Token | the |
Token ID | 262 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Fre | +0.014 |
bel | +0.014 |
Kay | +0.014 |
Hel | +0.013 |
J | +0.013 |
Neg logit contributions | |
oscope | -0.022 |
His | -0.022 |
omm | -0.021 |
DVD | -0.021 |
seventy | -0.021 |
Token | robot |
Token ID | 9379 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
His | +0.099 |
omm | +0.099 |
x | +0.096 |
oscope | +0.096 |
DVD | +0.095 |
Neg logit contributions | |
bel | -0.120 |
Fre | -0.116 |
Kay | -0.111 |
Hel | -0.111 |
Ag | -0.109 |
Token | found |
Token ID | 1043 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
omm | +0.397 |
x | +0.382 |
His | +0.374 |
oscope | +0.369 |
DVD | +0.368 |
Neg logit contributions | |
bel | -0.387 |
Fre | -0.362 |
Hel | -0.355 |
Kay | -0.352 |
Ag | -0.347 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
bel | +0.142 |
Fre | +0.138 |
Kay | +0.133 |
Hel | +0.133 |
Ag | +0.131 |
Neg logit contributions | |
omm | -0.116 |
His | -0.115 |
x | -0.115 |
oscope | -0.114 |
DVD | -0.114 |
Token | big |
Token ID | 1263 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
omm | +0.111 |
His | +0.109 |
oscope | +0.109 |
x | +0.106 |
DVD | +0.106 |
Neg logit contributions | |
bel | -0.104 |
Fre | -0.100 |
Kay | -0.097 |
Hel | -0.096 |
Ag | -0.095 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
common | +0.113 |
perspective | +0.113 |
bel | +0.112 |
Fre | +0.109 |
Hel | +0.107 |
Neg logit contributions | |
omm | -0.114 |
oll | -0.108 |
His | -0.107 |
oscope | -0.105 |
icle | -0.100 |
Token | in |
Token ID | 287 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
omm | +0.999 |
His | +0.974 |
x | +0.963 |
oscope | +0.945 |
Promise | +0.941 |
Neg logit contributions | |
bel | -0.666 |
Fre | -0.599 |
ies | -0.586 |
Ag | -0.574 |
ora | -0.571 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
bel | +0.039 |
Fre | +0.039 |
Kay | +0.037 |
Hel | +0.037 |
Ag | +0.037 |
Neg logit contributions | |
omm | -0.030 |
His | -0.030 |
x | -0.030 |
oscope | -0.030 |
DVD | -0.029 |
Token | garden |
Token ID | 11376 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Hel | +0.014 |
bel | +0.014 |
valleys | +0.014 |
hills | +0.014 |
J | +0.013 |
Neg logit contributions | |
omm | -0.025 |
seventy | -0.024 |
icle | -0.024 |
oll | -0.024 |
oscope | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
bel | +0.205 |
Fre | +0.201 |
Kay | +0.193 |
Hel | +0.193 |
Ag | +0.190 |
Neg logit contributions | |
His | -0.201 |
omm | -0.199 |
oscope | -0.199 |
x | -0.198 |
DVD | -0.197 |
Token | The |
Token ID | 383 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Fre | +0.021 |
Kay | +0.021 |
Hel | +0.021 |
Ag | +0.021 |
J | +0.021 |
Neg logit contributions | |
oscope | -0.015 |
x | -0.014 |
boo | -0.014 |
omm | -0.013 |
oll | -0.013 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
omm | +0.330 |
His | +0.328 |
oscope | +0.327 |
x | +0.326 |
DVD | +0.324 |
Neg logit contributions | |
bel | -0.289 |
Fre | -0.283 |
Kay | -0.272 |
Hel | -0.270 |
Ag | -0.266 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
omm | +0.156 |
x | +0.154 |
His | +0.154 |
oscope | +0.154 |
DVD | +0.154 |
Neg logit contributions | |
bel | -0.109 |
Fre | -0.105 |
Kay | -0.100 |
Hel | -0.100 |
Ag | -0.098 |
Token | look |
Token ID | 804 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
bel | +0.084 |
Fre | +0.083 |
Kay | +0.080 |
Hel | +0.078 |
Ag | +0.077 |
Neg logit contributions | |
omm | -0.074 |
DVD | -0.071 |
oscope | -0.071 |
x | -0.069 |
His | -0.069 |
Token | at |
Token ID | 379 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
bel | +0.258 |
Fre | +0.251 |
Kay | +0.243 |
Hel | +0.241 |
Ag | +0.238 |
Neg logit contributions | |
omm | -0.208 |
His | -0.207 |
x | -0.207 |
oscope | -0.205 |
DVD | -0.205 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
His | +0.085 |
x | +0.084 |
omm | +0.083 |
oscope | +0.083 |
DVD | +0.083 |
Neg logit contributions | |
bel | -0.106 |
Fre | -0.103 |
Hel | -0.100 |
Kay | -0.099 |
Ag | -0.099 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.007 |
Fre | +0.007 |
Kay | +0.007 |
Hel | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
His | -0.006 |
omm | -0.006 |
x | -0.006 |
oscope | -0.006 |
DVD | -0.006 |
Token | some |
Token ID | 617 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
omm | +0.881 |
His | +0.871 |
x | +0.856 |
DVD | +0.855 |
oscope | +0.854 |
Neg logit contributions | |
bel | -0.776 |
Fre | -0.747 |
Kay | -0.708 |
Hel | -0.695 |
ora | -0.693 |
Token | more |
Token ID | 517 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
x | +0.103 |
apple | +0.101 |
His | +0.101 |
magnet | +0.101 |
oscope | +0.101 |
Neg logit contributions | |
bel | -0.110 |
Fre | -0.109 |
Hel | -0.106 |
Kay | -0.105 |
Ag | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
apple | +0.141 |
His | +0.139 |
x | +0.138 |
magnet | +0.137 |
oscope | +0.136 |
Neg logit contributions | |
bel | -0.160 |
Hel | -0.159 |
Fre | -0.157 |
Ag | -0.153 |
Kay | -0.151 |
Token | His |
Token ID | 2399 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
Fre | +0.019 |
Kay | +0.018 |
bel | +0.018 |
Hel | +0.018 |
Ag | +0.018 |
Neg logit contributions | |
x | -0.014 |
oscope | -0.014 |
DVD | -0.014 |
omm | -0.013 |
boo | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
DVD | +0.408 |
oscope | +0.404 |
omm | +0.392 |
x | +0.391 |
penter | +0.385 |
Neg logit contributions | |
bel | -0.595 |
Fre | -0.569 |
Kay | -0.553 |
Hel | -0.538 |
ora | -0.535 |
Token | " |
Token ID | 366 |
Feature activation | +5.66e+00 |
Pos logit contributions | |
His | +0.135 |
apple | +0.128 |
omm | +0.121 |
Your | +0.120 |
seventy | +0.115 |
Neg logit contributions | |
bel | -0.220 |
Hel | -0.205 |
Fre | -0.203 |
Kay | -0.203 |
ymes | -0.202 |
Token | Don |
Token ID | 3987 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
omm | +0.452 |
x | +0.450 |
His | +0.449 |
DVD | +0.446 |
oscope | +0.446 |
Neg logit contributions | |
bel | -0.301 |
Fre | -0.290 |
Kay | -0.278 |
Hel | -0.277 |
Ag | -0.271 |
Token | 't |
Token ID | 470 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Kay | +0.070 |
Ag | +0.069 |
bel | +0.068 |
Hel | +0.068 |
Fre | +0.065 |
Neg logit contributions | |
urger | -0.109 |
DVD | -0.108 |
oscope | -0.107 |
microwave | -0.106 |
boo | -0.104 |
Token | eat |
Token ID | 4483 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
omm | +0.070 |
DVD | +0.070 |
x | +0.069 |
His | +0.068 |
oscope | +0.068 |
Neg logit contributions | |
bel | -0.072 |
Fre | -0.070 |
Kay | -0.068 |
Hel | -0.067 |
Ag | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
omm | +0.373 |
oscope | +0.370 |
His | +0.370 |
DVD | +0.366 |
x | +0.361 |
Neg logit contributions | |
bel | -0.386 |
Fre | -0.383 |
Kay | -0.361 |
Hel | -0.355 |
J | -0.355 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.008 |
Fre | +0.008 |
Kay | +0.007 |
common | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
His | -0.006 |
omm | -0.006 |
oscope | -0.006 |
DVD | -0.006 |
penter | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
x | +0.842 |
omm | +0.842 |
His | +0.840 |
DVD | +0.834 |
oscope | +0.830 |
Neg logit contributions | |
bel | -0.816 |
Fre | -0.776 |
Kay | -0.735 |
Ag | -0.724 |
ora | -0.721 |
Token | it |
Token ID | 340 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Fre | +0.073 |
bel | +0.069 |
Kay | +0.068 |
Ag | +0.066 |
J | +0.064 |
Neg logit contributions | |
oscope | -0.099 |
DVD | -0.095 |
omm | -0.094 |
x | -0.091 |
oll | -0.089 |
Token | 's |
Token ID | 338 |
Feature activation | +7.84e+00 |
Pos logit contributions | |
omm | +0.007 |
DVD | +0.007 |
His | +0.007 |
x | +0.007 |
icle | +0.007 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.010 |
ies | -0.010 |
ora | -0.010 |
Hel | -0.009 |
Token | bad |
Token ID | 2089 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
DVD | +0.558 |
His | +0.551 |
omm | +0.547 |
penter | +0.542 |
oscope | +0.537 |
Neg logit contributions | |
common | -0.460 |
ies | -0.440 |
bel | -0.437 |
Fre | -0.426 |
Ag | -0.402 |
Token | ." |
Token ID | 526 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
bel | +0.001 |
Fre | +0.001 |
ies | +0.001 |
Kay | +0.001 |
Hel | +0.001 |
Neg logit contributions | |
omm | -0.001 |
x | -0.001 |
His | -0.001 |
DVD | -0.001 |
oscope | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
His | +0.086 |
oscope | +0.082 |
x | +0.082 |
magnet | +0.082 |
DVD | +0.081 |
Neg logit contributions | |
bel | -0.103 |
Fre | -0.102 |
Hel | -0.099 |
Kay | -0.099 |
Ag | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
omm | +0.156 |
x | +0.154 |
His | +0.154 |
oscope | +0.154 |
DVD | +0.154 |
Neg logit contributions | |
bel | -0.109 |
Fre | -0.105 |
Kay | -0.100 |
Hel | -0.100 |
Ag | -0.098 |
Token | see |
Token ID | 766 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
bel | +0.084 |
Fre | +0.083 |
Kay | +0.080 |
Hel | +0.078 |
Ag | +0.077 |
Neg logit contributions | |
omm | -0.074 |
DVD | -0.071 |
oscope | -0.071 |
x | -0.069 |
His | -0.069 |
Token | what |
Token ID | 644 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
bel | +0.361 |
Fre | +0.359 |
Kay | +0.345 |
Hel | +0.341 |
Ag | +0.332 |
Neg logit contributions | |
omm | -0.343 |
oscope | -0.329 |
His | -0.324 |
DVD | -0.320 |
x | -0.316 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
His | +0.072 |
x | +0.070 |
DVD | +0.068 |
magnet | +0.068 |
oscope | +0.067 |
Neg logit contributions | |
bel | -0.095 |
Fre | -0.092 |
Kay | -0.089 |
Hel | -0.088 |
Ag | -0.088 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.007 |
Fre | +0.007 |
Kay | +0.007 |
Hel | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
omm | -0.007 |
His | -0.006 |
x | -0.006 |
oscope | -0.006 |
