +0.684 |
Neg logit contributions | |
Beir | -0.618 |
ippi | -0.608 |
nton | -0.596 |
Gad | -0.570 |
Sas | -0.565 |
Token | (@ |
Token ID | 4275 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
ILCS | +0.487 |
機 | +0.390 |
(_ | +0.374 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.372 |
belts | +0.366 |
Neg logit contributions | |
ippi | -0.455 |
Beir | -0.454 |
nton | -0.450 |
Gad | -0.427 |
Sas | -0.425 |
Token | andy |
Token ID | 10757 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Beir | +0.045 |
ippi | +0.045 |
nton | +0.044 |
Gad | +0.042 |
Sas | +0.042 |
Neg logit contributions | |
ILCS | -0.052 |
機 | -0.042 |
(_ | -0.040 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.040 |
belts | -0.039 |
Token | f |
Token ID | 69 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
ippi | +1.791 |
nton | +1.777 |
Beir | +1.772 |
Gad | +1.659 |
Sas | +1.655 |
Neg logit contributions | |
ILCS | -1.947 |
機 | -1.570 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.501 |
(_ | -1.495 |
ÃÂ | -1.469 |
Token | erv |
Token ID | 712 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
ILCS | +0.171 |
機 | +0.139 |
(_ | +0.134 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.133 |
belts | +0.131 |
Neg logit contributions | |
Beir | -0.137 |
ippi | -0.137 |
nton | -0.135 |
Gad | -0.128 |
Sas | -0.128 |
Token | s |
Token ID | 82 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ippi | +4.413 |
nton | +4.372 |
Beir | +4.347 |
Sas | +4.086 |
Gad | +4.080 |
Neg logit contributions | |
ILCS | -4.535 |
機 | -3.621 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.460 |
ーテ | -3.434 |
(_ | -3.430 |
Token | ) |
Token ID | 8 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
ippi | +0.593 |
Beir | +0.591 |
nton | +0.585 |
Gad | +0.545 |
Sas | +0.544 |
Neg logit contributions | |
ILCS | -0.923 |
機 | -0.767 |
(_ | -0.741 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.739 |
belts | -0.729 |
Token | September |
Token ID | 2693 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
ippi | +1.546 |
Beir | +1.542 |
nton | +1.522 |
Gad | +1.412 |
Sas | +1.407 |
Neg logit contributions | |
ILCS | -2.636 |
機 | -2.200 |
(_ | -2.133 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.126 |
belts | -2.092 |
Token | 27 |
Token ID | 2681 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ILCS | +0.405 |
機 | +0.334 |
(_ | +0.324 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.322 |
belts | +0.316 |
Neg logit contributions | |
ippi | -0.283 |
Beir | -0.281 |
nton | -0.278 |
spons | -0.259 |
Gad | -0.259 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ILCS | +0.665 |
機 | +0.530 |
(_ | +0.526 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.513 |
Send | +0.507 |
Neg logit contributions | |
Beir | -0.598 |
ippi | -0.597 |
nton | -0.578 |
spons | -0.574 |
lished | -0.559 |
Token | Williams |
Token ID | 6484 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
ippi | +0.048 |
Beir | +0.048 |
nton | +0.048 |
Gad | +0.045 |
Sas | +0.045 |
Neg logit contributions | |
ILCS | -0.062 |
機 | -0.050 |
(_ | -0.048 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.048 |
belts | -0.047 |
Token | ; |
Token ID | 26 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ippi | +0.177 |
Beir | +0.177 |
nton | +0.175 |
Gad | +0.166 |
Sas | +0.165 |
Neg logit contributions | |
ILCS | -0.214 |
機 | -0.174 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.166 |
(_ | -0.166 |
belts | -0.163 |
Token | but |
Token ID | 475 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
ILCS | +1.914 |
機 | +1.530 |
(_ | +1.489 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.480 |
belts | +1.476 |
Neg logit contributions | |
ippi | -1.655 |
Beir | -1.654 |
nton | -1.634 |
lished | -1.521 |
spons | -1.517 |
Token | Diana |
Token ID | 25752 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
ILCS | +0.662 |
機 | +0.526 |
(_ | +0.513 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.509 |
belts | +0.508 |
Neg logit contributions | |
ippi | -0.588 |
Beir | -0.585 |
nton | -0.580 |
Gad | -0.540 |
spons | -0.539 |
Token | 's |
Token ID | 338 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Beir | +1.494 |
ippi | +1.492 |
nton | +1.479 |
Gad | +1.393 |
Sas | +1.387 |
Neg logit contributions | |
ILCS | -2.059 |
機 | -1.692 |
(_ | -1.630 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.625 |
belts | -1.596 |
Token | reck |
Token ID | 12482 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
ippi | +0.748 |
Beir | +0.748 |
nton | +0.739 |
Gad | +0.696 |
Sas | +0.694 |
Neg logit contributions | |
ILCS | -0.862 |
機 | -0.693 |
(_ | -0.669 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.665 |
belts | -0.658 |
Token | lessness |
Token ID | 17587 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ippi | +3.340 |
nton | +3.297 |
Beir | +3.214 |
spons | +3.022 |
Sas | +3.019 |
Neg logit contributions | |
ILCS | -5.485 |
機 | -4.593 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.439 |
(_ | -4.387 |
ーテ | -4.363 |
Token | is |
Token ID | 318 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
ippi | +1.641 |
Beir | +1.641 |
nton | +1.625 |
Gad | +1.528 |
Sas | +1.524 |
Neg logit contributions | |
ILCS | -2.290 |
機 | -1.883 |
(_ | -1.813 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.810 |
belts | -1.770 |
Token | a |
Token ID | 257 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ippi | +0.385 |
Beir | +0.384 |
nton | +0.380 |
Gad | +0.358 |
Sas | +0.356 |
Neg logit contributions | |
ILCS | -0.439 |
機 | -0.354 |
(_ | -0.341 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.339 |
belts | -0.336 |
Token | perfect |
Token ID | 2818 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ippi | +0.711 |
Beir | +0.710 |
nton | +0.703 |
Gad | +0.662 |
Sas | +0.660 |
Neg logit contributions | |
ILCS | -0.812 |
機 | -0.655 |
(_ | -0.630 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.628 |
belts | -0.617 |
Token | match |
Token ID | 2872 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
Beir | +0.133 |
ippi | +0.133 |
nton | +0.132 |
Gad | +0.125 |
Sas | +0.125 |
Neg logit contributions | |
ILCS | -0.132 |
機 | -0.104 |
(_ | -0.100 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.099 |
belts | -0.098 |
Token | sensitivity |
Token ID | 14233 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
ILCS | +1.421 |
機 | +1.096 |
(_ | +1.047 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.037 |
belts | +1.021 |
Neg logit contributions | |
ippi | -1.831 |
Beir | -1.828 |
nton | -1.808 |
Gad | -1.712 |
Wonders | -1.709 |
Token | are |
Token ID | 389 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
ippi | +0.365 |
Beir | +0.362 |
nton | +0.360 |
Sas | +0.334 |
Gad | +0.333 |
Neg logit contributions | |
ILCS | -0.495 |
機 | -0.406 |
(_ | -0.395 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.389 |
belts | -0.386 |
Token | known |
Token ID | 1900 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ippi | +0.674 |
Beir | +0.671 |
nton | +0.666 |
Gad | +0.626 |
Sas | +0.625 |
Neg logit contributions | |
ILCS | -0.758 |
機 | -0.613 |
(_ | -0.590 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.584 |
belts | -0.578 |
Token | ( |
Token ID | 357 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
ILCS | +0.543 |
機 | +0.438 |
(_ | +0.421 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.416 |
belts | +0.410 |
Neg logit contributions | |
Beir | -0.506 |
ippi | -0.506 |
nton | -0.501 |
Sas | -0.471 |
Gad | -0.471 |
Token | E |
Token ID | 36 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ippi | +1.057 |
Beir | +1.056 |
nton | +1.046 |
Gad | +0.983 |
Sas | +0.979 |
Neg logit contributions | |
ILCS | -1.457 |
機 | -1.195 |
(_ | -1.153 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.149 |
belts | -1.134 |
Token | qs |
Token ID | 48382 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
ippi | +0.723 |
Beir | +0.720 |
nton | +0.714 |
Gad | +0.662 |
Sas | +0.658 |
Neg logit contributions | |
ILCS | -1.308 |
機 | -1.098 |
(_ | -1.062 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.060 |
belts | -1.048 |
Token | . |
Token ID | 13 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
ippi | +3.539 |
Beir | +3.534 |
nton | +3.459 |
Sas | +3.331 |
Gad | +3.280 |
Neg logit contributions | |
ILCS | -4.803 |
機 | -3.993 |
belts | -3.850 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.847 |
ーテ | -3.821 |
Token | 2 |
Token ID | 362 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ippi | +0.456 |
Beir | +0.456 |
nton | +0.451 |
Gad | +0.421 |
Sas | +0.419 |
Neg logit contributions | |
ILCS | -0.664 |
機 | -0.547 |
(_ | -0.530 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.527 |
belts | -0.519 |
Token | - |
Token ID | 12 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
ippi | +0.630 |
Beir | +0.629 |
nton | +0.622 |
Gad | +0.583 |
Sas | +0.581 |
Neg logit contributions | |
ILCS | -0.912 |
機 | -0.753 |
(_ | -0.727 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.724 |
belts | -0.714 |
Token | 3 |
Token ID | 18 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
ILCS | +0.025 |
機 | +0.020 |
(_ | +0.020 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.020 |
belts | +0.019 |
Neg logit contributions | |
ippi | -0.017 |
Beir | -0.017 |
nton | -0.017 |
Sas | -0.016 |
Gad | -0.016 |
Token | ). |
Token ID | 737 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
ippi | +0.591 |
Beir | +0.591 |
nton | +0.584 |
Gad | +0.548 |
Sas | +0.547 |
Neg logit contributions | |
ILCS | -0.820 |
機 | -0.674 |
(_ | -0.651 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.648 |
belts | -0.639 |
Token | map |
Token ID | 8899 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
ILCS | +0.806 |
機 | +0.581 |
(_ | +0.556 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.544 |
Send | +0.536 |
Neg logit contributions | |
Beir | -1.301 |
ippi | -1.297 |
nton | -1.284 |
Sas | -1.231 |
Gad | -1.231 |
Token | $ |
Token ID | 720 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ippi | +0.068 |
Beir | +0.068 |
nton | +0.067 |
spons | +0.063 |
Gad | +0.063 |
Neg logit contributions | |
ILCS | -0.087 |
機 | -0.071 |
(_ | -0.070 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.068 |
belts | -0.068 |
Token | b |
Token ID | 65 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
Beir | +0.305 |
ippi | +0.303 |
nton | +0.299 |
Gad | +0.284 |
Sas | +0.284 |
Neg logit contributions | |
ILCS | -0.364 |
機 | -0.294 |
(_ | -0.286 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.283 |
belts | -0.277 |
Token | mp |
Token ID | 3149 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
Beir | +0.606 |
ippi | +0.570 |
nton | +0.564 |
Sas | +0.553 |
Wonders | +0.549 |
Neg logit contributions | |
ILCS | -0.832 |
(_ | -0.673 |
機 | -0.669 |
Send | -0.650 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.647 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ippi | +1.592 |
Beir | +1.577 |
nton | +1.570 |
Gad | +1.482 |
Sas | +1.470 |
Neg logit contributions | |
ILCS | -2.221 |
機 | -1.832 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.757 |
(_ | -1.739 |
belts | -1.737 |
Token | Save |
Token ID | 16928 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
ippi | +0.801 |
Beir | +0.800 |
nton | +0.791 |
Gad | +0.738 |
Sas | +0.736 |
Neg logit contributions | |
ILCS | -1.281 |
機 | -1.065 |
(_ | -1.030 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.026 |
belts | -1.013 |
Token | ($ |
Token ID | 16763 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ippi | +4.465 |
Beir | +4.418 |
nton | +4.411 |
Gad | +4.222 |
Sas | +4.200 |
Neg logit contributions | |
ILCS | -3.912 |
機 | -3.068 |
belts | -2.846 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.840 |
ÃÂ | -2.836 |
Token | Out |
Token ID | 7975 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ippi | +1.216 |
Beir | +1.215 |
nton | +1.203 |
Gad | +1.132 |
Sas | +1.129 |
Neg logit contributions | |
ILCS | -1.567 |
機 | -1.279 |
(_ | -1.232 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.227 |
belts | -1.209 |
Token | File |
Token ID | 8979 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
ippi | +1.940 |
Beir | +1.927 |
nton | +1.915 |
Gad | +1.792 |
Sas | +1.787 |
Neg logit contributions | |
ILCS | -2.644 |
機 | -2.172 |
(_ | -2.083 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.079 |
belts | -2.062 |
Token | , |
Token ID | 11 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
ippi | +2.406 |
Beir | +2.386 |
nton | +2.377 |
Gad | +2.222 |
Sas | +2.218 |
Neg logit contributions | |
ILCS | -3.411 |
機 | -2.823 |
belts | -2.688 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.679 |
(_ | -2.669 |
Token | [ |
Token ID | 685 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Beir | +0.489 |
ippi | +0.489 |
nton | +0.484 |
Gad | +0.455 |
Sas | +0.453 |
Neg logit contributions | |
ILCS | -0.637 |
機 | -0.519 |
(_ | -0.504 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.501 |
belts | -0.491 |
Token | kin |
Token ID | 5116 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ippi | +1.790 |
Beir | +1.783 |
nton | +1.774 |
Gad | +1.675 |
Sas | +1.667 |
Neg logit contributions | |
ILCS | -2.149 |
機 | -1.743 |
(_ | -1.667 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.662 |
belts | -1.638 |
Token | ? |
Token ID | 30 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
Beir | +0.078 |
ippi | +0.078 |
nton | +0.077 |
Gad | +0.073 |
Sas | +0.073 |
Neg logit contributions | |
ILCS | -0.095 |
機 | -0.077 |
(_ | -0.074 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.074 |
belts | -0.073 |
Token | who |
Token ID | 508 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
ippi | +0.459 |
Beir | +0.458 |
nton | +0.453 |
Gad | +0.425 |
Sas | +0.424 |
Neg logit contributions | |
ILCS | -0.653 |
機 | -0.538 |
(_ | -0.519 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.517 |
belts | -0.510 |
Token | would |
Token ID | 561 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Beir | +1.360 |
ippi | +1.359 |
nton | +1.354 |
Gad | +1.280 |
Sas | +1.277 |
Neg logit contributions | |
ILCS | -1.518 |
機 | -1.223 |
(_ | -1.168 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.167 |
belts | -1.136 |
Token | f |
Token ID | 277 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
ILCS | +0.823 |
機 | +0.659 |
(_ | +0.644 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.639 |
belts | +0.638 |
Neg logit contributions | |
ippi | -0.696 |
Beir | -0.691 |
nton | -0.678 |
Gad | -0.640 |
Sas | -0.637 |
Token | ard |
Token ID | 446 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
ILCS | +0.702 |
機 | +0.560 |
(_ | +0.556 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.544 |
Send | +0.536 |
Neg logit contributions | |
Beir | -0.580 |
ippi | -0.573 |
nton | -0.568 |
Gad | -0.538 |
Wonders | -0.535 |
Token | els |
Token ID | 1424 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
ippi | +3.754 |
Beir | +3.754 |
nton | +3.723 |
Gad | +3.525 |
Sas | +3.521 |
Neg logit contributions | |
ILCS | -4.642 |