DVD | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
omm | +0.838 |
x | +0.831 |
His | +0.831 |
DVD | +0.826 |
oscope | +0.824 |
Neg logit contributions | |
bel | -0.814 |
Fre | -0.787 |
Kay | -0.757 |
Hel | -0.750 |
Ag | -0.743 |
Token | do |
Token ID | 466 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
His | +0.072 |
x | +0.072 |
oscope | +0.071 |
omm | +0.070 |
magnet | +0.070 |
Neg logit contributions | |
bel | -0.108 |
Fre | -0.106 |
Hel | -0.103 |
Kay | -0.102 |
Ag | -0.101 |
Token | in |
Token ID | 287 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Fre | +0.085 |
bel | +0.084 |
Kay | +0.081 |
Hel | +0.081 |
Ag | +0.079 |
Neg logit contributions | |
His | -0.076 |
x | -0.075 |
oscope | -0.075 |
DVD | -0.074 |
omm | -0.074 |
Token | the |
Token ID | 262 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
bel | +0.047 |
Fre | +0.045 |
Hel | +0.044 |
Kay | +0.044 |
Ag | +0.044 |
Neg logit contributions | |
x | -0.035 |
His | -0.034 |
omm | -0.034 |
magnet | -0.034 |
oscope | -0.034 |
Token | water |
Token ID | 1660 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
bel | +0.026 |
Fre | +0.025 |
Hel | +0.024 |
Kay | +0.024 |
Ag | +0.023 |
Neg logit contributions | |
omm | -0.022 |
His | -0.021 |
DVD | -0.021 |
oscope | -0.021 |
x | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
omm | +0.287 |
His | +0.274 |
oscope | +0.274 |
x | +0.272 |
DVD | +0.272 |
Neg logit contributions | |
bel | -0.293 |
Fre | -0.288 |
Hel | -0.275 |
Kay | -0.274 |
Ag | -0.267 |
Token | got |
Token ID | 1392 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
omm | +0.292 |
x | +0.290 |
His | +0.289 |
DVD | +0.287 |
oscope | +0.286 |
Neg logit contributions | |
bel | -0.250 |
Fre | -0.240 |
Kay | -0.230 |
Hel | -0.230 |
Ag | -0.225 |
Token | from |
Token ID | 422 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
His | +0.127 |
x | +0.125 |
omm | +0.122 |
DVD | +0.122 |
oscope | +0.121 |
Neg logit contributions | |
bel | -0.152 |
Fre | -0.152 |
Kay | -0.147 |
Hel | -0.147 |
Ag | -0.143 |
Token | the |
Token ID | 262 |
Feature activation | +7.38e-02 |
Pos logit contributions | |
x | +0.280 |
His | +0.279 |
omm | +0.277 |
oscope | +0.276 |
DVD | +0.275 |
Neg logit contributions | |
bel | -0.363 |
Fre | -0.355 |
Kay | -0.344 |
Hel | -0.342 |
Ag | -0.338 |
Token | magical |
Token ID | 10883 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
His | +0.004 |
omm | +0.004 |
oscope | +0.004 |
x | +0.004 |
DVD | +0.004 |
Neg logit contributions | |
bel | -0.006 |
Fre | -0.005 |
Kay | -0.005 |
Hel | -0.005 |
Ag | -0.005 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.025 |
Fre | +0.024 |
Kay | +0.023 |
Hel | +0.023 |
Ag | +0.023 |
Neg logit contributions | |
omm | -0.021 |
His | -0.021 |
x | -0.020 |
oscope | -0.020 |
DVD | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
omm | +0.872 |
x | +0.858 |
DVD | +0.849 |
His | +0.842 |
oscope | +0.837 |
Neg logit contributions | |
bel | -0.806 |
Fre | -0.748 |
Kay | -0.711 |
Hel | -0.705 |
Ag | -0.705 |
Token | |
Token ID | 220 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Fre | +0.013 |
Kay | +0.013 |
Hel | +0.012 |
Ag | +0.012 |
J | +0.012 |
Neg logit contributions | |
x | -0.009 |
oscope | -0.009 |
boo | -0.009 |
omm | -0.008 |
DVD | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
oscope | +0.101 |
x | +0.100 |
boo | +0.099 |
omm | +0.097 |
DVD | +0.096 |
Neg logit contributions | |
bel | -0.079 |
Kay | -0.076 |
Fre | -0.075 |
Hel | -0.075 |
J | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
omm | +0.008 |
x | +0.008 |
oscope | +0.008 |
DVD | +0.007 |
magnet | +0.007 |
Neg logit contributions | |
bel | -0.008 |
Fre | -0.008 |
Kay | -0.008 |
Hel | -0.008 |
J | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
omm | +0.007 |
x | +0.007 |
oscope | +0.007 |
DVD | +0.007 |
His | +0.007 |
Neg logit contributions | |
bel | -0.005 |
Fre | -0.005 |
Kay | -0.005 |
Hel | -0.005 |
Ag | -0.005 |
Token | ue |
Token ID | 518 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
bel | +0.208 |
Fre | +0.207 |
Kay | +0.202 |
Hel | +0.198 |
Ag | +0.198 |
Neg logit contributions | |
His | -0.153 |
omm | -0.150 |
x | -0.150 |
oscope | -0.150 |
DVD | -0.149 |
Token | sp |
Token ID | 599 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
His | +0.102 |
oscope | +0.100 |
omm | +0.100 |
x | +0.099 |
DVD | +0.098 |
Neg logit contributions | |
bel | -0.109 |
Fre | -0.107 |
Hel | -0.103 |
Kay | -0.102 |
Ag | -0.102 |
Token | its |
Token ID | 896 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Hel | +0.220 |
Fre | +0.215 |
bel | +0.210 |
Kay | +0.207 |
Ag | +0.207 |
Neg logit contributions | |
omm | -0.293 |
His | -0.282 |
oll | -0.276 |
x | -0.274 |
icle | -0.271 |
Token | out |
Token ID | 503 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
bel | +0.121 |
Fre | +0.118 |
Kay | +0.114 |
Hel | +0.114 |
Ag | +0.113 |
Neg logit contributions | |
His | -0.096 |
x | -0.096 |
omm | -0.095 |
DVD | -0.094 |
oscope | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
His | +0.102 |
x | +0.100 |
apple | +0.097 |
omm | +0.095 |
DVD | +0.095 |
Neg logit contributions | |
bel | -0.149 |
Fre | -0.147 |
Ag | -0.146 |
Hel | -0.145 |
Kay | -0.142 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.008 |
Fre | +0.008 |
Kay | +0.007 |
Hel | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
omm | -0.006 |
His | -0.006 |
x | -0.006 |
oscope | -0.006 |
DVD | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
omm | +0.850 |
x | +0.841 |
His | +0.839 |
DVD | +0.826 |
oscope | +0.823 |
Neg logit contributions | |
bel | -0.808 |
Fre | -0.759 |
Kay | -0.724 |
Hel | -0.714 |
Ag | -0.711 |
Token | She |
Token ID | 1375 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Fre | +0.011 |
Kay | +0.011 |
bel | +0.011 |
Hel | +0.010 |
Ag | +0.010 |
Neg logit contributions | |
x | -0.011 |
oscope | -0.011 |
DVD | -0.010 |
boo | -0.010 |
motorcycle | -0.010 |
Token | sp |
Token ID | 599 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
bel | +0.153 |
Fre | +0.149 |
Kay | +0.142 |
Hel | +0.140 |
Ag | +0.138 |
Neg logit contributions | |
omm | -0.151 |
x | -0.150 |
DVD | -0.149 |
oscope | -0.149 |
icle | -0.147 |
Token | its |
Token ID | 896 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Hel | +0.308 |
bel | +0.306 |
Fre | +0.305 |
Ag | +0.293 |
Kay | +0.293 |
Neg logit contributions | |
omm | -0.338 |
oll | -0.328 |
His | -0.323 |
x | -0.321 |
icle | -0.312 |
Token | out |
Token ID | 503 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
bel | +0.161 |
Fre | +0.157 |
Kay | +0.152 |
Hel | +0.151 |
Ag | +0.149 |
Neg logit contributions | |
omm | -0.138 |
His | -0.137 |
x | -0.136 |
oscope | -0.136 |
DVD | -0.135 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
His | +0.102 |
omm | +0.101 |
x | +0.101 |
DVD | +0.101 |
oscope | +0.100 |
Neg logit contributions | |
bel | -0.160 |
Fre | -0.159 |
Kay | -0.153 |
Hel | -0.152 |
Ag | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
His | +0.001 |
oscope | +0.001 |
omm | +0.001 |
x | +0.001 |
DVD | +0.001 |
Neg logit contributions | |
bel | -0.001 |
Fre | -0.001 |
Kay | -0.001 |
Hel | -0.001 |
Ag | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
x | +0.045 |
oscope | +0.043 |
omm | +0.041 |
boo | +0.041 |
DVD | +0.040 |
Neg logit contributions | |
Fre | -0.059 |
Hel | -0.058 |
Kay | -0.058 |
Ag | -0.057 |
bel | -0.057 |
Token | ate |
Token ID | 15063 |
Feature activation | +5.61e+00 |
Pos logit contributions | |
bel | +0.110 |
Fre | +0.107 |
Kay | +0.102 |
Hel | +0.102 |
Ag | +0.100 |
Neg logit contributions | |
omm | -0.118 |
His | -0.118 |
x | -0.118 |
oscope | -0.117 |
DVD | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
His | +0.335 |
omm | +0.334 |
x | +0.332 |
oscope | +0.329 |
DVD | +0.329 |
Neg logit contributions | |
bel | -0.413 |
Fre | -0.402 |
Kay | -0.389 |
Hel | -0.388 |
Ag | -0.382 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.085 |
Fre | +0.079 |
ies | +0.078 |
common | +0.076 |
ora | +0.076 |
Neg logit contributions | |
omm | -0.069 |
penter | -0.067 |
oscope | -0.065 |
DVD | -0.065 |
x | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
x | +0.790 |
omm | +0.787 |
DVD | +0.778 |
His | +0.771 |
oscope | +0.765 |
Neg logit contributions | |
bel | -0.885 |
Fre | -0.830 |
Kay | -0.795 |
Hel | -0.785 |
J | -0.780 |
Token | they |
Token ID | 484 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
His | +0.083 |
oscope | +0.082 |
DVD | +0.080 |
magnet | +0.080 |
apple | +0.080 |
Neg logit contributions | |
bel | -0.109 |
Fre | -0.108 |
Kay | -0.104 |
Hel | -0.103 |
Ag | -0.103 |
Token | continued |
Token ID | 3767 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
bel | +0.204 |
Fre | +0.203 |
Kay | +0.197 |
Ag | +0.194 |
Hel | +0.191 |
Neg logit contributions | |
His | -0.175 |
oscope | -0.174 |
DVD | -0.170 |
magnet | -0.170 |
apple | -0.168 |
Token | on |
Token ID | 319 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
His | +0.073 |
omm | +0.072 |
DVD | +0.072 |
x | +0.072 |
oscope | +0.072 |
Neg logit contributions | |
bel | -0.058 |
Fre | -0.057 |
Kay | -0.055 |
Hel | -0.054 |
Ag | -0.054 |
Token | their |
Token ID | 511 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
His | +0.059 |
apple | +0.059 |
DVD | +0.058 |
x | +0.057 |
magnet | +0.057 |
Neg logit contributions | |
bel | -0.076 |
Fre | -0.073 |
Ag | -0.071 |
Kay | -0.071 |
ora | -0.070 |
Token | bite |
Token ID | 13197 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
bel | +0.104 |
Fre | +0.102 |
Kay | +0.100 |
Ag | +0.098 |
Hel | +0.097 |
Neg logit contributions | |
His | -0.074 |
x | -0.071 |
magnet | -0.071 |
apple | -0.070 |
DVD | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
His | +0.443 |
x | +0.428 |
omm | +0.427 |
oscope | +0.426 |
apple | +0.424 |
Neg logit contributions | |
bel | -0.531 |
Fre | -0.523 |
Kay | -0.506 |
Hel | -0.505 |
Ag | -0.500 |
Token |
|
Token ID | 198 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
x | +0.044 |
oscope | +0.043 |
omm | +0.040 |
DVD | +0.040 |
motorcycle | +0.039 |
Neg logit contributions | |
Fre | -0.058 |
bel | -0.058 |
Kay | -0.057 |
Hel | -0.057 |
Ag | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
omm | +0.045 |
x | +0.045 |
oscope | +0.045 |
DVD | +0.044 |
magnet | +0.044 |
Neg logit contributions | |
bel | -0.051 |
Fre | -0.050 |
Kay | -0.049 |
Hel | -0.049 |
J | -0.048 |
Token | The |
Token ID | 464 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
His | +0.041 |
omm | +0.041 |
x | +0.040 |
oscope | +0.040 |
DVD | +0.040 |
Neg logit contributions | |
bel | -0.029 |
Fre | -0.028 |
Kay | -0.026 |
Hel | -0.026 |
Ag | -0.026 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.112 |
Fre | +0.107 |
Hel | +0.103 |
Kay | +0.102 |
Ag | +0.101 |
Neg logit contributions | |
His | -0.093 |
omm | -0.092 |
DVD | -0.087 |
oscope | -0.087 |
Your | -0.086 |
Token | belonged |
Token ID | 19611 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
omm | +0.834 |
x | +0.826 |
DVD | +0.825 |
His | +0.821 |
oscope | +0.811 |
Neg logit contributions | |
bel | -0.826 |
Fre | -0.780 |
Kay | -0.752 |
Hel | -0.748 |
J | -0.734 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
His | +0.435 |
omm | +0.427 |
magnet | +0.424 |
x | +0.424 |
oscope | +0.422 |
Neg logit contributions | |
bel | -0.392 |
Fre | -0.391 |
Hel | -0.370 |
Kay | -0.370 |
Ag | -0.357 |
Token | little |
Token ID | 1310 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
bel | +0.158 |
Fre | +0.157 |
Kay | +0.152 |
Hel | +0.151 |
Ag | +0.148 |
Neg logit contributions | |
omm | -0.129 |
oscope | -0.128 |
DVD | -0.126 |
x | -0.126 |
His | -0.125 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
x | +0.104 |
apple | +0.103 |
magnet | +0.103 |
DVD | +0.099 |
motorcycle | +0.098 |
Neg logit contributions | |
bel | -0.176 |
Fre | -0.170 |
Kay | -0.166 |
Ag | -0.166 |
Hel | -0.163 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
omm | +0.092 |
icle | +0.087 |
x | +0.086 |
DVD | +0.085 |
His | +0.083 |
Neg logit contributions | |
bel | -0.064 |
Fre | -0.060 |
ies | -0.060 |
Hel | -0.059 |
ora | -0.058 |
Token | juice |
Token ID | 13135 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
apple | +0.206 |
x | +0.206 |
oscope | +0.203 |
His | +0.201 |
DVD | +0.200 |
Neg logit contributions | |
Fre | -0.257 |
bel | -0.255 |
Hel | -0.254 |
Kay | -0.254 |
Ag | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
omm | +0.350 |
His | +0.348 |
x | +0.346 |
oscope | +0.345 |
DVD | +0.344 |
Neg logit contributions | |
bel | -0.437 |
Fre | -0.430 |
Kay | -0.416 |
Hel | -0.415 |
Ag | -0.407 |
Token | Amy |
Token ID | 14235 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
x | +0.024 |
oscope | +0.023 |
boo | +0.022 |
omm | +0.021 |
magnet | +0.021 |
Neg logit contributions | |
Fre | -0.025 |
Kay | -0.024 |
Ag | -0.024 |
Hel | -0.024 |
J | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
bel | +0.017 |
Fre | +0.017 |
Kay | +0.016 |
Hel | +0.016 |
Ag | +0.016 |
Neg logit contributions | |
omm | -0.017 |
x | -0.017 |
His | -0.017 |
DVD | -0.016 |
oscope | -0.016 |
Token | an |
Token ID | 281 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
His | +0.028 |
x | +0.028 |
boo | +0.027 |
oscope | +0.027 |
apple | +0.027 |
Neg logit contributions | |
bel | -0.042 |
Fre | -0.042 |
Kay | -0.040 |
ora | -0.040 |
Hel | -0.040 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
Fre | +0.046 |
common | +0.044 |
ora | +0.044 |
ies | +0.042 |
uttering | +0.041 |
Neg logit contributions | |
DVD | -0.101 |
osaurus | -0.100 |
His | -0.099 |
oscope | -0.097 |
icle | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
omm | +0.851 |
His | +0.847 |
x | +0.847 |
DVD | +0.843 |
oscope | +0.839 |
Neg logit contributions | |
bel | -0.796 |
Fre | -0.739 |
Kay | -0.708 |
J | -0.705 |
Ag | -0.703 |
Token | They |
Token ID | 1119 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Kay | +0.012 |
Fre | +0.012 |
J | +0.012 |
Hel | +0.012 |
Jud | +0.012 |
Neg logit contributions | |
oscope | -0.017 |
x | -0.016 |
boo | -0.016 |
motorcycle | -0.016 |
DVD | -0.016 |
Token | ate |
Token ID | 15063 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
bel | +0.172 |
Fre | +0.168 |
Kay | +0.161 |
Hel | +0.160 |
Ag | +0.159 |
Neg logit contributions | |
His | -0.186 |
oscope | -0.184 |
omm | -0.183 |
x | -0.183 |
DVD | -0.182 |
Token | their |
Token ID | 511 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
His | +0.320 |
omm | +0.317 |
x | +0.316 |
DVD | +0.316 |
magnet | +0.310 |
Neg logit contributions | |
bel | -0.373 |
Fre | -0.365 |
Hel | -0.352 |
Kay | -0.352 |
Ag | -0.347 |
Token | lunch |
Token ID | 9965 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
bel | +0.214 |
Fre | +0.201 |
Kay | +0.194 |
common | +0.191 |
Ag | +0.191 |
Neg logit contributions | |
oscope | -0.159 |
omm | -0.159 |
x | -0.156 |
DVD | -0.155 |
His | -0.154 |
Token | Thank |
Token ID | 10449 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
omm | +0.452 |
x | +0.450 |
His | +0.449 |
DVD | +0.446 |
oscope | +0.446 |
Neg logit contributions | |
bel | -0.301 |
Fre | -0.290 |
Kay | -0.278 |
Hel | -0.277 |
Ag | -0.271 |
Token | you |
Token ID | 345 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
bel | +0.058 |
Fre | +0.056 |
Kay | +0.055 |
Hel | +0.054 |
Ag | +0.054 |
Neg logit contributions | |
x | -0.047 |
omm | -0.047 |
His | -0.046 |
DVD | -0.046 |
oscope | -0.046 |
Token | for |
Token ID | 329 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
Fre | +0.036 |
bel | +0.036 |
Kay | +0.034 |
Hel | +0.034 |
Ag | +0.033 |
Neg logit contributions | |
x | -0.038 |
oscope | -0.038 |
His | -0.038 |
DVD | -0.037 |
omm | -0.037 |
Token | getting |
Token ID | 1972 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
omm | +0.245 |
His | +0.243 |
oscope | +0.239 |
DVD | +0.236 |
x | +0.236 |
Neg logit contributions | |
bel | -0.293 |
Fre | -0.289 |
Hel | -0.279 |
Kay | -0.278 |
Ag | -0.273 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
x | +0.218 |
His | +0.216 |
omm | +0.215 |
DVD | +0.214 |
oscope | +0.213 |
Neg logit contributions | |
bel | -0.264 |
Fre | -0.260 |
Kay | -0.251 |
Hel | -0.249 |
Ag | -0.245 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.014 |
Fre | +0.013 |
Kay | +0.012 |
Hel | +0.012 |
common | +0.012 |
Neg logit contributions | |
His | -0.013 |
omm | -0.012 |
oscope | -0.011 |
DVD | -0.011 |
penter | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | +3.68e+00 |
Pos logit contributions | |
omm | +0.829 |
His | +0.827 |
x | +0.821 |
DVD | +0.812 |
oscope | +0.806 |
Neg logit contributions | |
bel | -0.834 |
Fre | -0.786 |
Kay | -0.749 |
Hel | -0.740 |
Ag | -0.739 |
Token | me |
Token ID | 502 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
His | +0.212 |
omm | +0.209 |
oscope | +0.209 |
DVD | +0.208 |
magnet | +0.201 |
Neg logit contributions | |
Fre | -0.271 |
bel | -0.269 |
Kay | -0.258 |
Hel | -0.257 |
J | -0.255 |
Token | ." |
Token ID | 526 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
omm | +0.035 |
His | +0.035 |
x | +0.035 |
DVD | +0.035 |
oscope | +0.035 |
Neg logit contributions | |
bel | -0.041 |
Fre | -0.040 |
Kay | -0.039 |
Hel | -0.039 |
Ag | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
x | +0.156 |
oscope | +0.146 |
omm | +0.138 |
DVD | +0.135 |
boo | +0.135 |
Neg logit contributions | |
Kay | -0.139 |
bel | -0.138 |
Fre | -0.137 |
Hel | -0.136 |
J | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
oscope | +0.005 |
x | +0.005 |
omm | +0.005 |
magnet | +0.004 |
DVD | +0.004 |
Neg logit contributions | |
bel | -0.005 |
Fre | -0.005 |
Kay | -0.005 |
Hel | -0.005 |
J | -0.005 |
Token | on |
Token ID | 319 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
omm | +0.561 |
His | +0.559 |
x | +0.557 |
oscope | +0.553 |
DVD | +0.552 |
Neg logit contributions | |
bel | -0.601 |
Fre | -0.585 |
Kay | -0.564 |
Hel | -0.561 |
Ag | -0.554 |
Token | , |
Token ID | 11 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
His | +0.125 |
x | +0.123 |
omm | +0.122 |
DVD | +0.122 |
oscope | +0.120 |
Neg logit contributions | |
bel | -0.147 |
Fre | -0.145 |
Kay | -0.138 |
Hel | -0.138 |
Ag | -0.138 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
bel | +0.056 |
Fre | +0.055 |
Kay | +0.053 |
Hel | +0.053 |
Ag | +0.052 |
Neg logit contributions | |
His | -0.046 |
omm | -0.046 |
x | -0.046 |
DVD | -0.045 |
oscope | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
omm | +0.257 |
x | +0.255 |
His | +0.250 |
DVD | +0.249 |
oscope | +0.248 |
Neg logit contributions | |
bel | -0.268 |
Fre | -0.257 |
Hel | -0.248 |
Kay | -0.247 |
Ag | -0.241 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
omm | +0.084 |
x | +0.082 |
oscope | +0.079 |
DVD | +0.076 |
magnet | +0.075 |
Neg logit contributions | |
bel | -0.131 |
Fre | -0.123 |
Kay | -0.121 |
Hel | -0.120 |
J | -0.118 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.015 |
Fre | +0.014 |
Kay | +0.014 |
Hel | +0.014 |
Ag | +0.014 |
Neg logit contributions | |
omm | -0.011 |
His | -0.011 |
x | -0.011 |
oscope | -0.011 |
DVD | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
His | +0.833 |
oscope | +0.824 |
omm | +0.821 |
x | +0.821 |
DVD | +0.817 |
Neg logit contributions | |
bel | -0.802 |
Fre | -0.801 |
Kay | -0.767 |
Hel | -0.762 |
Ag | -0.750 |
Token | always |
Token ID | 1464 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
bel | +0.327 |
Fre | +0.315 |
Kay | +0.306 |
Hel | +0.303 |
Ag | +0.300 |
Neg logit contributions | |
omm | -0.290 |