機 | -3.824 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.568 |
ーテ | -3.534 |
(_ | -3.533 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
ippi | +0.586 |
Beir | +0.585 |
nton | +0.579 |
Gad | +0.548 |
Sas | +0.546 |
Neg logit contributions | |
ILCS | -0.695 |
機 | -0.563 |
(_ | -0.540 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.538 |
belts | -0.529 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ippi | +0.910 |
Beir | +0.908 |
nton | +0.902 |
Gad | +0.853 |
Sas | +0.849 |
Neg logit contributions | |
ILCS | -1.151 |
機 | -0.938 |
(_ | -0.897 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.894 |
belts | -0.876 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ILCS | +0.034 |
機 | +0.029 |
(_ | +0.028 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.027 |
belts | +0.027 |
Neg logit contributions | |
ippi | -0.019 |
Beir | -0.019 |
nton | -0.019 |
Gad | -0.018 |
Sas | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
ILCS | +1.333 |
(_ | +1.096 |
機 | +1.086 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.068 |
Send | +1.064 |
Neg logit contributions | |
Beir | -0.994 |
ippi | -0.990 |
nton | -0.958 |
spons | -0.953 |
lished | -0.933 |
Token | mountain |
Token ID | 8598 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
Beir | +0.141 |
ippi | +0.141 |
nton | +0.139 |
Gad | +0.131 |
Sas | +0.130 |
Neg logit contributions | |
ILCS | -0.189 |
機 | -0.155 |
(_ | -0.150 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.149 |
belts | -0.148 |
Token | overlook |
Token ID | 15677 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
ILCS | +0.401 |
機 | +0.324 |
(_ | +0.315 |
belts | +0.314 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.314 |
Neg logit contributions | |
ippi | -0.333 |
Beir | -0.330 |
nton | -0.327 |
Gad | -0.306 |
spons | -0.306 |
Token | area |
Token ID | 1989 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ippi | +0.445 |
Beir | +0.444 |
nton | +0.439 |
Gad | +0.415 |
Sas | +0.412 |
Neg logit contributions | |
ILCS | -0.537 |
機 | -0.435 |
(_ | -0.421 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.418 |
belts | -0.413 |
Token | for |
Token ID | 329 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
ILCS | +0.828 |
機 | +0.666 |
(_ | +0.651 |
belts | +0.639 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.637 |
Neg logit contributions | |
ippi | -0.718 |
Beir | -0.709 |
nton | -0.707 |
Gad | -0.666 |
spons | -0.662 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ippi | +0.359 |
Beir | +0.356 |
nton | +0.354 |
Gad | +0.331 |
spons | +0.330 |
Neg logit contributions | |
ILCS | -0.424 |
機 | -0.341 |
(_ | -0.330 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.329 |
belts | -0.326 |
Token | v |
Token ID | 410 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
ippi | +1.047 |
Beir | +1.045 |
nton | +1.035 |
Gad | +0.977 |
Sas | +0.974 |
Neg logit contributions | |
ILCS | -1.195 |
機 | -0.964 |
(_ | -0.926 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.923 |
belts | -0.908 |
Token | ista |
Token ID | 12523 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ippi | +3.047 |
Beir | +3.021 |
nton | +3.003 |
Sas | +2.797 |
Gad | +2.792 |
Neg logit contributions | |
ILCS | -5.375 |
機 | -4.532 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.360 |
(_ | -4.320 |
belts | -4.305 |
Token | camps |
Token ID | 11665 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ippi | +0.427 |
Beir | +0.425 |
nton | +0.421 |
Gad | +0.397 |
Sas | +0.394 |
Neg logit contributions | |
ILCS | -0.496 |
機 | -0.401 |
(_ | -0.388 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.385 |
belts | -0.379 |
Token | ite |
Token ID | 578 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Beir | +0.905 |
ippi | +0.902 |
nton | +0.898 |
Gad | +0.858 |
Sas | +0.854 |
Neg logit contributions | |
ILCS | -0.695 |
機 | -0.528 |
(_ | -0.504 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.500 |
belts | -0.489 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
ippi | +0.108 |
Beir | +0.107 |
nton | +0.106 |
Gad | +0.100 |
Sas | +0.100 |
Neg logit contributions | |
ILCS | -0.121 |
機 | -0.097 |
(_ | -0.094 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.094 |
belts | -0.092 |
Token | Great |
Token ID | 3878 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
ippi | +0.262 |
Beir | +0.260 |
nton | +0.259 |
spons | +0.242 |
Gad | +0.241 |
Neg logit contributions | |
ILCS | -0.345 |
機 | -0.282 |
(_ | -0.272 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.272 |
belts | -0.266 |
Token | ain |
Token ID | 391 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
Beir | +0.015 |
ippi | +0.015 |
nton | +0.014 |
spons | +0.014 |
lished | +0.014 |
Neg logit contributions | |
ILCS | -0.016 |
機 | -0.013 |
(_ | -0.013 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.012 |
belts | -0.012 |
Token | 's |
Token ID | 338 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
ippi | +0.031 |
Beir | +0.031 |
nton | +0.030 |
Gad | +0.028 |
Sas | +0.028 |
Neg logit contributions | |
ILCS | -0.041 |
機 | -0.034 |
(_ | -0.033 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.033 |
belts | -0.032 |
Token | model |
Token ID | 2746 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ippi | +0.491 |
Beir | +0.490 |
nton | +0.485 |
Gad | +0.458 |
Sas | +0.456 |
Neg logit contributions | |
ILCS | -0.559 |
機 | -0.450 |
(_ | -0.433 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.431 |
belts | -0.425 |
Token | of |
Token ID | 286 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ILCS | +0.091 |
機 | +0.074 |
(_ | +0.071 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.071 |
belts | +0.070 |
Neg logit contributions | |
Beir | -0.080 |
ippi | -0.080 |
nton | -0.079 |
Gad | -0.074 |
Sas | -0.074 |
Token | F |
Token ID | 376 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
ILCS | +0.158 |
機 | +0.127 |
(_ | +0.124 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.122 |
belts | +0.121 |
Neg logit contributions | |
Beir | -0.146 |
ippi | -0.146 |
nton | -0.144 |
Gad | -0.135 |
Sas | -0.134 |
Token | ender |
Token ID | 2194 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
ILCS | +0.991 |
機 | +0.815 |
(_ | +0.788 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.785 |
belts | +0.767 |
Neg logit contributions | |
Beir | -0.756 |
ippi | -0.743 |
nton | -0.739 |
Gad | -0.697 |
spons | -0.695 |
Token | Jaguar |
Token ID | 39288 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ippi | +3.546 |
Beir | +3.542 |
nton | +3.523 |
Gad | +3.364 |
Sas | +3.359 |
Neg logit contributions | |
ILCS | -4.866 |
機 | -3.943 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.781 |
(_ | -3.749 |
Send | -3.690 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ILCS | +0.107 |
機 | +0.088 |
(_ | +0.086 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.085 |
belts | +0.085 |
Neg logit contributions | |
Beir | -0.080 |
ippi | -0.080 |
nton | -0.079 |
Gad | -0.074 |
Wonders | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ILCS | +0.997 |
(_ | +0.819 |
機 | +0.818 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.794 |
Send | +0.789 |
Neg logit contributions | |
Beir | -0.751 |
ippi | -0.749 |
nton | -0.720 |
spons | -0.717 |
lished | -0.707 |
Token | C |
Token ID | 34 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ILCS | +0.804 |
機 | +0.658 |
(_ | +0.641 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.632 |
Send | +0.625 |
Neg logit contributions | |
Beir | -0.691 |
ippi | -0.683 |
nton | -0.671 |
spons | -0.639 |
Gad | -0.637 |
Token | ob |
Token ID | 672 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
ILCS | +0.498 |
機 | +0.394 |
(_ | +0.384 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.378 |
Send | +0.370 |
Neg logit contributions | |
Beir | -0.513 |
ippi | -0.502 |
nton | -0.498 |
Gad | -0.479 |
spons | -0.478 |
Token | headed |
Token ID | 9153 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ippi | +0.473 |
Beir | +0.472 |
nton | +0.469 |
Gad | +0.441 |
Sas | +0.438 |
Neg logit contributions | |
ILCS | -0.528 |
機 | -0.424 |
(_ | -0.409 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.406 |
belts | -0.402 |
Token | immediately |
Token ID | 3393 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
Beir | +1.391 |
ippi | +1.390 |
nton | +1.377 |
Sas | +1.308 |
Gad | +1.308 |
Neg logit contributions | |
ILCS | -1.394 |
機 | -1.109 |
(_ | -1.056 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.050 |
belts | -1.031 |
Token | for |
Token ID | 329 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILCS | +0.561 |
機 | +0.442 |
(_ | +0.427 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.423 |
belts | +0.418 |
Neg logit contributions | |
ippi | -0.564 |
Beir | -0.563 |
nton | -0.558 |
Gad | -0.530 |
Sas | -0.527 |
Token | the |
Token ID | 262 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ILCS | +0.991 |
機 | +0.796 |
(_ | +0.775 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.772 |
belts | +0.766 |
Neg logit contributions | |
ippi | -0.825 |
nton | -0.816 |
Beir | -0.816 |
Gad | -0.763 |
spons | -0.760 |
Token | former |
Token ID | 1966 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ippi | +0.213 |
Beir | +0.211 |
nton | +0.210 |
Gad | +0.197 |
spons | +0.195 |
Neg logit contributions | |
ILCS | -0.265 |
機 | -0.214 |
(_ | -0.208 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.207 |
belts | -0.206 |
Token | Wat |
Token ID | 12242 |
Feature activation | -5.83e+00 |
Pos logit contributions | |
ippi | +0.798 |
Beir | +0.795 |
nton | +0.788 |
Gad | +0.741 |
Sas | +0.737 |
Neg logit contributions | |
ILCS | -0.986 |
機 | -0.803 |
(_ | -0.774 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.769 |
belts | -0.760 |
Token | erville |
Token ID | 33487 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
ippi | +3.726 |
nton | +3.704 |
Beir | +3.674 |
Sas | +3.450 |
Gad | +3.432 |
Neg logit contributions | |
ILCS | -4.681 |
機 | -3.833 |
(_ | -3.669 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.650 |
belts | -3.594 |
Token | Hotel |
Token ID | 12696 |
Feature activation | -9.11e-01 |
Pos logit contributions | |
Beir | +0.342 |
ippi | +0.342 |
nton | +0.338 |
Gad | +0.317 |
spons | +0.315 |
Neg logit contributions | |
ILCS | -0.444 |
機 | -0.362 |
(_ | -0.350 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.348 |
belts | -0.345 |
Token | ( |
Token ID | 357 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
ippi | +0.606 |
Beir | +0.605 |
nton | +0.599 |
Gad | +0.566 |
Sas | +0.564 |
Neg logit contributions | |
ILCS | -0.704 |
機 | -0.569 |
(_ | -0.547 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.544 |
belts | -0.536 |
Token | now |
Token ID | 2197 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
ippi | +0.435 |
Beir | +0.435 |
nton | +0.430 |
Gad | +0.405 |
Sas | +0.403 |
Neg logit contributions | |
ILCS | -0.573 |
機 | -0.468 |
(_ | -0.452 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.449 |
belts | -0.443 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ILCS | +2.125 |
機 | +1.745 |
(_ | +1.677 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.675 |
belts | +1.654 |
Neg logit contributions | |
ippi | -1.741 |
Beir | -1.721 |
nton | -1.715 |
Gad | -1.591 |
spons | -1.587 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ILCS | +0.627 |
機 | +0.528 |
(_ | +0.512 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.510 |
belts | +0.504 |
Neg logit contributions | |
ippi | -0.327 |
Beir | -0.327 |
nton | -0.323 |
Gad | -0.298 |
Sas | -0.297 |
Token | Marc |
Token ID | 22697 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
ippi | +1.309 |
Beir | +1.298 |
nton | +1.296 |
Gad | +1.222 |
Sas | +1.218 |
Neg logit contributions | |
ILCS | -1.466 |
機 | -1.173 |
(_ | -1.122 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.122 |
belts | -1.113 |
Token | Dillon |
Token ID | 40057 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
ILCS | +0.316 |
機 | +0.261 |
(_ | +0.255 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.253 |
belts | +0.250 |
Neg logit contributions | |
ippi | -0.210 |
Beir | -0.207 |
nton | -0.206 |
spons | -0.195 |
lished | -0.189 |
Token | at |
Token ID | 379 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
ILCS | +0.680 |
機 | +0.558 |
(_ | +0.542 |
belts | +0.538 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.536 |
Neg logit contributions | |
ippi | -0.496 |
Beir | -0.493 |
nton | -0.490 |
spons | -0.455 |
Gad | -0.455 |
Token | M |
Token ID | 337 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ILCS | +0.275 |
機 | +0.225 |
(_ | +0.218 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.217 |
belts | +0.215 |
Neg logit contributions | |
ippi | -0.207 |
Beir | -0.206 |
nton | -0.205 |
spons | -0.190 |
Gad | -0.190 |
Token | WC |
Token ID | 27353 |
Feature activation | -5.79e+00 |
Pos logit contributions | |
ILCS | +0.209 |
機 | +0.172 |
(_ | +0.167 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.165 |
Send | +0.162 |
Neg logit contributions | |
Beir | -0.148 |
ippi | -0.146 |
nton | -0.145 |
Gad | -0.136 |
Sas | -0.136 |
Token | 2014 |
Token ID | 1946 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
Beir | +3.443 |
ippi | +3.424 |
nton | +3.375 |
Gad | +3.242 |
Sas | +3.235 |
Neg logit contributions | |
ILCS | -4.818 |
機 | -3.938 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.817 |
(_ | -3.787 |
ÃÂ | -3.739 |
Token | with |
Token ID | 351 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ILCS | +0.051 |
機 | +0.042 |
(_ | +0.041 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.040 |
belts | +0.040 |
Neg logit contributions | |
ippi | -0.038 |
Beir | -0.038 |
nton | -0.037 |
Gad | -0.035 |
Sas | -0.034 |
Token | Mak |
Token ID | 15841 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
ippi | +0.858 |
Beir | +0.857 |
nton | +0.848 |
Gad | +0.794 |
Sas | +0.791 |
Neg logit contributions | |
ILCS | -1.227 |
機 | -1.011 |
(_ | -0.976 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.972 |
belts | -0.960 |
Token | ia |
Token ID | 544 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Beir | +1.086 |
ippi | +1.086 |
nton | +1.074 |
Gad | +1.008 |
Sas | +1.003 |
Neg logit contributions | |
ILCS | -1.502 |
機 | -1.234 |
(_ | -1.193 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.187 |
belts | -1.170 |
Token | and |
Token ID | 290 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
ILCS | +1.631 |
機 | +1.352 |
(_ | +1.312 |
belts | +1.300 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.299 |
Neg logit contributions | |
ippi | -1.094 |
nton | -1.090 |
Beir | -1.081 |
spons | -1.010 |
lished | -0.997 |
Token | think |
Token ID | 892 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
ippi | +0.830 |
Beir | +0.829 |
nton | +0.824 |
Gad | +0.776 |
Sas | +0.774 |
Neg logit contributions | |
ILCS | -1.016 |
機 | -0.827 |
(_ | -0.793 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.790 |
belts | -0.776 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