x | -0.288 |
His | -0.287 |
oscope | -0.287 |
DVD | -0.284 |
Token | together |
Token ID | 1978 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
Fre | +0.072 |
bel | +0.071 |
Kay | +0.069 |
Hel | +0.068 |
Ag | +0.067 |
Neg logit contributions | |
x | -0.060 |
DVD | -0.060 |
His | -0.060 |
oscope | -0.060 |
magnet | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
bel | +0.284 |
Fre | +0.282 |
Kay | +0.273 |
Hel | +0.271 |
Ag | +0.268 |
Neg logit contributions | |
His | -0.255 |
DVD | -0.250 |
oscope | -0.249 |
x | -0.247 |
omm | -0.247 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
Kay | +0.016 |
Fre | +0.016 |
Ag | +0.016 |
Hel | +0.016 |
J | +0.015 |
Neg logit contributions | |
oscope | -0.023 |
x | -0.022 |
boo | -0.020 |
knee | -0.020 |
operation | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
x | +0.103 |
oscope | +0.099 |
omm | +0.096 |
boo | +0.093 |
DVD | +0.092 |
Neg logit contributions | |
bel | -0.128 |
Fre | -0.128 |
Kay | -0.126 |
Hel | -0.126 |
Ag | -0.124 |
Token | both |
Token ID | 1111 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
bel | +0.113 |
Fre | +0.112 |
Kay | +0.107 |
Ag | +0.107 |
Hel | +0.105 |
Neg logit contributions | |
His | -0.108 |
oscope | -0.108 |
x | -0.105 |
DVD | -0.104 |
magnet | -0.104 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
His | +0.041 |
oscope | +0.041 |
boo | +0.039 |
DVD | +0.039 |
x | +0.038 |
Neg logit contributions | |
bel | -0.041 |
Fre | -0.041 |
Ag | -0.040 |
Kay | -0.039 |
uttering | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
bel | +0.151 |
Fre | +0.148 |
Kay | +0.143 |
ora | +0.143 |
Hel | +0.141 |
Neg logit contributions | |
His | -0.122 |
DVD | -0.120 |
apple | -0.114 |
x | -0.113 |
motorcycle | -0.112 |
Token | tasty |
Token ID | 25103 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
bel | +0.007 |
Fre | +0.007 |
Kay | +0.007 |
Hel | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
x | -0.007 |
DVD | -0.007 |
oscope | -0.007 |
omm | -0.007 |
His | -0.007 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
x | +0.112 |
His | +0.112 |
omm | +0.112 |
DVD | +0.111 |
oscope | +0.111 |
Neg logit contributions | |
bel | -0.180 |
Fre | -0.177 |
Hel | -0.172 |
Kay | -0.172 |
Ag | -0.170 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
His | +0.881 |
magnet | +0.879 |
DVD | +0.878 |
oscope | +0.878 |
apple | +0.875 |
Neg logit contributions | |
Fre | -0.746 |
bel | -0.739 |
Hel | -0.717 |
Kay | -0.710 |
Ag | -0.692 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
His | +0.090 |
oscope | +0.088 |
DVD | +0.087 |
apple | +0.086 |
magnet | +0.086 |
Neg logit contributions | |
bel | -0.093 |
Fre | -0.093 |
Hel | -0.088 |
Kay | -0.088 |
Ag | -0.088 |
Token | the |
Token ID | 262 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
omm | +0.072 |
x | +0.072 |
His | +0.071 |
oscope | +0.071 |
DVD | +0.071 |
Neg logit contributions | |
bel | -0.065 |
Fre | -0.063 |
Kay | -0.061 |
Hel | -0.061 |
Ag | -0.060 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
bel | +0.025 |
Fre | +0.025 |
Kay | +0.024 |
Hel | +0.024 |
Ag | +0.023 |
Neg logit contributions | |
His | -0.022 |
omm | -0.022 |
oscope | -0.022 |
x | -0.021 |
DVD | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
omm | +0.103 |
x | +0.099 |
magnet | +0.096 |
boo | +0.096 |
oscope | +0.095 |
Neg logit contributions | |
bel | -0.124 |
Fre | -0.112 |
ies | -0.112 |
Kay | -0.112 |
Hel | -0.109 |
Token | out |
Token ID | 503 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
omm | +0.102 |
x | +0.101 |
His | +0.101 |
oscope | +0.101 |
DVD | +0.100 |
Neg logit contributions | |
bel | -0.148 |
Fre | -0.145 |
Kay | -0.140 |
Hel | -0.140 |
Ag | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
His | +0.142 |
x | +0.130 |
DVD | +0.125 |
oscope | +0.125 |
seventy | +0.124 |
Neg logit contributions | |
Fre | -0.195 |
bel | -0.191 |
Ag | -0.191 |
Hel | -0.190 |
Kay | -0.188 |
Token | pl |
Token ID | 458 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
His | +0.135 |
x | +0.131 |
oscope | +0.131 |
DVD | +0.130 |
magnet | +0.129 |
Neg logit contributions | |
Fre | -0.126 |
bel | -0.125 |
Kay | -0.120 |
Hel | -0.119 |
Ag | -0.119 |
Token | ucked |
Token ID | 17758 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
bel | +0.007 |
Fre | +0.007 |
Hel | +0.007 |
Kay | +0.007 |
Ag | +0.007 |
Neg logit contributions | |
omm | -0.007 |
His | -0.007 |
oscope | -0.007 |
x | -0.007 |
DVD | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
His | +0.025 |
x | +0.025 |
omm | +0.024 |
DVD | +0.024 |
oscope | +0.024 |
Neg logit contributions | |
bel | -0.037 |
Fre | -0.036 |
Hel | -0.035 |
Kay | -0.035 |
Ag | -0.035 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.24e+01 |
Pos logit contributions | |
bel | +0.015 |
Fre | +0.014 |
Kay | +0.013 |
Hel | +0.013 |
Ag | +0.013 |
Neg logit contributions | |
omm | -0.011 |
His | -0.011 |
oscope | -0.011 |
DVD | -0.011 |
penter | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
omm | +0.865 |
His | +0.850 |
x | +0.844 |
DVD | +0.834 |
oscope | +0.833 |
Neg logit contributions | |
bel | -0.801 |
Fre | -0.749 |
Kay | -0.719 |
Ag | -0.709 |
Hel | -0.706 |
Token | He |
Token ID | 679 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Fre | +0.018 |
Kay | +0.018 |
bel | +0.017 |
Ag | +0.017 |
J | +0.017 |
Neg logit contributions | |
oscope | -0.011 |
x | -0.011 |
boo | -0.010 |
DVD | -0.010 |
motorcycle | -0.010 |
Token | tasted |
Token ID | 29187 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
omm | +0.191 |
x | +0.189 |
His | +0.189 |
oscope | +0.188 |
DVD | +0.188 |
Neg logit contributions | |
bel | -0.175 |
Fre | -0.169 |
Kay | -0.163 |
Hel | -0.161 |
Ag | -0.159 |
Token | it |
Token ID | 340 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
bel | +0.058 |
Fre | +0.057 |
Kay | +0.055 |
Hel | +0.054 |
Ag | +0.054 |
Neg logit contributions | |
omm | -0.053 |
x | -0.053 |
oscope | -0.053 |
His | -0.053 |
DVD | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
omm | +0.004 |
oscope | +0.004 |
x | +0.004 |
DVD | +0.004 |
His | +0.004 |
Neg logit contributions | |
bel | -0.004 |
Fre | -0.004 |
Kay | -0.004 |
J | -0.004 |
ies | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
omm | +0.294 |
oscope | +0.289 |
His | +0.283 |
DVD | +0.282 |
x | +0.280 |
Neg logit contributions | |
bel | -0.438 |
Fre | -0.432 |
Kay | -0.415 |
Hel | -0.414 |
Ag | -0.405 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
omm | +0.110 |
oscope | +0.106 |
Promise | +0.103 |
x | +0.103 |
seventy | +0.103 |
Neg logit contributions | |
bel | -0.109 |
Fre | -0.106 |
Kay | -0.099 |
Hel | -0.098 |
J | -0.098 |
Token | big |
Token ID | 1263 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
oscope | +0.092 |
omm | +0.091 |
His | +0.089 |
penter | +0.085 |
x | +0.085 |
Neg logit contributions | |
bel | -0.075 |
Fre | -0.072 |
Kay | -0.068 |
Hel | -0.067 |
common | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bel | +0.130 |
Fre | +0.127 |
common | +0.123 |
ora | +0.119 |
ies | +0.119 |
Neg logit contributions | |
His | -0.124 |
omm | -0.123 |
oscope | -0.122 |
oll | -0.116 |
penter | -0.112 |
Token | juicy |
Token ID | 35075 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
omm | +0.117 |
oscope | +0.115 |
x | +0.111 |
DVD | +0.110 |
icle | +0.109 |
Neg logit contributions | |
bel | -0.075 |
Fre | -0.069 |
Kay | -0.067 |
Ag | -0.067 |
Hel | -0.066 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
oscope | +0.152 |
penter | +0.148 |
His | +0.147 |
Promise | +0.147 |
omm | +0.146 |
Neg logit contributions | |
bel | -0.230 |
Fre | -0.224 |
ies | -0.221 |
ora | -0.220 |
Kay | -0.212 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
omm | +0.960 |
x | +0.949 |
Promise | +0.940 |
oscope | +0.936 |
boo | +0.928 |
Neg logit contributions | |
bel | -0.690 |
Fre | -0.623 |
ies | -0.610 |
ora | -0.592 |
J | -0.578 |
Token | He |
Token ID | 679 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
bel | +0.016 |
Fre | +0.016 |
Hel | +0.015 |
Kay | +0.015 |
Ag | +0.015 |
Neg logit contributions | |
x | -0.011 |
oscope | -0.011 |
boo | -0.011 |
omm | -0.010 |
DVD | -0.010 |
Token | took |
Token ID | 1718 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
omm | +0.196 |
x | +0.196 |
oscope | +0.194 |
DVD | +0.192 |
His | +0.189 |
Neg logit contributions | |
bel | -0.179 |
Fre | -0.171 |
Kay | -0.163 |
J | -0.160 |
Hel | -0.160 |
Token | one |
Token ID | 530 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
omm | +0.257 |
oscope | +0.251 |
DVD | +0.246 |
boo | +0.245 |
x | +0.242 |
Neg logit contributions | |
bel | -0.256 |
Fre | -0.244 |
Kay | -0.235 |
Hel | -0.234 |
J | -0.231 |
Token | bite |
Token ID | 13197 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
omm | +0.059 |
oscope | +0.058 |
His | +0.058 |
penter | +0.057 |
Promise | +0.057 |
Neg logit contributions | |
bel | -0.065 |
ora | -0.059 |
Fre | -0.058 |
ies | -0.058 |
common | -0.056 |
Token | He |
Token ID | 679 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
bel | +0.018 |
Ag | +0.018 |
Kay | +0.018 |
J | +0.017 |
Fre | +0.017 |
Neg logit contributions | |
oscope | -0.013 |
x | -0.012 |
seventy | -0.012 |
DVD | -0.012 |
oll | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
omm | +0.211 |
x | +0.210 |
DVD | +0.210 |
oscope | +0.210 |
His | +0.209 |
Neg logit contributions | |
bel | -0.158 |
Fre | -0.153 |
Kay | -0.146 |
Hel | -0.145 |
Ag | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
His | +0.018 |
x | +0.018 |
omm | +0.018 |
oscope | +0.018 |
DVD | +0.017 |
Neg logit contributions | |
bel | -0.025 |
Fre | -0.024 |
Kay | -0.024 |
Hel | -0.024 |
Ag | -0.023 |
Token | y |
Token ID | 331 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