ippi | +2.792 |
nton | +2.757 |
Beir | +2.744 |
Gad | +2.637 |
Sas | +2.626 |
Neg logit contributions | |
ILCS | -3.582 |
機 | -2.933 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.810 |
(_ | -2.805 |
ÃÂ | -2.760 |
Token | In |
Token ID | 554 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
ippi | +0.283 |
Beir | +0.281 |
nton | +0.280 |
spons | +0.267 |
lished | +0.259 |
Neg logit contributions | |
ILCS | -0.320 |
機 | -0.258 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.247 |
(_ | -0.246 |
belts | -0.243 |
Token | 1938 |
Token ID | 28017 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ippi | +0.497 |
Beir | +0.497 |
nton | +0.492 |
Gad | +0.464 |
Sas | +0.463 |
Neg logit contributions | |
ILCS | -0.560 |
機 | -0.452 |
(_ | -0.432 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.431 |
belts | -0.427 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
ILCS | +1.689 |
機 | +1.379 |
(_ | +1.318 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.310 |
belts | +1.309 |
Neg logit contributions | |
Beir | -1.389 |
ippi | -1.388 |
nton | -1.371 |
spons | -1.286 |
Sas | -1.275 |
Token | archae |
Token ID | 16713 |
Feature activation | -5.77e+00 |
Pos logit contributions | |
ILCS | +0.329 |
機 | +0.269 |
(_ | +0.258 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.257 |
belts | +0.256 |
Neg logit contributions | |
ippi | -0.258 |
Beir | -0.258 |
nton | -0.255 |
Gad | -0.238 |
Sas | -0.238 |
Token | ologist |
Token ID | 7451 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
ippi | +3.240 |
nton | +3.193 |
Beir | +3.171 |
Gad | +2.961 |
Wonders | +2.957 |
Neg logit contributions | |
ILCS | -5.077 |
機 | -4.181 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.034 |
(_ | -4.015 |
belts | -3.980 |
Token | Wilhelm |
Token ID | 50031 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
Beir | +1.643 |
ippi | +1.639 |
nton | +1.622 |
Gad | +1.527 |
Sas | +1.520 |
Neg logit contributions | |
ILCS | -2.689 |
機 | -2.249 |
(_ | -2.166 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.160 |
belts | -2.123 |
Token | Kon |
Token ID | 17431 |
Feature activation | -7.82e-01 |
Pos logit contributions | |
ippi | +0.177 |
Beir | +0.176 |
nton | +0.175 |
spons | +0.164 |
Gad | +0.161 |
Neg logit contributions | |
ILCS | -0.257 |
機 | -0.212 |
(_ | -0.205 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.204 |
belts | -0.202 |
Token | ig |
Token ID | 328 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Beir | +0.502 |
ippi | +0.501 |
nton | +0.496 |
Gad | +0.468 |
Sas | +0.465 |
Neg logit contributions | |
ILCS | -0.620 |
機 | -0.506 |
(_ | -0.487 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.484 |
belts | -0.478 |
Token | discovered |
Token ID | 5071 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
ILCS | +0.033 |
機 | +0.027 |
(_ | +0.026 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.026 |
belts | +0.026 |
Neg logit contributions | |
Beir | -0.023 |
ippi | -0.022 |
nton | -0.022 |
spons | -0.021 |
Gad | -0.021 |
Token | According |
Token ID | 4784 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
ILCS | +0.176 |
機 | +0.143 |
(_ | +0.139 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.138 |
belts | +0.135 |
Neg logit contributions | |
ippi | -0.144 |
nton | -0.142 |
Beir | -0.142 |
spons | -0.134 |
Gad | -0.131 |
Token | to |
Token ID | 284 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
ILCS | +0.390 |
機 | +0.314 |
(_ | +0.309 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.302 |
belts | +0.299 |
Neg logit contributions | |
ippi | -0.361 |
Beir | -0.357 |
nton | -0.351 |
spons | -0.337 |
lished | -0.337 |
Token | Mur |
Token ID | 5921 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
ILCS | +0.244 |
機 | +0.201 |
(_ | +0.195 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.193 |
belts | +0.191 |
Neg logit contributions | |
ippi | -0.191 |
Beir | -0.187 |
nton | -0.187 |
Wonders | -0.174 |
spons | -0.173 |
Token | ad |
Token ID | 324 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
ippi | +1.262 |
Beir | +1.260 |
nton | +1.243 |
Gad | +1.140 |
Sas | +1.135 |
Neg logit contributions | |
ILCS | -2.798 |
機 | -2.377 |
(_ | -2.309 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.301 |
belts | -2.275 |
Token | Do |
Token ID | 2141 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ILCS | +0.516 |
機 | +0.427 |
(_ | +0.415 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.413 |
belts | +0.408 |
Neg logit contributions | |
ippi | -0.340 |
nton | -0.335 |
Beir | -0.333 |
spons | -0.310 |
Wonders | -0.307 |
Token | ğ |
Token ID | 33133 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
ILCS | +1.161 |
機 | +0.971 |
(_ | +0.945 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.938 |
belts | +0.925 |
Neg logit contributions | |
Beir | -0.665 |
ippi | -0.658 |
nton | -0.651 |
Gad | -0.610 |
spons | -0.607 |
Token | uk |
Token ID | 2724 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
ippi | +2.358 |
Beir | +2.325 |
nton | +2.294 |
Sas | +2.113 |
Gad | +2.105 |
Neg logit contributions | |
ILCS | -5.810 |
機 | -4.933 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.816 |
(_ | -4.800 |
belts | -4.749 |
Token | an |
Token ID | 272 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
ippi | +0.338 |
Beir | +0.335 |
nton | +0.332 |
Gad | +0.313 |
Sas | +0.310 |
Neg logit contributions | |
ILCS | -0.440 |
機 | -0.360 |
(_ | -0.349 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.345 |
belts | -0.341 |
Token | li |
Token ID | 4528 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ILCS | +0.344 |
機 | +0.282 |
(_ | +0.273 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.270 |
belts | +0.266 |
Neg logit contributions | |
ippi | -0.276 |
Beir | -0.274 |
nton | -0.272 |
Gad | -0.255 |
spons | -0.255 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ILCS | +1.013 |
機 | +0.833 |
(_ | +0.805 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.793 |
belts | +0.780 |
Neg logit contributions | |
ippi | -0.836 |
Beir | -0.833 |
nton | -0.827 |
spons | -0.779 |
Gad | -0.779 |
Token | writing |
Token ID | 3597 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
ILCS | +1.017 |
機 | +0.839 |
(_ | +0.813 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.805 |
belts | +0.796 |
Neg logit contributions | |
ippi | -0.833 |
Beir | -0.816 |
nton | -0.815 |
Wonders | -0.761 |
Gad | -0.757 |
Token | Stein |
Token ID | 15215 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
ippi | +0.254 |
Beir | +0.254 |
nton | +0.251 |
Gad | +0.234 |
Sas | +0.233 |
Neg logit contributions | |
ILCS | -0.419 |
機 | -0.349 |
(_ | -0.338 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.337 |
belts | -0.332 |
Token | � |
Token ID | 8582 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
ippi | +0.456 |
Beir | +0.456 |
nton | +0.452 |
Gad | +0.429 |
Sas | +0.427 |
Neg logit contributions | |
ILCS | -0.518 |
機 | -0.416 |
(_ | -0.398 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.397 |
belts | -0.391 |
Token | � |
Token ID | 234 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
ILCS | +0.236 |
機 | +0.181 |
(_ | +0.172 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.171 |
belts | +0.167 |
Neg logit contributions | |
ippi | -0.294 |
Beir | -0.294 |
nton | -0.292 |
Gad | -0.278 |
Sas | -0.277 |
Token | � |
Token ID | 119 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ippi | +1.802 |
Beir | +1.795 |
nton | +1.787 |
Gad | +1.694 |
Sas | +1.689 |
Neg logit contributions | |
ILCS | -1.705 |
機 | -1.336 |
(_ | -1.280 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.266 |
belts | -1.260 |
Token | (@ |
Token ID | 4275 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ippi | +0.079 |
Beir | +0.079 |
nton | +0.078 |
Gad | +0.074 |
Sas | +0.074 |
Neg logit contributions | |
ILCS | -0.078 |
機 | -0.062 |
(_ | -0.059 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.059 |
belts | -0.058 |
Token | Dr |
Token ID | 6187 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
ippi | +1.194 |
Beir | +1.186 |
nton | +1.185 |
Gad | +1.120 |
Sas | +1.114 |
Neg logit contributions | |
ILCS | -1.192 |
機 | -0.943 |
(_ | -0.902 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.897 |
belts | -0.888 |
Token | J |
Token ID | 41 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
ippi | +3.761 |
nton | +3.711 |
Beir | +3.531 |
Gad | +3.441 |
spons | +3.428 |
Neg logit contributions | |
ILCS | -4.161 |
機 | -3.385 |
ÃÂ | -3.345 |
ーテ | -3.320 |
belts | -3.309 |
Token | ill |
Token ID | 359 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
ippi | +1.525 |
nton | +1.510 |
Beir | +1.504 |
Gad | +1.440 |
spons | +1.430 |
Neg logit contributions | |
ILCS | -1.116 |
機 | -0.842 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.795 |
(_ | -0.794 |
belts | -0.779 |
Token | Ste |
Token ID | 7447 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ippi | +0.508 |
Beir | +0.507 |
nton | +0.502 |
Gad | +0.472 |
Sas | +0.470 |
Neg logit contributions | |
ILCS | -0.690 |
機 | -0.566 |
(_ | -0.546 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.544 |
belts | -0.537 |
Token | in |
Token ID | 259 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Beir | +0.471 |
ippi | +0.463 |
nton | +0.448 |
Gad | +0.392 |
Sas | +0.390 |
Neg logit contributions | |
ILCS | -2.012 |
機 | -1.759 |
(_ | -1.720 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.712 |
belts | -1.694 |
Token | ) |
Token ID | 8 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
ippi | +0.648 |
Beir | +0.644 |
nton | +0.640 |
Gad | +0.592 |
Sas | +0.591 |
Neg logit contributions | |
ILCS | -1.105 |
機 | -0.921 |
(_ | -0.895 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.890 |
belts | -0.882 |
Token | has |
Token ID | 468 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
ippi | +0.286 |
Beir | +0.286 |
nton | +0.283 |
Gad | +0.265 |
Sas | +0.265 |
Neg logit contributions | |
ILCS | -0.368 |
機 | -0.301 |
(_ | -0.290 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.289 |
belts | -0.287 |
Token | been |
Token ID | 587 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
ippi | +0.149 |
Beir | +0.148 |
nton | +0.147 |
Gad | +0.137 |
Sas | +0.137 |
Neg logit contributions | |
ILCS | -0.188 |
機 | -0.154 |
(_ | -0.148 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.148 |
belts | -0.147 |
Token | stolen |
Token ID | 9909 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
ILCS | +0.007 |
機 | +0.006 |
(_ | +0.006 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.006 |
belts | +0.006 |
Neg logit contributions | |
ippi | -0.006 |
Beir | -0.006 |
nton | -0.006 |
Gad | -0.005 |
Sas | -0.005 |
Token | by |
Token ID | 416 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
ippi | +0.478 |
Beir | +0.477 |
nton | +0.472 |
Gad | +0.446 |
Sas | +0.444 |
Neg logit contributions | |
ILCS | -0.569 |
機 | -0.461 |
(_ | -0.443 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.441 |
belts | -0.434 |
Token | a |
Token ID | 257 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ILCS | +0.356 |
機 | +0.288 |
(_ | +0.280 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.280 |
belts | +0.275 |
Neg logit contributions | |
ippi | -0.293 |
Beir | -0.291 |
nton | -0.291 |
spons | -0.270 |
Gad | -0.269 |
Token | meddling |
Token ID | 33545 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
ippi | +0.183 |
Beir | +0.183 |
nton | +0.181 |
Gad | +0.170 |
Wonders | +0.169 |
Neg logit contributions | |
ILCS | -0.221 |
機 | -0.179 |
(_ | -0.173 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.173 |
belts | -0.169 |
Token | gang |
Token ID | 7706 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
Beir | +3.525 |
ippi | +3.500 |
nton | +3.458 |
Sas | +3.354 |
Gad | +3.337 |
Neg logit contributions | |
ILCS | -4.463 |
機 | -3.658 |
(_ | -3.491 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.462 |
belts | -3.436 |
Token | known |
Token ID | 1900 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
ippi | +0.177 |
Beir | +0.176 |
nton | +0.174 |
Gad | +0.165 |
Sas | +0.164 |
Neg logit contributions | |
ILCS | -0.196 |
機 | -0.157 |
(_ | -0.152 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.151 |
belts | -0.148 |
Token | as |
Token ID | 355 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ILCS | +2.128 |
機 | +1.702 |
(_ | +1.632 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.622 |
belts | +1.594 |
Neg logit contributions | |
Beir | -2.051 |
ippi | -2.051 |
nton | -2.033 |
Gad | -1.923 |
Sas | -1.919 |
Token | the |
Token ID | 262 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
ILCS | +0.856 |
機 | +0.693 |
(_ | +0.670 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.668 |
belts | +0.655 |
Neg logit contributions | |
ippi | -0.724 |
nton | -0.719 |
Beir | -0.718 |
Gad | -0.670 |
spons | -0.667 |
Token | Fi |
Token ID | 23238 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ILCS | +0.392 |
機 | +0.322 |
(_ | +0.312 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.311 |
belts | +0.306 |
Neg logit contributions | |
ippi | -0.283 |
Beir | -0.281 |
nton | -0.281 |
Gad | -0.261 |
spons | -0.260 |
Token | yet |
Token ID | 1865 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ippi | +0.539 |
Beir | +0.537 |
nton | +0.533 |
Gad | +0.501 |
Sas | +0.499 |
Neg logit contributions | |
ILCS | -0.646 |
機 | -0.522 |
(_ | -0.504 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.501 |
belts | -0.496 |
Token | authorized |
Token ID | 10435 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
ILCS | +1.252 |
機 | +1.010 |
(_ | +0.984 |
belts | +0.980 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.974 |
Neg logit contributions | |
ippi | -1.086 |
nton | -1.074 |
Beir | -1.063 |
Gad | -0.986 |
Sas | -0.985 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ippi | +0.529 |
Beir | +0.529 |
nton | +0.523 |
Gad | +0.495 |
Sas | +0.493 |
Neg logit contributions | |
ILCS | -0.621 |
機 | -0.502 |
(_ | -0.482 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.480 |
belts | -0.472 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ippi | +0.129 |
Beir | +0.128 |
nton | +0.128 |
spons | +0.120 |
Gad | +0.119 |
Neg logit contributions | |
ILCS | -0.169 |
機 | -0.138 |
(_ | -0.133 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.132 |
belts | -0.130 |
Token | My |
Token ID | 3666 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ippi | +1.590 |
Beir | +1.577 |
nton | +1.576 |
Gad | +1.486 |
Sas | +1.480 |
Neg logit contributions | |
ILCS | -1.771 |
機 | -1.415 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.352 |
(_ | -1.352 |
belts | -1.344 |
Token | side |
Token ID | 1735 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
ippi | +0.160 |
Beir | +0.160 |
nton | +0.158 |
Gad | +0.148 |
Sas | +0.148 |
Neg logit contributions | |
ILCS | -0.194 |
機 | -0.157 |
(_ | -0.151 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.151 |
belts | -0.149 |
Token | project |
Token ID | 1628 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
Beir | +3.403 |
ippi | +3.339 |
nton | +3.320 |
spons | +3.194 |
Sas | +3.163 |
Neg logit contributions | |
ILCS | -4.546 |
機 | -3.728 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.518 |
(_ | -3.504 |
ーテ | -3.499 |
Token | for |
Token ID | 329 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
ippi | +0.034 |
Beir | +0.034 |
nton | +0.034 |
Gad | +0.031 |
Sas | +0.031 |
Neg logit contributions | |
ILCS | -0.047 |
機 | -0.039 |
(_ | -0.038 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.037 |
belts | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ippi | +0.185 |
Beir | +0.184 |
nton | +0.183 |
Gad | +0.171 |
Sas | +0.171 |
Neg logit contributions | |
ILCS | -0.221 |
機 | -0.179 |
(_ | -0.174 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.173 |
belts | -0.171 |
Token | last |
Token ID | 938 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
ippi | +1.212 |
Beir | +1.211 |
nton | +1.199 |
Gad | +1.135 |
Sas | +1.132 |
Neg logit contributions | |
ILCS | -1.321 |
機 | -1.059 |
(_ | -1.016 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.011 |
belts | -0.995 |
Token | month |
Token ID | 1227 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
ippi | +0.547 |
Beir | +0.543 |
nton | +0.540 |
Gad | +0.507 |
Sas | +0.503 |
Neg logit contributions | |
ILCS | -0.645 |
機 | -0.523 |
(_ | -0.505 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.501 |
belts | -0.496 |
Token | mass |
Token ID | 2347 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ippi | +0.643 |
Beir | +0.643 |
nton | +0.637 |
Gad | +0.603 |
Sas | +0.602 |
Neg logit contributions | |
ILCS | -0.700 |
機 | -0.561 |
(_ | -0.538 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.535 |
belts | -0.527 |
Token | of |
Token ID | 286 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ILCS | +0.090 |
機 | +0.071 |
(_ | +0.068 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.068 |
belts | +0.067 |
Neg logit contributions | |
ippi | -0.090 |
Beir | -0.089 |
nton | -0.089 |
Gad | -0.084 |
Sas | -0.084 |
Token | lies |
Token ID | 7363 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ippi | +0.482 |
Beir | +0.481 |
nton | +0.477 |
Gad | +0.452 |
Sas | +0.451 |
Neg logit contributions | |
ILCS | -0.508 |
機 | -0.406 |
(_ | -0.389 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.387 |
belts | -0.381 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
Beir | +1.125 |
ippi | +1.124 |
nton | +1.114 |
Gad | +1.044 |
Sas | +1.044 |
Neg logit contributions | |
ILCS | -1.530 |
機 | -1.253 |
(_ | -1.207 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.200 |
belts | -1.185 |
Token | ev |
Token ID | 819 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ILCS | +0.018 |
機 | +0.015 |
(_ | +0.014 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.014 |
belts | +0.014 |
Neg logit contributions | |
ippi | -0.016 |
Beir | -0.015 |
nton | -0.015 |
Gad | -0.014 |
Sas | -0.014 |
Token | asions |
Token ID | 39327 |
Feature activation | -5.55e+00 |
Pos logit contributions | |
Beir | +0.645 |
ippi | +0.634 |
nton | +0.625 |
Gad | +0.591 |
Sas | +0.588 |
Neg logit contributions | |
ILCS | -0.926 |
機 | -0.767 |
(_ | -0.747 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.738 |
belts | -0.727 |
Token | , |
Token ID | 11 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ippi | +2.842 |
Beir | +2.810 |
nton | +2.796 |
Sas | +2.584 |
spons | +2.558 |
Neg logit contributions | |
ILCS | -5.067 |
機 | -4.198 |
(_ | -4.049 |
Send | -4.021 |
belts | -3.991 |
Token | folly |
Token ID | 43411 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ippi | +0.723 |
Beir | +0.723 |
nton | +0.715 |
Gad | +0.674 |
Sas | +0.671 |
Neg logit contributions | |
ILCS | -0.919 |
機 | -0.749 |
(_ | -0.721 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.718 |
belts | -0.708 |
Token | , |
Token ID | 11 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ippi | +1.677 |
Beir | +1.672 |
nton | +1.669 |
Sas | +1.545 |
Gad | +1.541 |
Neg logit contributions | |
ILCS | -2.615 |
機 | -2.167 |
(_ | -2.090 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.070 |
belts | -2.051 |
Token | hatred |
Token ID | 13763 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ippi | +1.043 |
Beir | +1.043 |
nton | +1.032 |
Gad | +0.973 |
Sas | +0.970 |
Neg logit contributions | |
ILCS | -1.310 |
機 | -1.067 |
(_ | -1.028 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.022 |
belts | -1.006 |
Token | , |
Token ID | 11 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ippi | +0.803 |
Beir | +0.802 |
nton | +0.796 |
Gad | +0.740 |
Sas | +0.740 |
Neg logit contributions | |
ILCS | -1.210 |
機 | -1.002 |
(_ | -0.966 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.959 |
belts | -0.948 |
Token | out |
Token ID | 503 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
Beir | +1.725 |
ippi | +1.714 |
nton | +1.696 |
Gad | +1.619 |
Sas | +1.616 |
Neg logit contributions | |
ILCS | -1.836 |
機 | -1.468 |
(_ | -1.396 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.393 |
belts | -1.365 |
Token | of |
Token ID | 286 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
ippi | +0.303 |
Beir | +0.302 |
nton | +0.300 |
Gad | +0.283 |
Sas | +0.282 |
Neg logit contributions | |
ILCS | -0.337 |
機 | -0.271 |
(_ | -0.261 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.260 |
belts | -0.255 |
Token | the |
Token ID | 262 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
ippi | +0.943 |
Beir | +0.936 |
nton | +0.932 |
Gad | +0.876 |
Sas | +0.871 |
Neg logit contributions | |
ILCS | -1.085 |
機 | -0.876 |
(_ | -0.844 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.841 |
belts | -0.827 |
Token | Second |
Token ID | 5498 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ippi | +0.680 |
Beir | +0.677 |
nton | +0.673 |
Gad | +0.635 |
Sas | +0.632 |
Neg logit contributions | |
ILCS | -0.693 |
機 | -0.551 |
(_ | -0.528 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.526 |
belts | -0.520 |
Token | Division |
Token ID | 7458 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
ippi | +0.267 |
Beir | +0.266 |
nton | +0.264 |
Gad | +0.248 |
Sas | +0.247 |
Neg logit contributions | |
ILCS | -0.333 |
機 | -0.271 |
(_ | -0.262 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.260 |
belts | -0.256 |
Token | Barr |
Token ID | 27883 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
ippi | +1.261 |
Beir | +1.256 |
nton | +1.246 |
Gad | +1.175 |
Sas | +1.170 |
Neg logit contributions | |
ILCS | -1.435 |
機 | -1.157 |
(_ | -1.118 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.109 |
belts | -1.090 |
Token | acks |
Token ID | 4595 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
ippi | +2.764 |
Beir | +2.711 |
nton | +2.710 |
Sas | +2.528 |
Gad | +2.512 |
Neg logit contributions | |
ILCS | -5.144 |
機 | -4.340 |
(_ | -4.169 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -4.168 |
belts | -4.149 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ippi | +0.521 |
Beir | +0.520 |
nton | +0.516 |
Gad | +0.485 |
Sas | +0.484 |
Neg logit contributions | |
ILCS | -0.634 |
機 | -0.515 |
(_ | -0.498 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.495 |
belts | -0.486 |
Token | started |
Token ID | 2067 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
ippi | +0.093 |
Beir | +0.092 |
nton | +0.092 |
Gad | +0.086 |
spons | +0.086 |
Neg logit contributions | |
ILCS | -0.122 |
機 | -0.100 |
(_ | -0.096 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.096 |
belts | -0.095 |
Token | hur |
Token ID | 6990 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Beir | +1.072 |
ippi | +1.072 |
nton | +1.062 |
Gad | +1.004 |
Sas | +1.002 |
Neg logit contributions | |
ILCS | -1.214 |
機 | -0.978 |
(_ | -0.938 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.933 |
belts | -0.919 |
Token | rying |
Token ID | 14992 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
ippi | +1.855 |
nton | +1.847 |
Beir | +1.836 |
Sas | +1.723 |
Gad | +1.706 |
Neg logit contributions | |
ILCS | -2.531 |
機 | -2.100 |
(_ | -1.995 |
belts | -1.981 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.979 |
Token | { |
Token ID | 1391 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
ippi | +1.399 |
Beir | +1.394 |
nton | +1.374 |
Gad | +1.315 |
Sas | +1.296 |
Neg logit contributions | |
ILCS | -1.897 |
機 | -1.549 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.485 |
ーテ | -1.464 |
belts | -1.463 |
Token | pub |
Token ID | 2240 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ILCS | +1.364 |
機 | +1.060 |
(_ | +1.019 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.008 |
belts | +0.987 |
Neg logit contributions | |
ippi | -1.586 |
Beir | -1.582 |
nton | -1.572 |
Gad | -1.491 |
Sas | -1.485 |
Token | fn |
Token ID | 24714 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
ILCS | +0.920 |
機 | +0.660 |
(_ | +0.635 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.626 |
Send | +0.602 |
Neg logit contributions | |
ippi | -1.541 |
Beir | -1.540 |
nton | -1.535 |
Gad | -1.457 |
Sas | -1.452 |
Token | load |
Token ID | 3440 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
ILCS | +2.238 |
(_ | +1.745 |
機 | +1.708 |
belts | +1.697 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.662 |
Neg logit contributions | |
ippi | -2.634 |
Beir | -2.613 |
nton | -2.593 |
lished | -2.446 |
Sas | -2.420 |
Token | < |
Token ID | 1279 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
ILCS | +0.579 |
機 | +0.464 |
(_ | +0.444 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.443 |
belts | +0.436 |
Neg logit contributions | |
ippi | -0.528 |
Beir | -0.527 |
nton | -0.522 |
Gad | -0.495 |
Sas | -0.493 |
Token | ' |
Token ID | 705 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
Beir | +1.619 |
ippi | +1.619 |
nton | +1.602 |
Gad | +1.511 |
Sas | +1.507 |
Neg logit contributions | |
ILCS | -2.105 |
機 | -1.725 |
(_ | -1.651 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.649 |
belts | -1.627 |
Token | a |
Token ID | 64 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
ILCS | +2.643 |
機 | +2.086 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.059 |
(_ | +2.055 |
Send | +1.991 |
Neg logit contributions | |
Beir | -2.437 |
ippi | -2.430 |
nton | -2.364 |
spons | -2.223 |
Gad | -2.219 |
Token | > |
Token ID | 1875 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ILCS | +1.271 |
機 | +1.041 |
(_ | +1.017 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.010 |
belts | +0.993 |
Neg logit contributions | |
Beir | -0.922 |
ippi | -0.919 |
nton | -0.913 |
spons | -0.849 |
Sas | -0.848 |
Token | ( |
Token ID | 357 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
ippi | +1.475 |
Beir | +1.458 |
nton | +1.443 |
Gad | +1.377 |
Sas | +1.370 |
Neg logit contributions | |
ILCS | -1.759 |
機 | -1.427 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.349 |
ーテ | -1.336 |
belts | -1.331 |
Token | & |
Token ID | 1222 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ILCS | +0.142 |
機 | +0.119 |
(_ | +0.117 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.115 |
belts | +0.115 |
Neg logit contributions | |
Beir | -0.078 |
ippi | -0.077 |
nton | -0.076 |
Sas | -0.070 |
Gad | -0.070 |
Token | self |
Token ID | 2116 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
ILCS | +0.962 |
機 | +0.724 |
(_ | +0.700 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.687 |
belts | +0.684 |
Neg logit contributions | |
Beir | -1.276 |
ippi | -1.266 |
nton | -1.260 |
Sas | -1.188 |
lished | -1.188 |
Token | could |
Token ID | 714 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILCS | +0.473 |
機 | +0.373 |
(_ | +0.363 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.361 |
belts | +0.357 |
Neg logit contributions | |
ippi | -0.465 |
Beir | -0.465 |
nton | -0.461 |
Gad | -0.435 |
Sas | -0.433 |
Token | sit |
Token ID | 1650 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ILCS | +0.935 |
機 | +0.738 |
(_ | +0.722 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.722 |
belts | +0.712 |
Neg logit contributions | |
ippi | -0.882 |
Beir | -0.880 |
nton | -0.870 |
Gad | -0.826 |
Sas | -0.819 |
Token | in |
Token ID | 287 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
ILCS | +0.243 |
機 | +0.180 |
(_ | +0.172 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.171 |
belts | +0.169 |
Neg logit contributions | |
ippi | -0.350 |
Beir | -0.349 |
nton | -0.348 |
Gad | -0.332 |
Sas | -0.330 |
Token | the |
Token ID | 262 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
ippi | +0.052 |
Beir | +0.052 |
nton | +0.052 |
Gad | +0.049 |
Sas | +0.048 |
Neg logit contributions | |
ILCS | -0.057 |
機 | -0.045 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.044 |
(_ | -0.044 |
belts | -0.043 |
Token | same |
Token ID | 976 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
ippi | +0.298 |
nton | +0.296 |
Beir | +0.296 |
Gad | +0.278 |
Sas | +0.277 |
Neg logit contributions | |
ILCS | -0.355 |
機 | -0.287 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.275 |
(_ | -0.274 |
belts | -0.272 |
Token | room |
Token ID | 2119 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
ILCS | +2.777 |
機 | +2.198 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.141 |
belts | +2.126 |
(_ | +2.106 |
Neg logit contributions | |
ippi | -2.593 |
nton | -2.556 |
Beir | -2.540 |
lished | -2.461 |
Gad | -2.421 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ILCS | +2.785 |
機 | +2.187 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.145 |
(_ | +2.144 |
belts | +2.113 |
Neg logit contributions | |
Beir | -2.702 |
ippi | -2.698 |
nton | -2.673 |
Gad | -2.535 |
Sas | -2.505 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ippi | +0.119 |
Beir | +0.119 |
nton | +0.118 |
Gad | +0.112 |
Sas | +0.112 |
Neg logit contributions | |
ILCS | -0.116 |
機 | -0.091 |
(_ | -0.087 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.087 |
belts | -0.086 |
Token | what |
Token ID | 644 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
ILCS | +1.025 |
機 | +0.809 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.790 |
belts | +0.787 |
(_ | +0.787 |
Neg logit contributions | |
ippi | -0.953 |
nton | -0.952 |
Beir | -0.950 |
Gad | -0.890 |
Sas | -0.885 |
Token | she |
Token ID | 673 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
ippi | +0.535 |
Beir | +0.532 |
nton | +0.530 |
Gad | +0.498 |
Sas | +0.498 |
Neg logit contributions | |
ILCS | -0.621 |
機 | -0.501 |
(_ | -0.483 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.481 |
belts | -0.476 |
Token | called |
Token ID | 1444 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ippi | +1.156 |
Beir | +1.156 |
nton | +1.144 |
Gad | +1.078 |
Sas | +1.074 |
Neg logit contributions | |
ILCS | -1.509 |
機 | -1.232 |
(_ | -1.188 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.183 |
belts | -1.162 |
Token | According |
Token ID | 4784 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ILCS | +0.705 |
機 | +0.580 |
(_ | +0.563 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.560 |
belts | +0.547 |