omm | +0.085 |
His | +0.084 |
x | +0.084 |
DVD | +0.083 |
oscope | +0.083 |
Neg logit contributions | |
bel | -0.080 |
Fre | -0.078 |
Kay | -0.075 |
Hel | -0.074 |
Ag | -0.073 |
Token | ummy |
Token ID | 13513 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
omm | +0.123 |
His | +0.123 |
x | +0.122 |
oscope | +0.121 |
DVD | +0.121 |
Neg logit contributions | |
bel | -0.274 |
Fre | -0.269 |
Kay | -0.261 |
Hel | -0.260 |
Ag | -0.258 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
omm | +0.172 |
His | +0.171 |
oscope | +0.168 |
DVD | +0.166 |
x | +0.165 |
Neg logit contributions | |
bel | -0.283 |
Fre | -0.272 |
Kay | -0.264 |
J | -0.260 |
Hel | -0.260 |
Token | that |
Token ID | 326 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
His | +0.835 |
omm | +0.832 |
DVD | +0.830 |
x | +0.826 |
oscope | +0.818 |
Neg logit contributions | |
bel | -0.812 |
Fre | -0.762 |
J | -0.722 |
ies | -0.720 |
Kay | -0.719 |
Token | he |
Token ID | 339 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
omm | +0.139 |
oscope | +0.139 |
x | +0.138 |
DVD | +0.137 |
His | +0.135 |
Neg logit contributions | |
bel | -0.127 |
Fre | -0.119 |
Kay | -0.116 |
Hel | -0.115 |
J | -0.114 |
Token | was |
Token ID | 373 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
omm | +0.153 |
DVD | +0.152 |
x | +0.151 |
His | +0.150 |
oscope | +0.150 |
Neg logit contributions | |
bel | -0.134 |
Fre | -0.127 |
Kay | -0.122 |
Hel | -0.121 |
J | -0.119 |
Token | m |
Token ID | 285 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
oscope | +0.039 |
omm | +0.039 |
His | +0.039 |
x | +0.039 |
DVD | +0.039 |
Neg logit contributions | |
bel | -0.040 |
Fre | -0.039 |
Kay | -0.037 |
J | -0.036 |
Ag | -0.036 |
Token | unch |
Token ID | 3316 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
omm | +0.161 |
oscope | +0.149 |
x | +0.148 |
His | +0.148 |
icle | +0.143 |
Neg logit contributions | |
bel | -0.288 |
Fre | -0.282 |
Hel | -0.279 |
Ag | -0.272 |
Kay | -0.271 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
omm | +0.319 |
oscope | +0.312 |
DVD | +0.306 |
penter | +0.300 |
motorcycle | +0.298 |
Neg logit contributions | |
bel | -0.181 |
J | -0.178 |
Kay | -0.161 |
Hel | -0.160 |
common | -0.160 |
Token | bite |
Token ID | 13197 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
omm | +0.073 |
His | +0.071 |
oscope | +0.071 |
x | +0.070 |
DVD | +0.070 |
Neg logit contributions | |
bel | -0.092 |
Fre | -0.089 |
Kay | -0.086 |
Hel | -0.086 |
Ag | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
omm | +0.421 |
oscope | +0.419 |
x | +0.414 |
DVD | +0.411 |
penter | +0.408 |
Neg logit contributions | |
bel | -0.280 |
J | -0.269 |
Fre | -0.268 |
Kay | -0.258 |
Hel | -0.252 |
Token | But |
Token ID | 887 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
J | +0.013 |
bel | +0.013 |
Kay | +0.013 |
Hel | +0.012 |
hills | +0.012 |
Neg logit contributions | |
oscope | -0.016 |
x | -0.015 |
oll | -0.014 |
DVD | -0.014 |
seventy | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
bel | +0.025 |
J | +0.024 |
sudden | +0.023 |
ies | +0.023 |
admired | +0.022 |
Neg logit contributions | |
DVD | -0.042 |
omm | -0.042 |
oscope | -0.041 |
teaches | -0.039 |
oll | -0.039 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
bel | +0.031 |
Fre | +0.030 |
Jud | +0.030 |
Kay | +0.030 |
Hel | +0.029 |
Neg logit contributions | |
DVD | -0.009 |
oscope | -0.008 |
penter | -0.008 |
omm | -0.008 |
x | -0.008 |
Token | tasted |
Token ID | 29187 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
DVD | +0.906 |
omm | +0.895 |
x | +0.883 |
oscope | +0.881 |
His | +0.874 |
Neg logit contributions | |
bel | -0.750 |
Fre | -0.683 |
Kay | -0.663 |
J | -0.658 |
Ag | -0.653 |
Token | funny |
Token ID | 8258 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
bel | +0.050 |
Fre | +0.049 |
Kay | +0.047 |
Ag | +0.046 |
Hel | +0.046 |
Neg logit contributions | |
oscope | -0.052 |
DVD | -0.051 |
omm | -0.051 |
x | -0.051 |
His | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
bel | +0.168 |
Fre | +0.164 |
Kay | +0.158 |
Hel | +0.158 |
Ag | +0.155 |
Neg logit contributions | |
omm | -0.161 |
His | -0.161 |
x | -0.160 |
oscope | -0.159 |
DVD | -0.159 |
Token | made |
Token ID | 925 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
oscope | +0.090 |
omm | +0.089 |
DVD | +0.088 |
x | +0.088 |
His | +0.085 |
Neg logit contributions | |
bel | -0.100 |
Fre | -0.095 |
Kay | -0.093 |
Ag | -0.092 |
J | -0.092 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
bel | +0.149 |
J | +0.140 |
Ag | +0.134 |
Kay | +0.134 |
Hel | +0.131 |
Neg logit contributions | |
oscope | -0.156 |
seventy | -0.153 |
DVD | -0.148 |
omm | -0.147 |
penter | -0.143 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
His | +0.267 |
omm | +0.262 |
x | +0.260 |
DVD | +0.257 |
oscope | +0.257 |
Neg logit contributions | |
bel | -0.279 |
Fre | -0.271 |
Kay | -0.260 |
Hel | -0.257 |
Ag | -0.254 |
Token | Fl |
Token ID | 1610 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
bel | +0.087 |
Fre | +0.082 |
Ag | +0.080 |
Kay | +0.080 |
Hel | +0.080 |
Neg logit contributions | |
omm | -0.097 |
oscope | -0.096 |
x | -0.095 |
DVD | -0.093 |
His | -0.092 |
Token | uffy |
Token ID | 15352 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
omm | +0.285 |
x | +0.275 |
His | +0.272 |
oscope | +0.269 |
DVD | +0.267 |
Neg logit contributions | |
bel | -0.234 |
Fre | -0.228 |
Kay | -0.214 |
Hel | -0.210 |
Ag | -0.209 |
Token | ate |
Token ID | 15063 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
Fre | +0.263 |
bel | +0.261 |
Hel | +0.257 |
Kay | +0.248 |
ies | +0.247 |
Neg logit contributions | |
DVD | -0.327 |
x | -0.318 |
omm | -0.318 |
icle | -0.310 |
oscope | -0.305 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
oscope | +0.415 |
omm | +0.397 |
penter | +0.393 |
DVD | +0.391 |
x | +0.390 |
Neg logit contributions | |
bel | -0.287 |
Fre | -0.285 |
J | -0.273 |
Ag | -0.268 |
Kay | -0.267 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
bel | +0.030 |
Fre | +0.029 |
Kay | +0.028 |
J | +0.028 |
ora | +0.028 |
Neg logit contributions | |
DVD | -0.011 |
oscope | -0.011 |
omm | -0.010 |
penter | -0.010 |
x | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
omm | +0.836 |
x | +0.833 |
DVD | +0.828 |
oscope | +0.809 |
His | +0.800 |
Neg logit contributions | |
bel | -0.831 |
Fre | -0.762 |
Kay | -0.734 |
J | -0.729 |
ies | -0.724 |
Token | it |
Token ID | 340 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
omm | +0.090 |
x | +0.090 |
His | +0.089 |
oscope | +0.089 |
DVD | +0.089 |
Neg logit contributions | |
bel | -0.096 |
Fre | -0.094 |
Kay | -0.090 |
Hel | -0.090 |
Ag | -0.089 |
Token | was |
Token ID | 373 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
omm | +0.011 |
x | +0.011 |
His | +0.011 |
oscope | +0.011 |
DVD | +0.011 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.010 |
Kay | -0.009 |
Hel | -0.009 |
Ag | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
oscope | +0.050 |
x | +0.049 |
omm | +0.047 |
DVD | +0.047 |
penter | +0.046 |
Neg logit contributions | |
bel | -0.030 |
Fre | -0.029 |
J | -0.029 |
Kay | -0.029 |
ies | -0.028 |
Token | y |
Token ID | 331 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
oscope | +0.044 |
x | +0.044 |
omm | +0.044 |
DVD | +0.044 |
His | +0.043 |
Neg logit contributions | |
bel | -0.040 |
Fre | -0.039 |
Kay | -0.037 |
Hel | -0.037 |
Ag | -0.037 |
Token | had |
Token ID | 550 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
bel | +0.147 |
Fre | +0.140 |
Kay | +0.134 |
J | +0.133 |
Hel | +0.130 |
Neg logit contributions | |
omm | -0.162 |
x | -0.159 |
DVD | -0.158 |
oscope | -0.158 |
icle | -0.157 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
His | +0.017 |
apple | +0.016 |
seventy | +0.016 |
x | +0.016 |
DVD | +0.016 |
Neg logit contributions | |
bel | -0.026 |
Fre | -0.025 |
Hel | -0.024 |
Kay | -0.024 |
Ag | -0.024 |
Token | sandwich |
Token ID | 20433 |
Feature activation | +6.70e+00 |
Pos logit contributions | |
omm | +0.077 |
His | +0.077 |
oscope | +0.077 |
x | +0.076 |
DVD | +0.076 |
Neg logit contributions | |
bel | -0.087 |
Fre | -0.085 |
Kay | -0.082 |
Hel | -0.081 |
Ag | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
omm | +0.420 |
x | +0.418 |
His | +0.417 |
oscope | +0.413 |
DVD | +0.409 |
Neg logit contributions | |
bel | -0.473 |
Fre | -0.451 |
Kay | -0.438 |
J | -0.432 |
Hel | -0.430 |
Token | an |
Token ID | 281 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
bel | +0.090 |
Fre | +0.086 |
Kay | +0.083 |
J | +0.083 |
common | +0.082 |
Neg logit contributions | |
omm | -0.088 |
x | -0.082 |
oscope | -0.082 |
DVD | -0.081 |
penter | -0.081 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
ies | +0.075 |
Fre | +0.073 |
insects | +0.072 |
ora | +0.070 |
uttering | +0.068 |
Neg logit contributions | |
DVD | -0.081 |
magnet | -0.078 |
penter | -0.078 |
omm | -0.078 |
ccoli | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
omm | +0.940 |
His | +0.937 |
x | +0.931 |
oscope | +0.921 |
DVD | +0.912 |
Neg logit contributions | |
bel | -0.683 |
Fre | -0.634 |
ies | -0.618 |
ora | -0.610 |
J | -0.593 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
omm | +0.088 |
oscope | +0.086 |
x | +0.086 |
DVD | +0.085 |
His | +0.084 |
Neg logit contributions | |
bel | -0.099 |
Fre | -0.095 |
Kay | -0.092 |
J | -0.091 |
Hel | -0.090 |
Token | cookie |
Token ID | 19751 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
omm | +0.061 |
oscope | +0.060 |
His | +0.059 |
x | +0.058 |
penter | +0.057 |
Neg logit contributions | |
bel | -0.105 |
Fre | -0.102 |
Kay | -0.099 |
Ag | -0.098 |
J | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
omm | +0.485 |
His | +0.484 |