Neg logit contributions | |
ippi | -0.495 |
Beir | -0.490 |
nton | -0.486 |
spons | -0.465 |
Gad | -0.457 |
Token | to |
Token ID | 284 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
ILCS | +0.751 |
機 | +0.603 |
(_ | +0.590 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.581 |
belts | +0.569 |
Neg logit contributions | |
ippi | -0.696 |
Beir | -0.689 |
nton | -0.678 |
lished | -0.659 |
spons | -0.657 |
Token | the |
Token ID | 262 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
ILCS | +0.404 |
機 | +0.331 |
(_ | +0.318 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.317 |
belts | +0.314 |
Neg logit contributions | |
ippi | -0.306 |
Beir | -0.305 |
nton | -0.302 |
Gad | -0.284 |
spons | -0.282 |
Token | San |
Token ID | 2986 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ILCS | +0.513 |
機 | +0.417 |
(_ | +0.400 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.400 |
belts | +0.394 |
Neg logit contributions | |
Beir | -0.401 |
ippi | -0.400 |
nton | -0.397 |
Gad | -0.373 |
Sas | -0.371 |
Token | Francisco |
Token ID | 6033 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ILCS | +0.503 |
機 | +0.408 |
(_ | +0.393 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.392 |
belts | +0.385 |
Neg logit contributions | |
Beir | -0.412 |
ippi | -0.412 |
nton | -0.408 |
Gad | -0.385 |
Sas | -0.382 |
Token | Chronicle |
Token ID | 14160 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
ILCS | +0.827 |
機 | +0.650 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.629 |
(_ | +0.628 |
belts | +0.615 |
Neg logit contributions | |
Beir | -0.802 |
ippi | -0.795 |
nton | -0.792 |
Gad | -0.746 |
spons | -0.739 |
Token | , |
Token ID | 11 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ILCS | +3.956 |
機 | +3.239 |
(_ | +3.128 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +3.084 |
belts | +3.010 |
Neg logit contributions | |
Beir | -3.466 |
ippi | -3.446 |
nton | -3.415 |
Gad | -3.287 |
Sas | -3.232 |
Token | K |
Token ID | 509 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
ILCS | +1.303 |
機 | +1.065 |
(_ | +1.025 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.022 |
belts | +1.011 |
Neg logit contributions | |
ippi | -1.031 |
Beir | -1.023 |
nton | -1.014 |
Gad | -0.963 |
spons | -0.952 |
Token | uy |
Token ID | 4669 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ILCS | +0.400 |
機 | +0.332 |
(_ | +0.323 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.319 |
umann | +0.314 |
Neg logit contributions | |
Beir | -0.281 |
ippi | -0.274 |
nton | -0.271 |
Gad | -0.261 |
Sas | -0.259 |
Token | k |
Token ID | 74 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ILCS | +0.263 |
機 | +0.203 |
(_ | +0.199 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.192 |
Send | +0.190 |
Neg logit contributions | |
Beir | -0.312 |
ippi | -0.309 |
nton | -0.302 |
spons | -0.293 |
Gad | -0.292 |
Token | end |
Token ID | 437 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
ILCS | +0.575 |
機 | +0.446 |
(_ | +0.434 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.423 |
Send | +0.418 |
Neg logit contributions | |
Beir | -0.660 |
ippi | -0.654 |
nton | -0.642 |
Sas | -0.619 |
Gad | -0.617 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ippi | +0.407 |
Beir | +0.407 |
nton | +0.403 |
Gad | +0.381 |
Sas | +0.380 |
Neg logit contributions | |
ILCS | -0.462 |
機 | -0.372 |
(_ | -0.357 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.355 |
belts | -0.350 |
Token | Bronx |
Token ID | 32486 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
ippi | +0.923 |
Beir | +0.923 |
nton | +0.916 |
Gad | +0.876 |
Sas | +0.874 |
Neg logit contributions | |
ILCS | -0.651 |
機 | -0.490 |
(_ | -0.462 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.459 |
belts | -0.449 |
Token | County |
Token ID | 3418 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ILCS | +1.386 |
機 | +1.121 |
(_ | +1.094 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.084 |
belts | +1.070 |
Neg logit contributions | |
ippi | -1.081 |
Beir | -1.079 |
nton | -1.063 |
Gad | -1.005 |
Sas | -1.003 |
Token | but |
Token ID | 475 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ippi | +1.021 |
Beir | +1.020 |
nton | +1.012 |
Gad | +0.953 |
Sas | +0.951 |
Neg logit contributions | |
ILCS | -1.235 |
機 | -1.004 |
(_ | -0.963 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.960 |
belts | -0.946 |
Token | the |
Token ID | 262 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ippi | +0.352 |
Beir | +0.352 |
nton | +0.349 |
Gad | +0.330 |
Sas | +0.329 |
Neg logit contributions | |
ILCS | -0.384 |
機 | -0.307 |
(_ | -0.295 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.294 |
belts | -0.289 |
Token | same |
Token ID | 976 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
ippi | +0.286 |
Beir | +0.286 |
nton | +0.283 |
Gad | +0.268 |
Sas | +0.268 |
Neg logit contributions | |
ILCS | -0.302 |
機 | -0.241 |
(_ | -0.232 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.230 |
belts | -0.227 |
Token | problem |
Token ID | 1917 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ILCS | +3.017 |
機 | +2.413 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +2.352 |
(_ | +2.349 |
belts | +2.322 |
Neg logit contributions | |
ippi | -2.691 |
Beir | -2.673 |
nton | -2.616 |
lished | -2.488 |
spons | -2.475 |
Token | hits |
Token ID | 7127 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ILCS | +0.937 |
機 | +0.774 |
(_ | +0.753 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.745 |
belts | +0.742 |
Neg logit contributions | |
ippi | -0.658 |
Beir | -0.649 |
nton | -0.644 |
Gad | -0.606 |
spons | -0.599 |
Token | black |
Token ID | 2042 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
ILCS | +0.497 |
機 | +0.395 |
(_ | +0.381 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.379 |
belts | +0.374 |
Neg logit contributions | |
ippi | -0.469 |
Beir | -0.467 |
nton | -0.463 |
Gad | -0.437 |
spons | -0.437 |
Token | people |
Token ID | 661 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
ILCS | +0.024 |
機 | +0.019 |
(_ | +0.018 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.018 |
belts | +0.018 |
Neg logit contributions | |
ippi | -0.022 |
Beir | -0.022 |
nton | -0.021 |
Gad | -0.020 |
Sas | -0.020 |
Token | all |
Token ID | 477 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ILCS | +0.455 |
機 | +0.361 |
(_ | +0.349 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.346 |
belts | +0.341 |
Neg logit contributions | |
ippi | -0.443 |
Beir | -0.441 |
nton | -0.437 |
Gad | -0.415 |
Sas | -0.413 |
Token | --+ |
Token ID | 44785 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ILCS | +1.297 |
機 | +1.016 |
(_ | +0.994 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.975 |
Send | +0.957 |
Neg logit contributions | |
Beir | -1.345 |
ippi | -1.333 |
nton | -1.322 |
Gad | -1.263 |
spons | -1.256 |
Token | < |
Token ID | 1279 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
Beir | +0.584 |
ippi | +0.583 |
nton | +0.578 |
Gad | +0.548 |
Sas | +0.547 |
Neg logit contributions | |
ILCS | -0.648 |
機 | -0.518 |
(_ | -0.497 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.495 |
belts | -0.487 |
Token | -- |
Token ID | 438 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
Beir | +0.315 |
ippi | +0.314 |
nton | +0.310 |
Sas | +0.297 |
Gad | +0.296 |
Neg logit contributions | |
ILCS | -0.229 |
機 | -0.173 |
(_ | -0.166 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.164 |
belts | -0.160 |
Token | Start |
Token ID | 7253 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
ippi | +0.264 |
Beir | +0.263 |
nton | +0.261 |
Gad | +0.247 |
Sas | +0.246 |
Neg logit contributions | |
ILCS | -0.259 |
機 | -0.205 |
(_ | -0.198 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.196 |
belts | -0.192 |
Token | of |
Token ID | 286 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ippi | +0.026 |
Beir | +0.026 |
nton | +0.025 |
spons | +0.024 |
Gad | +0.024 |
Neg logit contributions | |
ILCS | -0.026 |
機 | -0.020 |
(_ | -0.020 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.019 |
belts | -0.019 |
Token | system |
Token ID | 1080 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
ippi | +0.119 |
Beir | +0.119 |
nton | +0.118 |
Gad | +0.111 |
Sas | +0.111 |
Neg logit contributions | |
ILCS | -0.141 |
機 | -0.113 |
(_ | -0.109 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.108 |
belts | -0.107 |
Token | () |
Token ID | 3419 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ILCS | +1.475 |
(_ | +1.015 |
機 | +0.896 |
Send | +0.865 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.808 |
Neg logit contributions | |
Beir | -4.002 |
ippi | -3.919 |
nton | -3.855 |
spons | -3.822 |
lished | -3.798 |
Token | ' |
Token ID | 6 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
ILCS | +0.598 |
(_ | +0.437 |
機 | +0.433 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.414 |
Send | +0.406 |
Neg logit contributions | |
ippi | -0.992 |
Beir | -0.989 |
nton | -0.979 |
lished | -0.949 |
Gad | -0.936 |
Token | s |
Token ID | 82 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
ILCS | +1.694 |
(_ | +1.371 |
機 | +1.354 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.319 |
Send | +1.317 |
Neg logit contributions | |
Beir | -1.711 |
ippi | -1.681 |
nton | -1.607 |
spons | -1.594 |
lished | -1.586 |
Token | frame |
Token ID | 5739 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ippi | +0.083 |
Beir | +0.083 |
nton | +0.082 |
lished | +0.078 |
Gad | +0.078 |
Neg logit contributions | |
ILCS | -0.067 |
機 | -0.051 |
(_ | -0.051 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.049 |
belts | -0.049 |
Token | | |
Token ID | 930 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ILCS | +2.256 |
(_ | +1.861 |
機 | +1.794 |
Send | +1.771 |
belts | +1.770 |
Neg logit contributions | |
ippi | -1.972 |
Beir | -1.907 |
nton | -1.882 |
lished | -1.857 |
spons | -1.772 |
Token | bass |
Token ID | 12702 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ippi | +0.993 |
Beir | +0.991 |
nton | +0.982 |
Gad | +0.928 |
Sas | +0.925 |
Neg logit contributions | |
ILCS | -1.097 |
機 | -0.881 |
(_ | -0.846 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.842 |
belts | -0.830 |
Token | aside |
Token ID | 7263 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
ippi | +0.206 |
Beir | +0.205 |
nton | +0.203 |
Gad | +0.191 |
Sas | +0.190 |
Neg logit contributions | |
ILCS | -0.260 |
機 | -0.212 |
(_ | -0.204 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.204 |
belts | -0.201 |
Token | , |
Token ID | 11 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ILCS | +0.750 |
機 | +0.613 |
(_ | +0.591 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.588 |
belts | +0.580 |
Neg logit contributions | |
ippi | -0.569 |
Beir | -0.569 |
nton | -0.563 |
Gad | -0.530 |
Sas | -0.528 |
Token | I |
Token ID | 314 |
Feature activation | -8.91e-02 |
Pos logit contributions | |
ippi | +0.024 |
Beir | +0.024 |
nton | +0.024 |
Gad | +0.023 |
Sas | +0.023 |
Neg logit contributions | |
ILCS | -0.028 |
機 | -0.022 |
(_ | -0.022 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.022 |
belts | -0.021 |
Token | preferred |
Token ID | 9871 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
ippi | +0.060 |
Beir | +0.059 |
nton | +0.059 |
Gad | +0.056 |
lished | +0.055 |
Neg logit contributions | |
ILCS | -0.067 |
機 | -0.055 |
(_ | -0.053 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.053 |
belts | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Beir | +1.794 |
ippi | +1.789 |
nton | +1.770 |
Sas | +1.686 |
Gad | +1.679 |
Neg logit contributions | |
ILCS | -2.224 |
機 | -1.790 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.722 |
(_ | -1.719 |
belts | -1.679 |
Token | Silver |
Token ID | 7698 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ILCS | +0.112 |
機 | +0.093 |
(_ | +0.089 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.089 |
belts | +0.088 |
Neg logit contributions | |
ippi | -0.087 |
Beir | -0.086 |
nton | -0.085 |
Gad | -0.080 |
spons | -0.079 |
Token | Phant |
Token ID | 38699 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
ippi | +0.588 |
Beir | +0.587 |
nton | +0.579 |
Gad | +0.533 |
Sas | +0.531 |
Neg logit contributions | |
ILCS | -1.248 |
機 | -1.058 |
(_ | -1.027 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.024 |
belts | -1.012 |
Token | oms |
Token ID | 3150 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Beir | +0.432 |
ippi | +0.427 |
nton | +0.425 |
Gad | +0.404 |
Sas | +0.403 |
Neg logit contributions | |
ILCS | -0.435 |
機 | -0.345 |
(_ | -0.336 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.328 |
belts | -0.325 |
Token | to |
Token ID | 284 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
ILCS | +1.078 |
機 | +0.869 |
(_ | +0.843 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.830 |
belts | +0.820 |
Neg logit contributions | |
ippi | -1.025 |
Beir | -1.024 |
nton | -1.016 |
Gad | -0.960 |
Sas | -0.952 |
Token | the |
Token ID | 262 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ILCS | +0.221 |
機 | +0.180 |
(_ | +0.172 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.171 |
belts | +0.170 |
Neg logit contributions | |
ippi | -0.197 |
Beir | -0.197 |
nton | -0.195 |
Gad | -0.183 |
Sas | -0.182 |
Token | clothes |
Token ID | 8242 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
ippi | +0.083 |
Beir | +0.082 |
nton | +0.081 |
Gad | +0.077 |
Sas | +0.076 |
Neg logit contributions | |
ILCS | -0.082 |
機 | -0.064 |
belts | -0.062 |
(_ | -0.062 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ippi | +0.397 |
Beir | +0.396 |
nton | +0.393 |
Gad | +0.369 |
Sas | +0.368 |
Neg logit contributions | |
ILCS | -0.505 |
機 | -0.412 |
(_ | -0.398 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.395 |
belts | -0.391 |
Token | You |
Token ID | 921 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
ippi | +0.151 |
Beir | +0.149 |
nton | +0.149 |
spons | +0.140 |
Gad | +0.139 |
Neg logit contributions | |
ILCS | -0.174 |
機 | -0.140 |
(_ | -0.135 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.135 |
belts | -0.133 |
Token | are |
Token ID | 389 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
ILCS | +0.514 |
機 | +0.412 |
(_ | +0.399 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.396 |
belts | +0.395 |
Neg logit contributions | |
Beir | -0.498 |
ippi | -0.497 |
nton | -0.491 |
Gad | -0.469 |
Sas | -0.462 |
Token | going |
Token ID | 1016 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
ILCS | +0.384 |
機 | +0.309 |
(_ | +0.299 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.297 |
belts | +0.295 |
Neg logit contributions | |
ippi | -0.342 |
Beir | -0.340 |
nton | -0.337 |
Gad | -0.316 |
spons | -0.315 |
Token | to |
Token ID | 284 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
ILCS | +0.702 |
機 | +0.573 |
(_ | +0.553 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.551 |
belts | +0.542 |
Neg logit contributions | |
ippi | -0.531 |
Beir | -0.530 |
nton | -0.524 |
Sas | -0.494 |
Gad | -0.494 |
Token | be |
Token ID | 307 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ILCS | +0.674 |
機 | +0.544 |
(_ | +0.530 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.528 |
belts | +0.526 |
Neg logit contributions | |
ippi | -0.594 |
Beir | -0.587 |
nton | -0.584 |
Gad | -0.551 |
lished | -0.549 |
Token | on |
Token ID | 319 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
ILCS | +0.435 |
機 | +0.352 |
(_ | +0.341 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.339 |
belts | +0.337 |
Neg logit contributions | |
ippi | -0.384 |
Beir | -0.381 |
nton | -0.381 |
Gad | -0.356 |
lished | -0.355 |
Token | your |
Token ID | 534 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
ippi | +0.461 |
Beir | +0.460 |
nton | +0.457 |
Gad | +0.429 |
Sas | +0.427 |
Neg logit contributions | |
ILCS | -0.534 |
機 | -0.431 |
(_ | -0.417 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.415 |
belts | -0.411 |
Token | feet |
Token ID | 3625 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
ippi | +0.083 |
Beir | +0.082 |
nton | +0.082 |
Gad | +0.077 |
Sas | +0.077 |
Neg logit contributions | |
ILCS | -0.089 |
機 | -0.072 |
(_ | -0.069 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.069 |
belts | -0.068 |
Token | for |
Token ID | 329 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ippi | +0.377 |
Beir | +0.377 |
nton | +0.373 |
Gad | +0.353 |
Sas | +0.352 |
Neg logit contributions | |
ILCS | -0.405 |
機 | -0.324 |
(_ | -0.311 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.309 |
belts | -0.304 |
Token | in |
Token ID | 259 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ippi | +0.559 |
Beir | +0.559 |
nton | +0.552 |
Gad | +0.520 |
Sas | +0.519 |
Neg logit contributions | |
ILCS | -0.711 |
機 | -0.580 |
(_ | -0.559 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.556 |
belts | -0.548 |
Token | theory |
Token ID | 4583 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
Beir | +0.179 |
ippi | +0.179 |
nton | +0.177 |
Gad | +0.166 |
Sas | +0.166 |
Neg logit contributions | |
ILCS | -0.206 |
機 | -0.166 |
(_ | -0.160 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.159 |
belts | -0.157 |
Token | at |
Token ID | 379 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
ILCS | +0.285 |
機 | +0.239 |
(_ | +0.231 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.230 |
belts | +0.227 |
Neg logit contributions | |
ippi | -0.160 |
Beir | -0.159 |
nton | -0.157 |
Gad | -0.146 |
Sas | -0.146 |
Token | least |
Token ID | 1551 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
ILCS | +0.701 |
機 | +0.549 |
(_ | +0.530 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.527 |
belts | +0.525 |
Neg logit contributions | |
ippi | -0.727 |
nton | -0.724 |
Beir | -0.723 |
Gad | -0.676 |
Wonders | -0.676 |
Token | ) |
Token ID | 8 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
ippi | +0.437 |
Beir | +0.437 |
nton | +0.431 |
Gad | +0.401 |
Sas | +0.400 |
Neg logit contributions | |
ILCS | -0.785 |
機 | -0.658 |
(_ | -0.638 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.635 |
belts | -0.627 |
Token | universal |
Token ID | 10112 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ippi | +1.453 |
Beir | +1.452 |
nton | +1.436 |
Gad | +1.380 |
Sas | +1.374 |
Neg logit contributions | |
ILCS | -1.440 |
機 | -1.140 |
(_ | -1.088 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.078 |
belts | -1.058 |
Token | . |
Token ID | 13 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
ILCS | +0.975 |
機 | +0.783 |
(_ | +0.758 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.750 |
belts | +0.747 |
Neg logit contributions | |
Beir | -0.865 |
ippi | -0.860 |
nton | -0.849 |
Gad | -0.795 |
Sas | -0.794 |
Token | The |
Token ID | 383 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ILCS | +0.401 |
機 | +0.327 |
(_ | +0.316 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.314 |
Send | +0.308 |
Neg logit contributions | |
ippi | -0.319 |
Beir | -0.317 |
nton | -0.315 |
spons | -0.299 |
lished | -0.292 |
Token | idea |
Token ID | 2126 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
ILCS | +0.911 |
機 | +0.726 |
(_ | +0.697 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.691 |
belts | +0.686 |
Neg logit contributions | |
ippi | -0.908 |
Beir | -0.905 |
nton | -0.898 |
Gad | -0.843 |
Sas | -0.839 |
Token | here |
Token ID | 994 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ILCS | +2.258 |
機 | +1.865 |
(_ | +1.811 |
belts | +1.788 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.767 |
Neg logit contributions | |
ippi | -1.772 |
Beir | -1.761 |
nton | -1.756 |
Gad | -1.639 |
spons | -1.632 |
Token | is |
Token ID | 318 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ippi | +0.264 |
Beir | +0.264 |
nton | +0.260 |
Gad | +0.240 |
Sas | +0.239 |
Neg logit contributions | |
ILCS | -0.506 |
機 | -0.427 |
(_ | -0.415 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.412 |
belts | -0.409 |
Token | 2015 |
Token ID | 1853 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ippi | +0.023 |
Beir | +0.023 |
nton | +0.023 |
Gad | +0.021 |
Sas | +0.021 |
Neg logit contributions | |
ILCS | -0.036 |
機 | -0.029 |
(_ | -0.028 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.028 |
belts | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
ILCS | +0.653 |
機 | +0.532 |
(_ | +0.515 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.511 |
belts | +0.504 |
Neg logit contributions | |
Beir | -0.510 |
ippi | -0.510 |
nton | -0.504 |
Gad | -0.475 |
Sas | -0.473 |
Token | Price |
Token ID | 7886 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ippi | +0.294 |
Beir | +0.293 |
nton | +0.290 |
Gad | +0.268 |
Sas | +0.266 |
Neg logit contributions | |
ILCS | -0.558 |
機 | -0.469 |
(_ | -0.455 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.453 |
belts | -0.448 |
Token | complained |
Token ID | 13832 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
ippi | +0.686 |
Beir | +0.685 |
nton | +0.676 |
Gad | +0.634 |
Sas | +0.631 |
Neg logit contributions | |
ILCS | -0.988 |
機 | -0.814 |
(_ | -0.790 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.782 |
belts | -0.780 |
Token | that |
Token ID | 326 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Beir | +0.012 |
ippi | +0.012 |
nton | +0.012 |
Gad | +0.012 |
Sas | +0.012 |
Neg logit contributions | |
ILCS | -0.016 |
機 | -0.013 |
(_ | -0.013 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.013 |
belts | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
ILCS | +0.911 |
機 | +0.751 |
(_ | +0.734 |
belts | +0.731 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.728 |
Neg logit contributions | |
ippi | -0.621 |
Beir | -0.619 |
nton | -0.613 |
Gad | -0.567 |
Wonders | -0.566 |
Token | club |
Token ID | 3430 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ILCS | +0.475 |
機 | +0.381 |
(_ | +0.371 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.368 |
belts | +0.365 |
Neg logit contributions | |
ippi | -0.427 |
Beir | -0.425 |
nton | -0.416 |
Gad | -0.396 |
Wonders | -0.394 |
Token | manager |
Token ID | 4706 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
ippi | +0.083 |
Beir | +0.083 |
nton | +0.081 |
Gad | +0.077 |
Wonders | +0.076 |
Neg logit contributions | |
ILCS | -0.105 |
機 | -0.085 |
(_ | -0.083 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.082 |
belts | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
ippi | +0.584 |
Beir | +0.582 |
nton | +0.575 |
Gad | +0.540 |
Sas | +0.538 |
Neg logit contributions | |
ILCS | -0.760 |
機 | -0.623 |
(_ | -0.603 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.596 |
belts | -0.593 |
Token | Randy |
Token ID | 21248 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ILCS | +0.620 |
機 | +0.503 |
(_ | +0.492 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.486 |
belts | +0.485 |
Neg logit contributions | |
ippi | -0.472 |
Beir | -0.468 |
nton | -0.461 |
Gad | -0.433 |
Wonders | -0.432 |
Token | Thornton |
Token ID | 37519 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Beir | +1.294 |
ippi | +1.279 |
nton | +1.268 |
Gad | +1.199 |
Sas | +1.195 |
Neg logit contributions | |
ILCS | -2.012 |
機 | -1.678 |
(_ | -1.616 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.610 |
belts | -1.590 |
Token | producer |
Token ID | 9920 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ILCS | +0.081 |
機 | +0.066 |
(_ | +0.064 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.064 |
belts | +0.063 |
Neg logit contributions | |
ippi | -0.061 |
Beir | -0.061 |
nton | -0.061 |
Gad | -0.057 |
Sas | -0.057 |
Token | Jordan |
Token ID | 8078 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Beir | +1.032 |
ippi | +1.029 |
nton | +1.017 |
Gad | +0.951 |
Sas | +0.948 |
Neg logit contributions | |
ILCS | -1.736 |
機 | -1.452 |
(_ | -1.401 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.397 |
belts | -1.378 |
Token | Horowitz |
Token ID | 47591 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
ippi | +0.495 |
Beir | +0.491 |
nton | +0.488 |
Gad | +0.454 |
spons | +0.453 |
Neg logit contributions | |
ILCS | -0.752 |
機 | -0.621 |
(_ | -0.602 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.599 |
belts | -0.592 |
Token | delivering |
Token ID | 13630 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ILCS | +0.576 |
機 | +0.470 |
(_ | +0.454 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.448 |
belts | +0.445 |
Neg logit contributions | |
ippi | -0.473 |
Beir | -0.471 |
nton | -0.466 |
Gad | -0.442 |
Sas | -0.438 |
Token | the |
Token ID | 262 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
ILCS | +0.214 |
機 | +0.172 |
(_ | +0.167 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.165 |
belts | +0.164 |
Neg logit contributions | |
ippi | -0.187 |
Beir | -0.186 |
nton | -0.185 |
Gad | -0.174 |
Sas | -0.173 |
Token | news |
Token ID | 1705 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
ippi | +0.249 |
Beir | +0.249 |
nton | +0.247 |
Gad | +0.234 |
Sas | +0.233 |
Neg logit contributions | |
ILCS | -0.261 |
機 | -0.208 |
(_ | -0.200 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.199 |
belts | -0.196 |
Token | to |
Token ID | 284 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
ILCS | +1.966 |
機 | +1.566 |
(_ | +1.539 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.502 |
belts | +1.496 |
Neg logit contributions | |
ippi | -1.877 |
Beir | -1.869 |
nton | -1.869 |
Gad | -1.758 |
Sas | -1.745 |
Token | the |
Token ID | 262 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ippi | +0.421 |
nton | +0.416 |
Beir | +0.416 |
Gad | +0.390 |
Wonders | +0.388 |
Neg logit contributions | |
ILCS | -0.525 |
機 | -0.426 |
(_ | -0.415 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.411 |
belts | -0.407 |
Token | world |
Token ID | 995 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
ippi | +0.614 |
Beir | +0.612 |
nton | +0.607 |
Gad | +0.568 |
Sas | +0.566 |
Neg logit contributions | |
ILCS | -0.790 |
機 | -0.644 |
(_ | -0.622 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.618 |
belts | -0.612 |
Token | that |
Token ID | 326 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
ILCS | +1.225 |
機 | +0.983 |
(_ | +0.953 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.933 |
belts | +0.924 |
Neg logit contributions | |
ippi | -1.178 |
Beir | -1.161 |
nton | -1.154 |
Gad | -1.097 |
Sas | -1.086 |
Token | � |
Token ID | 564 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
ILCS | +0.273 |
機 | +0.222 |
(_ | +0.214 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.213 |
belts | +0.210 |
Neg logit contributions | |
ippi | -0.229 |
Beir | -0.227 |
nton | -0.227 |
Gad | -0.213 |
Sas | -0.212 |
Token | people |
Token ID | 661 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
ILCS | +0.805 |
機 | +0.651 |
(_ | +0.630 |
belts | +0.625 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.624 |
Neg logit contributions | |
ippi | -0.647 |
Beir | -0.643 |
nton | -0.639 |
Wonders | -0.598 |
spons | -0.595 |
Token | including |
Token ID | 1390 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
ILCS | +0.585 |
機 | +0.473 |
belts | +0.463 |
(_ | +0.460 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.453 |
Neg logit contributions | |
ippi | -0.470 |
Beir | -0.464 |
nton | -0.461 |
lished | -0.431 |
Gad | -0.429 |
Token | women |
Token ID | 1466 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ILCS | +0.290 |
機 | +0.235 |
belts | +0.231 |
(_ | +0.231 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.224 |
Neg logit contributions | |
ippi | -0.223 |
Beir | -0.220 |
nton | -0.219 |
lished | -0.205 |
spons | -0.205 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ILCS | +0.279 |
機 | +0.228 |
belts | +0.223 |
(_ | +0.223 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.220 |
Neg logit contributions | |
ippi | -0.209 |
Beir | -0.208 |
nton | -0.205 |
Gad | -0.191 |
Wonders | -0.191 |
Token | children |
Token ID | 1751 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ILCS | +0.085 |
機 | +0.069 |
belts | +0.068 |
(_ | +0.067 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.066 |
Neg logit contributions | |
ippi | -0.066 |
Beir | -0.066 |
nton | -0.066 |
Wonders | -0.061 |
lished | -0.061 |
Token | were |
Token ID | 547 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ILCS | +1.522 |
belts | +1.232 |
機 | +1.229 |
(_ | +1.211 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.189 |
Neg logit contributions | |
ippi | -1.141 |
Beir | -1.125 |
nton | -1.115 |
lished | -1.059 |
Gad | -1.037 |
Token | her |
Token ID | 607 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ippi | +0.151 |
Beir | +0.149 |
nton | +0.148 |
Wonders | +0.138 |
Gad | +0.138 |
Neg logit contributions | |
ILCS | -0.201 |
機 | -0.164 |
belts | -0.160 |
(_ | -0.159 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.157 |
Token | ded |
Token ID | 9395 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
ippi | +0.790 |
Beir | +0.790 |
nton | +0.773 |
Gad | +0.734 |
Sas | +0.733 |
Neg logit contributions | |
ILCS | -0.955 |
機 | -0.767 |
(_ | -0.747 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.741 |
belts | -0.737 |
Token | into |
Token ID | 656 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
ILCS | +0.827 |
機 | +0.652 |
(_ | +0.637 |
belts | +0.636 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.632 |
Neg logit contributions | |
ippi | -0.764 |
nton | -0.760 |
Beir | -0.758 |
Wonders | -0.714 |
spons | -0.710 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ippi | +0.617 |
nton | +0.613 |
Beir | +0.611 |
Gad | +0.569 |
Wonders | +0.568 |
Neg logit contributions | |
ILCS | -0.733 |
機 | -0.589 |
(_ | -0.569 |
belts | -0.569 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.565 |
Token | stadium |
Token ID | 10308 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
ILCS | +0.080 |
機 | +0.064 |
belts | +0.062 |
(_ | +0.062 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.061 |
Neg logit contributions | |
ippi | -0.072 |