x | +0.482 |
oscope | +0.477 |
DVD | +0.474 |
Neg logit contributions | |
bel | -0.448 |
Fre | -0.431 |
Kay | -0.413 |
Hel | -0.408 |
Ag | -0.406 |
Token | She |
Token ID | 1375 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
bel | +0.014 |
Fre | +0.014 |
Kay | +0.013 |
Hel | +0.013 |
Ag | +0.013 |
Neg logit contributions | |
oscope | -0.012 |
omm | -0.012 |
x | -0.012 |
DVD | -0.012 |
His | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
x | +0.012 |
omm | +0.012 |
His | +0.012 |
oscope | +0.012 |
DVD | +0.012 |
Neg logit contributions | |
bel | -0.015 |
Fre | -0.014 |
Kay | -0.014 |
Hel | -0.014 |
Ag | -0.014 |
Token | you |
Token ID | 345 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
bel | +0.111 |
Fre | +0.106 |
Kay | +0.104 |
Hel | +0.103 |
Ag | +0.102 |
Neg logit contributions | |
His | -0.070 |
x | -0.069 |
omm | -0.068 |
magnet | -0.067 |
apple | -0.067 |
Token | must |
Token ID | 1276 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
bel | +0.071 |
Fre | +0.068 |
Hel | +0.066 |
Kay | +0.065 |
Ag | +0.064 |
Neg logit contributions | |
omm | -0.083 |
His | -0.081 |
DVD | -0.080 |
x | -0.079 |
oscope | -0.079 |
Token | eat |
Token ID | 4483 |
Feature activation | +5.40e+00 |
Pos logit contributions | |
DVD | +0.104 |
omm | +0.100 |
motorcycle | +0.099 |
His | +0.098 |
x | +0.097 |
Neg logit contributions | |
Fre | -0.115 |
Kay | -0.114 |
common | -0.113 |
ora | -0.112 |
Ag | -0.109 |
Token | an |
Token ID | 281 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
omm | +0.335 |
His | +0.334 |
oscope | +0.331 |
x | +0.330 |
DVD | +0.328 |
Neg logit contributions | |
bel | -0.380 |
Fre | -0.372 |
Kay | -0.357 |
Hel | -0.355 |
Ag | -0.351 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
ies | +0.105 |
Fre | +0.105 |
insects | +0.102 |
ora | +0.102 |
perspective | +0.098 |
Neg logit contributions | |
His | -0.063 |
DVD | -0.056 |
spoiler | -0.055 |
penter | -0.054 |
trailer | -0.054 |
Token | instead |
Token ID | 2427 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
His | +0.833 |
omm | +0.830 |
x | +0.822 |
oscope | +0.817 |
DVD | +0.811 |
Neg logit contributions | |
bel | -0.813 |
Fre | -0.780 |
Kay | -0.739 |
Ag | -0.729 |
Hel | -0.725 |
Token | of |
Token ID | 286 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
x | +0.117 |
omm | +0.116 |
DVD | +0.116 |
His | +0.115 |
boo | +0.114 |
Neg logit contributions | |
bel | -0.108 |
Fre | -0.105 |
Kay | -0.100 |
Hel | -0.099 |
ora | -0.098 |
Token | drinking |
Token ID | 7722 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
His | +0.214 |
omm | +0.213 |
oscope | +0.210 |
DVD | +0.210 |
x | +0.208 |
Neg logit contributions | |
bel | -0.248 |
Fre | -0.245 |
Kay | -0.234 |
Hel | -0.232 |
Ag | -0.230 |
Token | tea |
Token ID | 8887 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
oscope | +0.256 |
His | +0.253 |
x | +0.253 |
omm | +0.251 |
penter | +0.248 |
Neg logit contributions | |
bel | -0.277 |
Fre | -0.271 |
Kay | -0.256 |
J | -0.254 |
ora | -0.252 |
Token | . |
Token ID | 13 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
bel | +0.059 |
Fre | +0.057 |
Kay | +0.055 |
Hel | +0.054 |
Ag | +0.054 |
Neg logit contributions | |
His | -0.054 |
omm | -0.054 |
x | -0.054 |
oscope | -0.054 |
DVD | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
omm | +0.126 |
oscope | +0.124 |
x | +0.122 |
DVD | +0.122 |
boo | +0.119 |
Neg logit contributions | |
Fre | -0.132 |
bel | -0.132 |
Kay | -0.127 |
Hel | -0.125 |
J | -0.124 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
hills | +0.016 |
bel | +0.016 |
Fre | +0.016 |
valleys | +0.014 |
Kay | +0.014 |
Neg logit contributions | |
DVD | -0.024 |
oscope | -0.023 |
penter | -0.022 |
omm | -0.022 |
teaches | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
omm | +0.141 |
x | +0.136 |
DVD | +0.136 |
oscope | +0.134 |
Promise | +0.134 |
Neg logit contributions | |
bel | -0.093 |
Fre | -0.081 |
Kay | -0.079 |
Hel | -0.077 |
J | -0.076 |
Token | The |
Token ID | 383 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
bel | +0.016 |
ways | +0.015 |
hills | +0.015 |
Kay | +0.014 |
Ag | +0.014 |
Neg logit contributions | |
oscope | -0.014 |
DVD | -0.014 |
oll | -0.013 |
seventy | -0.013 |
x | -0.013 |
Token | red |
Token ID | 2266 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
DVD | +0.153 |
omm | +0.145 |
oscope | +0.144 |
x | +0.142 |
penter | +0.137 |
Neg logit contributions | |
bel | -0.191 |
Fre | -0.177 |
J | -0.172 |
Kay | -0.172 |
Hel | -0.171 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
DVD | +0.038 |
omm | +0.036 |
oscope | +0.035 |
x | +0.035 |
oll | +0.033 |
Neg logit contributions | |
bel | -0.108 |
ies | -0.103 |
Fre | -0.100 |
ora | -0.099 |
perspective | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
DVD | +0.882 |
omm | +0.880 |
x | +0.873 |
oscope | +0.862 |
His | +0.857 |
Neg logit contributions | |
bel | -0.773 |
Fre | -0.714 |
Kay | -0.688 |
Hel | -0.685 |
J | -0.682 |
Token | very |
Token ID | 845 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
oscope | +0.046 |
DVD | +0.044 |
omm | +0.043 |
penter | +0.042 |
x | +0.042 |
Neg logit contributions | |
bel | -0.030 |
Fre | -0.027 |
Kay | -0.026 |
J | -0.026 |
common | -0.025 |
Token | high |
Token ID | 1029 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
His | +0.044 |
omm | +0.043 |
x | +0.043 |
DVD | +0.042 |
magnet | +0.042 |
Neg logit contributions | |
bel | -0.041 |
Fre | -0.040 |
Hel | -0.038 |
Kay | -0.038 |
Ag | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
bel | +0.302 |
Fre | +0.291 |
Kay | +0.279 |
Hel | +0.277 |
Ag | +0.276 |
Neg logit contributions | |
omm | -0.293 |
His | -0.290 |
DVD | -0.287 |
oscope | -0.286 |
x | -0.285 |
Token | but |
Token ID | 475 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
bel | +0.091 |
Fre | +0.087 |
Kay | +0.084 |
Ag | +0.084 |
Hel | +0.083 |
Neg logit contributions | |
omm | -0.087 |
x | -0.085 |
DVD | -0.085 |
oscope | -0.085 |
His | -0.084 |
Token | � |
Token ID | 6184 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
Fre | +0.048 |
Ag | +0.046 |
Kay | +0.046 |
bel | +0.046 |
Hel | +0.045 |
Neg logit contributions | |
x | -0.033 |
oscope | -0.032 |
magnet | -0.030 |
DVD | -0.030 |
omm | -0.029 |
Token | � |
Token ID | 95 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
His | +0.004 |
oscope | +0.004 |
DVD | +0.004 |
omm | +0.004 |
x | +0.004 |
Neg logit contributions | |
Fre | -0.003 |
bel | -0.003 |
Ag | -0.003 |
Kay | -0.003 |
Hel | -0.003 |
Token | € |
Token ID | 26391 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Hel | +0.255 |
Kay | +0.254 |
Fre | +0.252 |
Ag | +0.248 |
J | +0.240 |
Neg logit contributions | |
magnet | -0.207 |
seventy | -0.204 |
apple | -0.202 |
boo | -0.201 |
motorcycle | -0.199 |
Token | � |
Token ID | 129 |
Feature activation | -7.29e+00 |
Pos logit contributions | |
His | +0.012 |
omm | +0.012 |
oscope | +0.012 |
DVD | +0.011 |
penter | +0.011 |
Neg logit contributions | |
bel | -0.012 |
Fre | -0.012 |
Kay | -0.011 |
Ag | -0.011 |
Hel | -0.011 |
Token | � |
Token ID | 241 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
Fre | +0.493 |
Kay | +0.479 |
Ag | +0.470 |
Hel | +0.466 |
bel | +0.451 |
Neg logit contributions | |
magnet | -0.493 |
DVD | -0.466 |
seventy | -0.456 |
omm | -0.454 |
x | -0.453 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
bel | +0.001 |
Fre | +0.001 |
ies | +0.001 |
Hel | +0.001 |
ora | +0.001 |
Neg logit contributions | |
His | -0.001 |
DVD | -0.001 |
oscope | -0.001 |
icle | -0.001 |
omm | -0.001 |
Token | ping |
Token ID | 13886 |
Feature activation | -8.44e-02 |
Pos logit contributions | |
Fre | +1.064 |
ies | +1.031 |
ora | +1.024 |
Kay | +0.984 |
bel | +0.962 |
Neg logit contributions | |
DVD | -1.062 |
magnet | -1.056 |
His | -1.047 |
microwave | -1.045 |
motorcycle | -1.015 |
Token | others |
Token ID | 1854 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
bel | +0.006 |
Fre | +0.006 |
Kay | +0.006 |
Hel | +0.006 |
Ag | +0.006 |
Neg logit contributions | |
His | -0.005 |
omm | -0.005 |
x | -0.005 |
oscope | -0.005 |
DVD | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
bel | +0.433 |
Fre | +0.423 |
Kay | +0.411 |
Ag | +0.407 |
J | +0.403 |
Neg logit contributions | |
His | -0.381 |
oscope | -0.379 |
DVD | -0.377 |
magnet | -0.374 |
x | -0.372 |
Token | the |
Token ID | 262 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
omm | +0.092 |
x | +0.091 |
oscope | +0.090 |
His | +0.090 |
DVD | +0.089 |
Neg logit contributions | |
bel | -0.101 |
Fre | -0.100 |
Kay | -0.095 |
Hel | -0.094 |
Ag | -0.093 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
bel | +0.045 |
Fre | +0.045 |
Kay | +0.042 |
Hel | +0.042 |
Ag | +0.041 |
Neg logit contributions | |
His | -0.042 |
omm | -0.041 |
DVD | -0.041 |
x | -0.040 |
oscope | -0.040 |
Token | with |
Token ID | 351 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
omm | +0.041 |
oscope | +0.039 |
His | +0.038 |
oll | +0.038 |
seventy | +0.037 |
Neg logit contributions | |
bel | -0.028 |
Hel | -0.025 |
Fre | -0.025 |
Ag | -0.025 |
J | -0.024 |
Token | me |
Token ID | 502 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
bel | +0.104 |
Fre | +0.103 |
Hel | +0.100 |
Kay | +0.100 |
Ag | +0.098 |
Neg logit contributions | |
omm | -0.070 |
oscope | -0.068 |
DVD | -0.068 |
His | -0.067 |
x | -0.067 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
omm | +0.015 |
His | +0.015 |
oscope | +0.015 |
x | +0.014 |
DVD | +0.014 |
Neg logit contributions | |
bel | -0.019 |
Fre | -0.018 |
Hel | -0.017 |
Kay | -0.017 |
J | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
omm | +0.167 |
oscope | +0.165 |
oll | +0.164 |
x | +0.163 |
DVD | +0.162 |
Neg logit contributions | |
bel | -0.210 |