nton | -0.072 |
Beir | -0.071 |
lished | -0.067 |
Wonders | -0.067 |
Token | death |
Token ID | 1918 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ILCS | +0.842 |
機 | +0.654 |
belts | +0.638 |
(_ | +0.634 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.627 |
Neg logit contributions | |
ippi | -0.942 |
nton | -0.932 |
Beir | -0.929 |
Wonders | -0.871 |
Gad | -0.869 |
Token | was |
Token ID | 373 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
ippi | +0.079 |
Beir | +0.079 |
nton | +0.078 |
Gad | +0.073 |
Sas | +0.073 |
Neg logit contributions | |
ILCS | -0.103 |
機 | -0.084 |
(_ | -0.082 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.081 |
belts | -0.080 |
Token | imposed |
Token ID | 10893 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
ILCS | +0.355 |
機 | +0.283 |
(_ | +0.272 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.271 |
belts | +0.268 |
Neg logit contributions | |
ippi | -0.339 |
Beir | -0.337 |
nton | -0.335 |
Gad | -0.316 |
Sas | -0.315 |
Token | on |
Token ID | 319 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Beir | +0.459 |
ippi | +0.459 |
nton | +0.454 |
Gad | +0.431 |
Sas | +0.430 |
Neg logit contributions | |
ILCS | -0.511 |
機 | -0.411 |
(_ | -0.394 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.393 |
belts | -0.385 |
Token | anyone |
Token ID | 2687 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
ILCS | +0.217 |
機 | +0.180 |
(_ | +0.176 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.174 |
belts | +0.173 |
Neg logit contributions | |
ippi | -0.138 |
Beir | -0.137 |
nton | -0.137 |
Gad | -0.126 |
Sas | -0.126 |
Token | who |
Token ID | 508 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ippi | +0.151 |
Beir | +0.150 |
nton | +0.149 |
Gad | +0.140 |
Sas | +0.140 |
Neg logit contributions | |
ILCS | -0.160 |
機 | -0.127 |
(_ | -0.123 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.122 |
belts | -0.120 |
Token | opposed |
Token ID | 6886 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
ippi | +0.798 |
Beir | +0.797 |
nton | +0.789 |
Gad | +0.739 |
Sas | +0.737 |
Neg logit contributions | |
ILCS | -1.143 |
機 | -0.942 |
(_ | -0.910 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.906 |
belts | -0.894 |
Token | being |
Token ID | 852 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
ippi | +1.111 |
Beir | +1.110 |
nton | +1.098 |
Gad | +1.040 |
Sas | +1.036 |
Neg logit contributions | |
ILCS | -1.323 |
機 | -1.071 |
(_ | -1.028 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.025 |
belts | -1.008 |
Token | cons |
Token ID | 762 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
ILCS | +0.223 |
機 | +0.183 |
(_ | +0.177 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.176 |
belts | +0.174 |
Neg logit contributions | |
ippi | -0.170 |
Beir | -0.169 |
nton | -0.168 |
Wonders | -0.157 |
Gad | -0.157 |
Token | cript |
Token ID | 6519 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
ILCS | +0.256 |
機 | +0.189 |
(_ | +0.186 |
umann | +0.178 |
ñ | +0.178 |
Neg logit contributions | |
Beir | -0.352 |
nton | -0.339 |
ippi | -0.338 |
Sas | -0.332 |
Wonders | -0.328 |
Token | ed |
Token ID | 276 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
ILCS | +2.108 |
機 | +1.695 |
(_ | +1.650 |
belts | +1.614 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.587 |
Neg logit contributions | |
Beir | -1.979 |
nton | -1.952 |
ippi | -1.946 |
Sas | -1.834 |
Gad | -1.827 |
Token | { |
Token ID | 1391 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
ILCS | +0.721 |
機 | +0.590 |
(_ | +0.569 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.567 |
belts | +0.559 |
Neg logit contributions | |
ippi | -0.542 |
Beir | -0.542 |
nton | -0.536 |
Gad | -0.504 |
Sas | -0.502 |
Token | 1 |
Token ID | 16 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ippi | +0.025 |
Beir | +0.025 |
nton | +0.025 |
Gad | +0.023 |
Sas | +0.023 |
Neg logit contributions | |
ILCS | -0.039 |
機 | -0.032 |
(_ | -0.031 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.031 |
belts | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
ippi | +0.107 |
Beir | +0.107 |
nton | +0.105 |
spons | +0.099 |
Gad | +0.099 |
Neg logit contributions | |
ILCS | -0.135 |
機 | -0.110 |
(_ | -0.107 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.106 |
belts | -0.104 |
Token | 14 |
Token ID | 1478 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
ippi | +0.194 |
Beir | +0.194 |
nton | +0.192 |
Gad | +0.180 |
Sas | +0.179 |
Neg logit contributions | |
ILCS | -0.262 |
機 | -0.215 |
(_ | -0.208 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.207 |
belts | -0.203 |
Token | } |
Token ID | 92 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ILCS | +0.644 |
機 | +0.527 |
(_ | +0.507 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.506 |
belts | +0.501 |
Neg logit contributions | |
ippi | -0.470 |
Beir | -0.468 |
nton | -0.465 |
Gad | -0.437 |
Sas | -0.434 |
Token | -> |
Token ID | 4613 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
ippi | +0.278 |
Beir | +0.277 |
nton | +0.273 |
Gad | +0.254 |
Sas | +0.252 |
Neg logit contributions | |
ILCS | -0.552 |
機 | -0.465 |
(_ | -0.450 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.449 |
belts | -0.445 |
Token | " |
Token ID | 366 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Beir | +1.930 |
ippi | +1.921 |
nton | +1.916 |
Gad | +1.814 |
Sas | +1.807 |
Neg logit contributions | |
ILCS | -2.306 |
機 | -1.877 |
(_ | -1.782 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.773 |
ÃÂ | -1.763 |
Token | S |
Token ID | 50 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
ILCS | +1.296 |
機 | +1.058 |
(_ | +1.026 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.018 |
Send | +0.997 |
Neg logit contributions | |
Beir | -1.086 |
ippi | -1.085 |
nton | -1.068 |
Gad | -1.013 |
spons | -1.009 |
Token | ", |
Token ID | 1600 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ippi | +0.115 |
Beir | +0.115 |
nton | +0.114 |
Gad | +0.106 |
Sas | +0.106 |
Neg logit contributions | |
ILCS | -0.182 |
機 | -0.151 |
(_ | -0.146 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.145 |
belts | -0.143 |
Token | { |
Token ID | 1391 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
ILCS | +1.041 |
機 | +0.854 |
(_ | +0.824 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.820 |
belts | +0.808 |
Neg logit contributions | |
ippi | -0.769 |
Beir | -0.768 |
nton | -0.760 |
Gad | -0.714 |
Sas | -0.712 |
Token | 2 |
Token ID | 17 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
ippi | +0.053 |
Beir | +0.053 |
nton | +0.053 |
Gad | +0.049 |
Sas | +0.049 |
Neg logit contributions | |
ILCS | -0.083 |
機 | -0.068 |
(_ | -0.066 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.066 |
belts | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ILCS | +1.329 |
機 | +1.072 |
(_ | +1.040 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.036 |
belts | +1.026 |
Neg logit contributions | |
ippi | -1.210 |
Beir | -1.206 |
nton | -1.195 |
Gad | -1.124 |
Sas | -1.123 |
Token | my |
Token ID | 616 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
ILCS | +2.018 |
機 | +1.669 |
(_ | +1.628 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.611 |
belts | +1.609 |
Neg logit contributions | |
ippi | -1.397 |
Beir | -1.397 |
nton | -1.386 |
Wonders | -1.286 |
Gad | -1.281 |
Token | ears |
Token ID | 11368 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
ILCS | +0.720 |
機 | +0.597 |
(_ | +0.582 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.577 |
belts | +0.574 |
Neg logit contributions | |
ippi | -0.472 |
Beir | -0.469 |
nton | -0.466 |
Gad | -0.433 |
Wonders | -0.432 |
Token | . |
Token ID | 13 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
ippi | +0.488 |
Beir | +0.487 |
nton | +0.483 |
Sas | +0.456 |
Gad | +0.456 |
Neg logit contributions | |
ILCS | -0.571 |
機 | -0.463 |
(_ | -0.441 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.439 |
belts | -0.430 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ippi | +0.292 |
Beir | +0.290 |
nton | +0.289 |
spons | +0.271 |
Gad | +0.269 |
Neg logit contributions | |
ILCS | -0.388 |
機 | -0.317 |
(_ | -0.307 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.306 |
belts | -0.300 |
Token |
|
Token ID | 198 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ippi | +0.961 |
Beir | +0.960 |
nton | +0.944 |
Gad | +0.879 |
spons | +0.877 |
Neg logit contributions | |
ILCS | -1.578 |
機 | -1.315 |
(_ | -1.279 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.270 |
belts | -1.252 |
Token | About |
Token ID | 8585 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
ippi | +0.912 |
Beir | +0.908 |
nton | +0.902 |
Gad | +0.851 |
Sas | +0.848 |
Neg logit contributions | |
ILCS | -1.090 |
機 | -0.881 |
(_ | -0.846 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.843 |
belts | -0.834 |
Token | that |
Token ID | 326 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
ILCS | +0.398 |
機 | +0.319 |
(_ | +0.311 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.307 |
belts | +0.307 |
Neg logit contributions | |
ippi | -0.360 |
nton | -0.353 |
Beir | -0.352 |
lished | -0.330 |
Gad | -0.329 |
Token | time |
Token ID | 640 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
ippi | +0.160 |
Beir | +0.159 |
nton | +0.158 |
Gad | +0.149 |
Sas | +0.148 |
Neg logit contributions | |
ILCS | -0.192 |
機 | -0.155 |
(_ | -0.150 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.149 |
belts | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ippi | +0.281 |
Beir | +0.281 |
nton | +0.278 |
Gad | +0.261 |
Sas | +0.260 |
Neg logit contributions | |
ILCS | -0.380 |
機 | -0.312 |
(_ | -0.301 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.299 |
belts | -0.295 |
Token | the |
Token ID | 262 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ippi | +0.220 |
Beir | +0.219 |
nton | +0.218 |
Gad | +0.203 |
Sas | +0.202 |
Neg logit contributions | |
ILCS | -0.285 |
機 | -0.233 |
(_ | -0.225 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.224 |
belts | -0.222 |
Token | gone |
Token ID | 3750 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ILCS | +0.290 |
機 | +0.236 |
belts | +0.229 |
(_ | +0.228 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.227 |
Neg logit contributions | |
ippi | -0.234 |
Beir | -0.232 |
nton | -0.231 |
Gad | -0.214 |
lished | -0.214 |
Token | through |
Token ID | 832 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
ILCS | +1.088 |
機 | +0.836 |
(_ | +0.808 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.798 |
belts | +0.797 |
Neg logit contributions | |
ippi | -1.257 |
Beir | -1.256 |
nton | -1.244 |
lished | -1.176 |
Gad | -1.171 |
Token | there |
Token ID | 612 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ILCS | +0.268 |
機 | +0.214 |
(_ | +0.208 |
belts | +0.207 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.206 |
Neg logit contributions | |
ippi | -0.239 |
Beir | -0.238 |
nton | -0.237 |
Gad | -0.222 |
Wonders | -0.221 |
Token | in |
Token ID | 287 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
ippi | +0.772 |
Beir | +0.772 |
nton | +0.765 |
Gad | +0.724 |
Sas | +0.722 |
Neg logit contributions | |
ILCS | -0.841 |
機 | -0.674 |
(_ | -0.646 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.643 |
belts | -0.632 |
Token | a |
Token ID | 257 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ILCS | +0.064 |
機 | +0.052 |
(_ | +0.050 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.050 |
belts | +0.050 |
Neg logit contributions | |
ippi | -0.053 |
Beir | -0.053 |
nton | -0.052 |
Gad | -0.049 |
Sas | -0.049 |
Token | rage |
Token ID | 14404 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ippi | +0.240 |
Beir | +0.239 |
nton | +0.237 |
Gad | +0.223 |
Sas | +0.222 |
Neg logit contributions | |
ILCS | -0.280 |
機 | -0.227 |
(_ | -0.218 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.217 |
belts | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
Beir | +0.366 |
ippi | +0.366 |
nton | +0.363 |
Gad | +0.344 |
Sas | +0.344 |
Neg logit contributions | |
ILCS | -0.399 |
機 | -0.321 |
(_ | -0.307 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.305 |
belts | -0.299 |
Token | ripped |
Token ID | 19551 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
ippi | +0.081 |
Beir | +0.080 |
nton | +0.080 |
Gad | +0.075 |
spons | +0.075 |
Neg logit contributions | |
ILCS | -0.093 |
機 | -0.075 |
(_ | -0.072 |
belts | -0.072 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
ILCS | +0.318 |
機 | +0.251 |
(_ | +0.242 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.240 |
belts | +0.239 |
Neg logit contributions | |
ippi | -0.321 |
Beir | -0.320 |
nton | -0.319 |
Gad | -0.300 |
Sas | -0.299 |
Token | place |
Token ID | 1295 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ILCS | +0.705 |
機 | +0.566 |
belts | +0.549 |
(_ | +0.546 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.541 |
Neg logit contributions | |
ippi | -0.644 |
Beir | -0.642 |
nton | -0.639 |
Gad | -0.597 |
Sas | -0.595 |
Token | apart |
Token ID | 5475 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ippi | +0.842 |
Beir | +0.841 |
nton | +0.834 |
Gad | +0.795 |
Sas | +0.793 |
Neg logit contributions | |
ILCS | -0.668 |
機 | -0.512 |
(_ | -0.487 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.484 |
belts | -0.475 |
Token | enter |
Token ID | 9255 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
ILCS | +1.898 |
機 | +1.507 |
(_ | +1.492 |
belts | +1.454 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.453 |
Neg logit contributions | |
nton | -1.516 |
ippi | -1.515 |
Beir | -1.512 |
Wonders | -1.420 |
Gad | -1.420 |
Token | forms |
Token ID | 5107 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ippi | +1.356 |
Beir | +1.353 |
nton | +1.348 |
Gad | +1.266 |
Sas | +1.263 |
Neg logit contributions | |
ILCS | -1.792 |
機 | -1.459 |
(_ | -1.407 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.406 |
belts | -1.371 |
Token | Cel |
Token ID | 15248 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ippi | +0.740 |
Beir | +0.738 |
nton | +0.731 |
Gad | +0.687 |
Sas | +0.684 |
Neg logit contributions | |
ILCS | -0.925 |
機 | -0.754 |
(_ | -0.727 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.723 |
belts | -0.714 |
Token | era |
Token ID | 8607 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
ILCS | +1.290 |
機 | +1.044 |
(_ | +1.018 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +1.009 |
Send | +0.994 |
Neg logit contributions | |
ippi | -1.003 |
Beir | -0.996 |
nton | -0.992 |
spons | -0.930 |
Gad | -0.922 |
Token | Gen |
Token ID | 5215 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ippi | +0.272 |
Beir | +0.271 |
nton | +0.269 |
Gad | +0.251 |
spons | +0.250 |
Neg logit contributions | |
ILCS | -0.350 |
機 | -0.285 |
(_ | -0.276 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.274 |
belts | -0.270 |
Token | omics |
Token ID | 31994 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
ippi | +0.536 |
Beir | +0.536 |
nton | +0.529 |
Gad | +0.486 |
Sas | +0.485 |
Neg logit contributions | |
ILCS | -1.069 |
機 | -0.903 |
(_ | -0.878 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.874 |
belts | -0.863 |
Token | and |
Token ID | 290 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
ippi | +2.949 |
Beir | +2.946 |
nton | +2.919 |
Gad | +2.783 |
Sas | +2.755 |
Neg logit contributions | |
ILCS | -4.077 |
機 | -3.355 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.211 |
(_ | -3.175 |
belts | -3.135 |
Token | begins |
Token ID | 6140 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
ILCS | +0.027 |
機 | +0.022 |
(_ | +0.021 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.021 |
belts | +0.021 |
Neg logit contributions | |
ippi | -0.023 |
Beir | -0.023 |
nton | -0.022 |
Gad | -0.021 |
spons | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
ippi | +1.076 |
Beir | +1.075 |
nton | +1.065 |
Gad | +1.006 |
Sas | +1.003 |
Neg logit contributions | |
ILCS | -1.230 |
機 | -0.992 |
(_ | -0.953 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.949 |
belts | -0.934 |
Token | private |
Token ID | 2839 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ippi | +0.583 |
Beir | +0.581 |
nton | +0.576 |
Gad | +0.541 |
Sas | +0.540 |
Neg logit contributions | |
ILCS | -0.669 |
機 | -0.542 |
(_ | -0.521 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.518 |
belts | -0.512 |
Token | effort |
Token ID | 3626 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
ippi | +1.550 |
Beir | +1.548 |
nton | +1.534 |
Gad | +1.454 |
Sas | +1.450 |
Neg logit contributions | |
ILCS | -1.606 |
機 | -1.280 |
(_ | -1.227 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.220 |
belts | -1.200 |
Token | came |
Token ID | 1625 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
ippi | +0.590 |
Beir | +0.588 |
nton | +0.581 |
Gad | +0.542 |
Sas | +0.541 |
Neg logit contributions | |
ILCS | -0.905 |
機 | -0.752 |
(_ | -0.728 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.723 |
belts | -0.715 |
Token | home |
Token ID | 1363 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Beir | +1.717 |
ippi | +1.714 |
nton | +1.701 |
Gad | +1.619 |
Sas | +1.615 |
Neg logit contributions | |
ILCS | -1.582 |
機 | -1.246 |
(_ | -1.181 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.174 |
belts | -1.150 |
Token | , |
Token ID | 11 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ippi | +0.763 |
Beir | +0.762 |
nton | +0.755 |
Gad | +0.711 |
Sas | +0.709 |
Neg logit contributions | |
ILCS | -0.949 |
機 | -0.772 |
(_ | -0.744 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.740 |
belts | -0.729 |
Token | the |
Token ID | 262 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
ippi | +0.399 |
Beir | +0.397 |
nton | +0.395 |
Gad | +0.373 |
Sas | +0.372 |
Neg logit contributions | |
ILCS | -0.405 |
機 | -0.319 |
(_ | -0.307 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.305 |
belts | -0.302 |
Token | D |
Token ID | 360 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ippi | +0.320 |
Beir | +0.318 |
nton | +0.315 |
Gad | +0.297 |
Sas | +0.296 |
Neg logit contributions | |
ILCS | -0.363 |
機 | -0.291 |
(_ | -0.281 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.279 |
belts | -0.276 |
Token | ugg |
Token ID | 6837 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
ILCS | +0.969 |
機 | +0.803 |
(_ | +0.784 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.776 |
umann | +0.768 |
Neg logit contributions | |
Beir | -0.623 |
ippi | -0.599 |
nton | -0.589 |
spons | -0.561 |
Sas | -0.560 |
Token | ars |
Token ID | 945 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ippi | +1.894 |
Beir | +1.888 |
nton | +1.868 |
Gad | +1.701 |
Sas | +1.697 |
Neg logit contributions | |
ILCS | -4.408 |
機 | -3.754 |
(_ | -3.631 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.627 |
belts | -3.579 |
Token | brought |
Token ID | 3181 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
ILCS | +0.598 |
機 | +0.490 |
(_ | +0.480 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.476 |
belts | +0.476 |
Neg logit contributions | |
ippi | -0.417 |
Beir | -0.417 |
nton | -0.411 |
Gad | -0.387 |
Sas | -0.384 |
Token | him |
Token ID | 683 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
ippi | +1.272 |
Beir | +1.270 |
nton | +1.261 |
Gad | +1.184 |
Sas | +1.181 |
Neg logit contributions | |
ILCS | -1.549 |
機 | -1.256 |
(_ | -1.211 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.205 |
belts | -1.190 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ippi | +0.237 |
Beir | +0.236 |
nton | +0.235 |
Gad | +0.221 |
Sas | +0.220 |
Neg logit contributions | |
ILCS | -0.270 |
機 | -0.217 |
(_ | -0.209 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.208 |
belts | -0.206 |
Token | the |
Token ID | 262 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ippi | +0.711 |
Beir | +0.703 |
nton | +0.701 |
Gad | +0.659 |
spons | +0.659 |
Neg logit contributions | |
ILCS | -0.798 |
機 | -0.637 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.614 |
(_ | -0.614 |
belts | -0.603 |
Token | News |
Token ID | 3000 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
ippi | +0.461 |
Beir | +0.460 |
nton | +0.455 |
Gad | +0.424 |
Sas | +0.422 |
Neg logit contributions | |
ILCS | -0.769 |
機 | -0.641 |
(_ | -0.621 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.618 |
belts | -0.610 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ippi | +0.368 |
Beir | +0.368 |
nton | +0.363 |
Gad | +0.339 |
Sas | +0.338 |
Neg logit contributions | |
ILCS | -0.607 |
機 | -0.506 |
(_ | -0.489 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.488 |
belts | -0.481 |
Token |
|
Token ID | 198 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
Beir | +0.086 |
ippi | +0.085 |
nton | +0.083 |
spons | +0.081 |
lished | +0.079 |
Neg logit contributions | |
ILCS | -0.123 |
機 | -0.101 |
(_ | -0.100 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.098 |
Send | -0.097 |
Token | The |
Token ID | 464 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
Beir | +0.069 |
ippi | +0.069 |
nton | +0.068 |
Gad | +0.065 |
Sas | +0.065 |
Neg logit contributions | |
ILCS | -0.074 |
機 | -0.059 |
(_ | -0.057 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.057 |
Send | -0.056 |
Token | Environmental |
Token ID | 13272 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
ILCS | +0.583 |
機 | +0.467 |
(_ | +0.450 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.447 |
belts | +0.445 |
Neg logit contributions | |
ippi | -0.508 |
Beir | -0.503 |
nton | -0.502 |
Gad | -0.471 |
spons | -0.468 |
Token | Protection |
Token ID | 9985 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
Beir | +2.723 |
ippi | +2.705 |
nton | +2.654 |
Gad | +2.531 |
Sas | +2.506 |
Neg logit contributions | |
ILCS | -4.011 |
機 | -3.344 |
(_ | -3.202 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.190 |
belts | -3.129 |
Token | Agency |
Token ID | 7732 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
Beir | +2.990 |
ippi | +2.973 |
nton | +2.953 |
Gad | +2.820 |
Sas | +2.818 |
Neg logit contributions | |
ILCS | -2.808 |
機 | -2.243 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.110 |
(_ | -2.110 |
ーテ | -2.061 |
Token | � |
Token ID | 447 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
ippi | +1.489 |
Beir | +1.487 |
nton | +1.472 |
Gad | +1.384 |
Sas | +1.380 |
Neg logit contributions | |
ILCS | -1.929 |
機 | -1.575 |
(_ | -1.519 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.511 |
belts | -1.491 |
Token | � |
Token ID | 247 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
ippi | +0.470 |
Beir | +0.466 |
nton | +0.465 |
Sas | +0.443 |
Gad | +0.442 |
Neg logit contributions | |
ILCS | -0.378 |
機 | -0.290 |
(_ | -0.274 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.272 |
belts | -0.270 |
Token | s |
Token ID | 82 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Beir | +0.542 |
ippi | +0.540 |
nton | +0.535 |
Gad | +0.505 |
Sas | +0.503 |
Neg logit contributions | |
ILCS | -0.670 |
機 | -0.544 |
(_ | -0.525 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.523 |
belts | -0.514 |
Token | Office |
Token ID | 4452 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ippi | +0.070 |
Beir | +0.070 |
nton | +0.070 |
Gad | +0.065 |
Sas | +0.065 |
Neg logit contributions | |
ILCS | -0.076 |
機 | -0.061 |
(_ | -0.059 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.058 |
belts | -0.058 |
Token | � |
Token ID | 564 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ILCS | +0.389 |
機 | +0.319 |
(_ | +0.309 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.308 |
belts | +0.300 |
Neg logit contributions | |
ippi | -0.302 |
Beir | -0.300 |
nton | -0.299 |
spons | -0.286 |
lished | -0.278 |
Token | � |
Token ID | 250 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
ILCS | +0.193 |
機 | +0.146 |
(_ | +0.139 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.138 |
belts | +0.135 |
Neg logit contributions | |
ippi | -0.259 |
Beir | -0.259 |
nton | -0.257 |
Gad | -0.245 |
Sas | -0.245 |
Token | When |
Token ID | 2215 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
ILCS | +0.128 |
機 | +0.104 |
(_ | +0.100 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.100 |
belts | +0.098 |
Neg logit contributions | |
Beir | -0.106 |
ippi | -0.105 |
nton | -0.104 |
Gad | -0.098 |
spons | -0.098 |
Token | cal |
Token ID | 2386 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
ippi | +1.813 |
Beir | +1.811 |
nton | +1.792 |
Gad | +1.692 |
Sas | +1.688 |
Neg logit contributions | |
ILCS | -2.234 |
機 | -1.811 |
(_ | -1.744 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.736 |
belts | -1.706 |
Token | ving |
Token ID | 1075 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ILCS | +0.530 |
機 | +0.408 |
(_ | +0.396 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.391 |
belts | +0.384 |
Neg logit contributions | |
Beir | -0.631 |
ippi | -0.626 |
nton | -0.621 |
Sas | -0.593 |
Gad | -0.592 |
Token | fronts |
Token ID | 29324 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
Beir | +0.701 |
ippi | +0.701 |
nton | +0.694 |
Gad | +0.650 |
Sas | +0.648 |
Neg logit contributions | |
ILCS | -0.924 |
機 | -0.756 |
(_ | -0.732 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.727 |
belts | -0.720 |
Token | rec |
Token ID | 664 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ippi | +2.567 |
Beir | +2.557 |
nton | +2.532 |
Sas | +2.407 |
Gad | +2.405 |
Neg logit contributions | |
ILCS | -3.037 |
機 | -2.463 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -2.335 |
(_ | -2.328 |
ÃÂ | -2.298 |
Token | ede |
Token ID | 18654 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
ippi | +0.099 |
Beir | +0.099 |
nton | +0.098 |
Gad | +0.094 |
Sas | +0.094 |
Neg logit contributions | |
ILCS | -0.066 |
機 | -0.049 |
(_ | -0.047 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.046 |
belts | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ippi | +1.314 |
Beir | +1.305 |
nton | +1.290 |
Sas | +1.223 |
Gad | +1.220 |
Neg logit contributions | |
ILCS | -1.727 |
機 | -1.407 |
(_ | -1.351 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.344 |
belts | -1.319 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ippi | +1.038 |
Beir | +1.038 |
nton | +1.028 |
Gad | +0.974 |
Sas | +0.970 |
Neg logit contributions | |
ILCS | -1.054 |
機 | -0.839 |
(_ | -0.804 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.800 |
belts | -0.788 |
Token | point |
Token ID | 966 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ippi | +0.934 |
Beir | +0.931 |
nton | +0.920 |
Gad | +0.871 |
Sas | +0.864 |
Neg logit contributions | |
ILCS | -0.985 |
機 | -0.790 |
(_ | -0.759 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.755 |
belts | -0.745 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ILCS | +0.635 |
機 | +0.512 |
(_ | +0.495 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | +0.492 |
belts | +0.486 |
Neg logit contributions | |
ippi | -0.541 |
Beir | -0.538 |
nton | -0.533 |
Gad | -0.503 |
Sas | -0.502 |
Token | � |
Token ID | 447 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
ippi | +0.817 |
Beir | +0.815 |
nton | +0.808 |
Gad | +0.763 |
Sas | +0.761 |
Neg logit contributions | |
ILCS | -0.900 |
機 | -0.723 |
(_ | -0.694 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.691 |
belts | -0.679 |
Token | � |
Token ID | 251 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ippi | +0.439 |
Beir | +0.438 |
nton | +0.435 |
Gad | +0.414 |
Sas | +0.413 |
Neg logit contributions | |
ILCS | -0.370 |
機 | -0.285 |
(_ | -0.270 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.269 |
belts | -0.266 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
ippi | +0.348 |
Beir | +0.347 |
nton | +0.344 |
Gad | +0.323 |
Sas | +0.322 |
Neg logit contributions | |
ILCS | -0.455 |
機 | -0.372 |
(_ | -0.359 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.358 |
belts | -0.351 |
Token |
|
Token ID | 198 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Beir | +0.815 |
ippi | +0.815 |
nton | +0.800 |
spons | +0.749 |
Gad | +0.743 |
Neg logit contributions | |
ILCS | -1.309 |
機 | -1.090 |
(_ | -1.062 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.053 |
belts | -1.037 |
Token | Inter |
Token ID | 9492 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
ippi | +0.688 |
Beir | +0.688 |
nton | +0.681 |
Gad | +0.645 |
Sas | +0.643 |
Neg logit contributions | |
ILCS | -0.742 |
機 | -0.596 |
(_ | -0.572 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.569 |
belts | -0.558 |
Token | rupt |
Token ID | 3622 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ippi | +2.742 |
Beir | +2.729 |
nton | +2.723 |
Gad | +2.535 |
Sas | +2.516 |
Neg logit contributions | |
ILCS | -4.032 |
機 | -3.321 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -3.196 |
(_ | -3.181 |
belts | -3.158 |
Token | ing |
Token ID | 278 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ippi | +0.953 |
Beir | +0.953 |
nton | +0.942 |
Gad | +0.876 |
Sas | +0.873 |
Neg logit contributions | |
ILCS | -1.593 |
機 | -1.331 |
(_ | -1.289 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.282 |
belts | -1.267 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ippi | +0.841 |
nton | +0.837 |
Beir | +0.834 |
spons | +0.776 |
Wonders | +0.776 |
Neg logit contributions | |
ILCS | -1.045 |
機 | -0.855 |
(_ | -0.829 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.823 |
belts | -0.815 |
Token | question |
Token ID | 1808 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
ippi | +0.213 |
Beir | +0.211 |
nton | +0.210 |
Gad | +0.197 |
Sas | +0.197 |
Neg logit contributions | |
ILCS | -0.207 |
機 | -0.165 |
(_ | -0.159 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -0.158 |
belts | -0.157 |
Token | er |
Token ID | 263 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ippi | +1.218 |
Beir | +1.216 |
nton | +1.203 |
Gad | +1.132 |
Sas | +1.128 |
Neg logit contributions | |
ILCS | -1.621 |
機 | -1.328 |
(_ | -1.280 |
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ | -1.274 |
belts | -1.256 |