Kay | -0.210 |
Hel | -0.209 |
Fre | -0.205 |
Ag | -0.202 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
bel | +0.016 |
Fre | +0.016 |
Kay | +0.015 |
Hel | +0.015 |
Ag | +0.015 |
Neg logit contributions | |
His | -0.012 |
omm | -0.012 |
x | -0.012 |
DVD | -0.011 |
oscope | -0.011 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
bel | +0.013 |
Fre | +0.013 |
ora | +0.012 |
ies | +0.012 |
uttering | +0.012 |
Neg logit contributions | |
His | -0.014 |
penter | -0.014 |
x | -0.013 |
omm | -0.013 |
oscope | -0.013 |
Token | i |
Token ID | 72 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
Fre | +0.942 |
ora | +0.901 |
ies | +0.896 |
Kay | +0.881 |
Hel | +0.861 |
Neg logit contributions | |
DVD | -1.236 |
magnet | -1.208 |
x | -1.205 |
His | -1.186 |
microwave | -1.184 |
Token | landed |
Token ID | 11406 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
bel | +0.221 |
Fre | +0.214 |
Hel | +0.208 |
Kay | +0.207 |
Ag | +0.200 |
Neg logit contributions | |
omm | -0.242 |
x | -0.242 |
DVD | -0.241 |
oscope | -0.237 |
His | -0.236 |
Token | next |
Token ID | 1306 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
His | +0.091 |
omm | +0.091 |
x | +0.091 |
oscope | +0.090 |
DVD | +0.090 |
Neg logit contributions | |
bel | -0.104 |
Fre | -0.102 |
Kay | -0.098 |
Hel | -0.098 |
Ag | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
omm | +0.264 |
His | +0.263 |
x | +0.262 |
oscope | +0.261 |
DVD | +0.261 |
Neg logit contributions | |
bel | -0.182 |
Fre | -0.172 |
Kay | -0.164 |
Hel | -0.163 |
Ag | -0.159 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
bel | +0.204 |
Fre | +0.201 |
Kay | +0.197 |
Hel | +0.196 |
Ag | +0.192 |
Neg logit contributions | |
omm | -0.131 |
oscope | -0.128 |
DVD | -0.127 |
x | -0.127 |
His | -0.126 |
Token | get |
Token ID | 651 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
bel | +0.184 |
Fre | +0.177 |
Kay | +0.170 |
common | +0.168 |
Hel | +0.167 |
Neg logit contributions | |
omm | -0.157 |
DVD | -0.146 |
His | -0.145 |
seventy | -0.140 |
oscope | -0.139 |
Token | it |
Token ID | 340 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
omm | +0.275 |
His | +0.269 |
oscope | +0.266 |
DVD | +0.265 |
x | +0.264 |
Neg logit contributions | |
bel | -0.283 |
Fre | -0.270 |
Hel | -0.260 |
Kay | -0.258 |
Ag | -0.257 |
Token | ." |
Token ID | 526 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
bel | +0.014 |
Fre | +0.013 |
ies | +0.012 |
common | +0.012 |
Hel | +0.012 |
Neg logit contributions | |
omm | -0.015 |
DVD | -0.014 |
x | -0.014 |
His | -0.014 |
oscope | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
His | +0.093 |
penter | +0.077 |
Your | +0.076 |
magnet | +0.075 |
omm | +0.073 |
Neg logit contributions | |
bel | -0.163 |
Fre | -0.159 |
uttering | -0.149 |
common | -0.146 |
Kay | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
bel | +0.021 |
ies | +0.020 |
mons | +0.019 |
Fre | +0.019 |
uttering | +0.019 |
Neg logit contributions | |
His | -0.008 |
teaches | -0.006 |
From | -0.006 |
penter | -0.006 |
x | -0.006 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
mons | +0.011 |
bel | +0.011 |
uttering | +0.010 |
ies | +0.010 |
owers | +0.009 |
Neg logit contributions | |
� | -0.016 |
teaches | -0.015 |
penter | -0.015 |
His | -0.015 |
's | -0.014 |
Token | en |
Token ID | 268 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
Fre | +1.029 |
bel | +1.019 |
Hel | +1.016 |
Kay | +0.997 |
ora | +0.988 |
Neg logit contributions | |
DVD | -1.100 |
x | -1.081 |
omm | -1.077 |
His | -1.072 |
microwave | -1.070 |
Token | was |
Token ID | 373 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
bel | +0.142 |
Fre | +0.139 |
Kay | +0.133 |
Hel | +0.132 |
Ag | +0.131 |
Neg logit contributions | |
His | -0.145 |
omm | -0.144 |
x | -0.143 |
oscope | -0.143 |
DVD | -0.142 |
Token | a |
Token ID | 257 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
magnet | +0.017 |
icle | +0.017 |
omm | +0.017 |
motorcycle | +0.017 |
oscope | +0.017 |
Neg logit contributions | |
Fre | -0.012 |
bel | -0.012 |
Kay | -0.011 |
Hel | -0.011 |
Ag | -0.010 |
Token | bit |
Token ID | 1643 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
omm | +0.060 |
His | +0.060 |
x | +0.060 |
oscope | +0.059 |
DVD | +0.059 |
Neg logit contributions | |
bel | -0.058 |
Fre | -0.056 |
Kay | -0.054 |
Hel | -0.054 |
Ag | -0.053 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
His | +0.031 |
x | +0.031 |
omm | +0.030 |
DVD | +0.030 |
oscope | +0.030 |
Neg logit contributions | |
bel | -0.032 |
Fre | -0.032 |
Kay | -0.031 |
Hel | -0.030 |
Ag | -0.030 |
Token | of |
Token ID | 286 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
bel | +0.094 |
Fre | +0.094 |
Hel | +0.091 |
Kay | +0.091 |
Ag | +0.089 |
Neg logit contributions | |
His | -0.043 |
omm | -0.040 |
DVD | -0.040 |
x | -0.040 |
magnet | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
His | +0.186 |
x | +0.171 |
omm | +0.169 |
Your | +0.167 |
apple | +0.166 |
Neg logit contributions | |
bel | -0.256 |
Fre | -0.227 |
Hel | -0.215 |
uttering | -0.210 |
ora | -0.210 |
Token | ! |
Token ID | 0 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
bel | +0.104 |
Fre | +0.092 |
ies | +0.092 |
Hel | +0.090 |
Kay | +0.089 |
Neg logit contributions | |
omm | -0.123 |
oscope | -0.120 |
seventy | -0.119 |
DVD | -0.119 |
His | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
Fre | +0.145 |
Kay | +0.143 |
Hel | +0.142 |
bel | +0.142 |
Ag | +0.139 |
Neg logit contributions | |
x | -0.141 |
oscope | -0.139 |
magnet | -0.132 |
motorcycle | -0.131 |
boo | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
bel | +0.015 |
Fre | +0.014 |
Kay | +0.014 |
Hel | +0.014 |
Ag | +0.013 |
Neg logit contributions | |
His | -0.010 |
omm | -0.010 |
x | -0.010 |
DVD | -0.010 |
oscope | -0.010 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
bel | +0.012 |
Fre | +0.011 |
ies | +0.011 |
common | +0.011 |
ora | +0.011 |
Neg logit contributions | |
His | -0.011 |
omm | -0.011 |
DVD | -0.011 |
penter | -0.011 |
x | -0.011 |
Token | en |
Token ID | 268 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Hel | +0.945 |
bel | +0.940 |
Fre | +0.925 |
ies | +0.922 |
Kay | +0.908 |
Neg logit contributions | |
DVD | -1.157 |
His | -1.151 |
microwave | -1.139 |
x | -1.138 |
omm | -1.137 |
Token | decided |
Token ID | 3066 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
bel | +0.144 |
Fre | +0.141 |
Kay | +0.135 |
Hel | +0.134 |
Ag | +0.133 |
Neg logit contributions | |
His | -0.139 |
omm | -0.139 |
x | -0.138 |
oscope | -0.137 |
DVD | -0.137 |
Token | to |
Token ID | 284 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
His | +0.054 |
apple | +0.050 |
x | +0.050 |
motorcycle | +0.050 |
Your | +0.050 |
Neg logit contributions | |
bel | -0.055 |
Fre | -0.055 |
Hel | -0.052 |
ora | -0.051 |
Jay | -0.051 |
Token | use |
Token ID | 779 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
bel | +0.163 |
Fre | +0.163 |
Kay | +0.159 |
common | +0.155 |
Hel | +0.154 |
Neg logit contributions | |
DVD | -0.165 |
omm | -0.164 |
x | -0.151 |
oscope | -0.151 |
microwave | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
His | +0.044 |
x | +0.044 |
omm | +0.043 |
DVD | +0.043 |
oscope | +0.043 |
Neg logit contributions | |
bel | -0.049 |
Fre | -0.047 |
Kay | -0.046 |
Hel | -0.045 |
Ag | -0.045 |
Token | said |
Token ID | 531 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
bel | +0.026 |
Fre | +0.025 |
Kay | +0.024 |
Hel | +0.024 |
Ag | +0.024 |
Neg logit contributions | |
omm | -0.029 |
x | -0.029 |
His | -0.029 |
oscope | -0.029 |
DVD | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
bel | +0.065 |
Fre | +0.062 |
Hel | +0.062 |
Kay | +0.061 |
J | +0.060 |
Neg logit contributions | |
omm | -0.052 |
oscope | -0.051 |
x | -0.051 |
DVD | -0.051 |
His | -0.049 |
Token | mum |
Token ID | 25682 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
bel | +0.135 |
Fre | +0.133 |
Kay | +0.131 |
Hel | +0.130 |
J | +0.127 |
Neg logit contributions | |
oscope | -0.079 |
DVD | -0.078 |
omm | -0.078 |
x | -0.077 |
His | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
omm | +0.076 |
DVD | +0.074 |
x | +0.074 |
Promise | +0.073 |
microwave | +0.073 |
Neg logit contributions | |
bel | -0.042 |
ies | -0.039 |
Kay | -0.036 |
J | -0.036 |
Hel | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Hel | +0.039 |
bel | +0.038 |
Kay | +0.038 |
J | +0.037 |
Fre | +0.037 |
Neg logit contributions | |
x | -0.031 |
oscope | -0.030 |
icle | -0.029 |
motorcycle | -0.029 |
DVD | -0.029 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
omm | +0.264 |
His | +0.264 |
x | +0.263 |
oscope | +0.262 |
DVD | +0.261 |
Neg logit contributions | |
bel | -0.190 |
Fre | -0.183 |
Kay | -0.175 |
Hel | -0.174 |
Ag | -0.171 |
Token | ping |
Token ID | 13886 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
Fre | +1.145 |
Hel | +1.130 |
Kay | +1.111 |
bel | +1.098 |
ies | +1.084 |
Neg logit contributions | |
DVD | -0.973 |
His | -0.973 |
microwave | -0.941 |
magnet | -0.921 |
x | -0.919 |
Token | others |
Token ID | 1854 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
bel | +0.003 |
Fre | +0.003 |
Kay | +0.003 |
Hel | +0.003 |
Ag | +0.003 |
Neg logit contributions | |
His | -0.002 |
oscope | -0.002 |
omm | -0.002 |
x | -0.002 |
DVD | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
bel | +0.449 |
Fre | +0.440 |
Kay | +0.427 |
J | +0.422 |
Ag | +0.418 |
Neg logit contributions | |
oscope | -0.362 |
DVD | -0.359 |
His | -0.359 |
magnet | -0.355 |
x | -0.349 |
Token | be |
Token ID | 307 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
His | +0.064 |
x | +0.063 |
oscope | +0.063 |
omm | +0.063 |
magnet | +0.061 |
Neg logit contributions | |
bel | -0.097 |
Fre | -0.094 |
Kay | -0.091 |
Hel | -0.091 |
Ag | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
bel | +0.033 |
Fre | +0.032 |
Kay | +0.031 |
J | +0.031 |
Ag | +0.030 |
Neg logit contributions | |
His | -0.025 |
oscope | -0.024 |
x | -0.024 |
boo | -0.024 |
magnet | -0.024 |
Token | its |
Token ID | 663 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
x | +0.199 |
His | +0.198 |
omm | +0.196 |
DVD | +0.195 |
oscope | +0.195 |
Neg logit contributions | |
bel | -0.232 |
Fre | -0.226 |
Kay | -0.217 |
Hel | -0.217 |
Ag | -0.214 |
Token | nest |
Token ID | 16343 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
x | +0.046 |
His | +0.045 |
omm | +0.045 |
oscope | +0.045 |
DVD | +0.044 |
Neg logit contributions | |
bel | -0.066 |
Fre | -0.065 |
Kay | -0.063 |
Hel | -0.063 |
Ag | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
oscope | +0.109 |
His | +0.108 |
x | +0.106 |
DVD | +0.105 |
magnet | +0.105 |
Neg logit contributions | |
Fre | -0.130 |
bel | -0.127 |
Kay | -0.124 |
Hel | -0.124 |
Ag | -0.124 |
Token |
|
Token ID | 198 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
Kay | +0.039 |
Fre | +0.039 |
Hel | +0.038 |
Ag | +0.038 |
bel | +0.037 |
Neg logit contributions | |
oscope | -0.028 |
x | -0.027 |
DVD | -0.026 |
boo | -0.025 |
omm | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
bel | +0.012 |
Fre | +0.011 |
Kay | +0.011 |
Hel | +0.011 |
Ag | +0.011 |
Neg logit contributions | |
omm | -0.010 |
His | -0.009 |
x | -0.009 |
oscope | -0.009 |
DVD | -0.009 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
bel | +0.009 |
Fre | +0.009 |
Kay | +0.009 |
Hel | +0.009 |
Ag | +0.008 |
Neg logit contributions | |
His | -0.012 |
omm | -0.012 |
x | -0.012 |
oscope | -0.012 |
DVD | -0.012 |
Token | en |
Token ID | 268 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
bel | +1.056 |
Fre | +1.036 |
Hel | +1.034 |
Kay | +1.022 |
ora | +0.972 |
Neg logit contributions | |
DVD | -1.062 |
His | -1.058 |
omm | -1.051 |
x | -1.047 |
microwave | -1.031 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
bel | +0.142 |
Fre | +0.141 |
Ag | +0.134 |
Kay | +0.133 |
Hel | +0.131 |
Neg logit contributions | |
His | -0.140 |
oscope | -0.138 |
omm | -0.136 |
x | -0.134 |
penter | -0.132 |
Token | sorry |
Token ID | 7926 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
bel | +0.383 |
Fre | +0.374 |
Hel | +0.359 |
Kay | +0.358 |
Ag | +0.357 |
Neg logit contributions | |
omm | -0.408 |
oscope | -0.391 |
x | -0.391 |
icle | -0.389 |
DVD | -0.387 |
Token | for |
Token ID | 329 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
oscope | +0.237 |
omm | +0.235 |
DVD | +0.232 |
x | +0.229 |
seventy | +0.223 |
Neg logit contributions | |
bel | -0.396 |
Hel | -0.374 |
Fre | -0.372 |
Ag | -0.370 |
Kay | -0.367 |
Token | the |
Token ID | 262 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
omm | +0.213 |
His | +0.210 |
oscope | +0.210 |
DVD | +0.210 |
x | +0.208 |
Neg logit contributions | |
bel | -0.233 |
Fre | -0.228 |
Kay | -0.221 |
Hel | -0.220 |
Ag | -0.216 |
Token | found |
Token ID | 1043 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
bel | +0.097 |
Fre | +0.094 |
Kay | +0.091 |
Hel | +0.089 |
Ag | +0.089 |
Neg logit contributions | |
oscope | -0.095 |
His | -0.095 |
x | -0.094 |
omm | -0.094 |
DVD | -0.094 |
Token | me |
Token ID | 502 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
bel | +0.200 |
Fre | +0.198 |
Hel | +0.191 |
Kay | +0.191 |
Ag | +0.186 |
Neg logit contributions | |
omm | -0.173 |
His | -0.168 |
oscope | -0.167 |
DVD | -0.166 |
x | -0.164 |
Token | ." |
Token ID | 526 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
omm | +0.020 |
His | +0.019 |
x | +0.019 |
DVD | +0.019 |
magnet | +0.018 |
Neg logit contributions | |
bel | -0.022 |
Fre | -0.021 |
Hel | -0.020 |
Kay | -0.020 |
Ag | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
omm | +0.118 |
x | +0.118 |
oscope | +0.117 |
DVD | +0.116 |
His | +0.115 |
Neg logit contributions | |
bel | -0.135 |
Fre | -0.132 |
Hel | -0.129 |
Kay | -0.128 |
Ag | -0.126 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
bel | +0.011 |
Fre | +0.011 |
Kay | +0.010 |
Hel | +0.010 |
Ag | +0.010 |
Neg logit contributions | |
His | -0.008 |
omm | -0.008 |
x | -0.008 |
DVD | -0.008 |
oscope | -0.008 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
bel | +0.009 |
ies | +0.009 |
Fre | +0.008 |
ora | +0.008 |
common | +0.008 |
Neg logit contributions | |
His | -0.008 |
penter | -0.008 |
oscope | -0.008 |
Your | -0.008 |
magnet | -0.008 |
Token | en |
Token ID | 268 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Hel | +1.011 |
Fre | +1.002 |
bel | +0.984 |
Kay | +0.978 |
ies | +0.974 |
Neg logit contributions | |
His | -1.114 |
DVD | -1.107 |
microwave | -1.097 |
x | -1.089 |
omm | -1.068 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
bel | +0.138 |
Fre | +0.134 |
Kay | +0.129 |
Hel | +0.128 |
Ag | +0.127 |
Neg logit contributions | |
omm | -0.140 |
His | -0.140 |
x | -0.139 |
oscope | -0.139 |
DVD | -0.138 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bel | +0.102 |
Fre | +0.098 |
Hel | +0.096 |
Kay | +0.096 |
Ag | +0.094 |
Neg logit contributions | |
x | -0.089 |
oscope | -0.088 |
omm | -0.087 |
DVD | -0.087 |
His | -0.083 |
Token | gently |
Token ID | 15165 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
omm | +0.074 |
x | +0.074 |
oscope | +0.073 |
DVD | +0.072 |
His | +0.072 |
Neg logit contributions | |
bel | -0.075 |
Fre | -0.073 |
Kay | -0.070 |
Hel | -0.070 |
Ag | -0.069 |
Token | placed |
Token ID | 4624 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
His | +0.219 |
oscope | +0.213 |
x | +0.207 |
DVD | +0.206 |
omm | +0.204 |
Neg logit contributions | |
bel | -0.269 |
Fre | -0.269 |
Kay | -0.256 |
Hel | -0.254 |
Ag | -0.252 |
Token | her |
Token ID | 607 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
His | +0.097 |
x | +0.096 |
oscope | +0.093 |
apple | +0.091 |
DVD | +0.091 |
Neg logit contributions | |
bel | -0.124 |
Fre | -0.116 |
Ag | -0.113 |
uttering | -0.109 |
Kay | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
bel | +0.102 |
Fre | +0.098 |
Kay | +0.094 |
Hel | +0.093 |
Ag | +0.091 |
Neg logit contributions | |
omm | -0.109 |
His | -0.108 |
x | -0.108 |
DVD | -0.107 |
oscope | -0.107 |
Token | |
Token ID | 220 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
bel | +0.038 |
Fre | +0.037 |
Kay | +0.035 |
Ag | +0.034 |
J | +0.034 |
Neg logit contributions | |
His | -0.023 |
omm | -0.021 |
DVD | -0.020 |
penter | -0.020 |
magnet | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
oscope | +0.074 |
x | +0.074 |
omm | +0.073 |
DVD | +0.072 |
magnet | +0.071 |
Neg logit contributions | |
bel | -0.074 |
Fre | -0.072 |
Kay | -0.071 |
Hel | -0.070 |
Ag | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
bel | +0.008 |
ies | +0.008 |
ymes | +0.007 |
uttering | +0.007 |
Fre | +0.007 |
Neg logit contributions | |
His | -0.003 |
teaches | -0.002 |
From | -0.002 |
� | -0.002 |
Your | -0.002 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
ies | +0.004 |
bel | +0.004 |
mons | +0.004 |
suits | +0.004 |
uttering | +0.004 |
Neg logit contributions | |
� | -0.006 |
teaches | -0.006 |
His | -0.006 |
penter | -0.005 |
` | -0.005 |
Token | en |
Token ID | 268 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
bel | +1.079 |
Fre | +1.071 |
Hel | +1.054 |
Kay | +1.040 |
ora | +1.006 |
Neg logit contributions | |
DVD | -1.022 |
His | -1.022 |
x | -1.020 |
omm | -1.016 |
magnet | -0.999 |
Token | was |
Token ID | 373 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
bel | +0.136 |
Fre | +0.132 |
Kay | +0.127 |
Hel | +0.126 |
Ag | +0.124 |
Neg logit contributions | |
omm | -0.133 |
x | -0.132 |
His | -0.132 |
DVD | -0.131 |
oscope | -0.131 |
Token | very |
Token ID | 845 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
omm | +0.022 |
x | +0.022 |
oscope | +0.021 |
magnet | +0.021 |
His | +0.021 |
Neg logit contributions | |
bel | -0.025 |
Fre | -0.025 |
Kay | -0.024 |
Hel | -0.024 |
Ag | -0.023 |
Token | proud |
Token ID | 6613 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
His | +0.023 |
boo | +0.021 |
DVD | +0.020 |
seventy | +0.020 |
omm | +0.020 |
Neg logit contributions | |
bel | -0.029 |
Hel | -0.029 |
Fre | -0.029 |
Ag | -0.028 |
Kay | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
bel | +0.078 |
Fre | +0.077 |
Hel | +0.075 |
Kay | +0.075 |
Ag | +0.073 |
Neg logit contributions | |
His | -0.041 |
omm | -0.039 |
x | -0.038 |
DVD | -0.038 |
magnet | -0.037 |
Token | much |
Token ID | 881 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
bel | +0.225 |
Fre | +0.218 |
Kay | +0.211 |
Hel | +0.210 |
Ag | +0.208 |
Neg logit contributions | |
omm | -0.190 |
His | -0.189 |
x | -0.188 |
oscope | -0.187 |
DVD | -0.186 |
Token | better |
Token ID | 1365 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
omm | +0.049 |
His | +0.048 |
x | +0.048 |
oscope | +0.048 |
DVD | +0.047 |
Neg logit contributions | |
bel | -0.107 |
Fre | -0.104 |
Kay | -0.102 |
Hel | -0.101 |
Ag | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
apple | +0.296 |
knee | +0.286 |
magnet | +0.283 |
oll | +0.282 |
motorcycle | +0.273 |
Neg logit contributions | |
Fre | -0.644 |
Hel | -0.631 |
Kay | -0.615 |
bel | -0.600 |
Jud | -0.593 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
bel | +0.040 |
Fre | +0.039 |
ies | +0.037 |
common | +0.036 |
ora | +0.036 |
Neg logit contributions | |
His | -0.021 |
Your | -0.017 |
omm | -0.017 |
That | -0.016 |
Tomorrow | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
bel | +0.007 |
ies | +0.006 |
Fre | +0.006 |
Ag | +0.006 |
ora | +0.006 |
Neg logit contributions | |
His | -0.003 |
x | -0.002 |
DVD | -0.002 |
omm | -0.002 |
Your | -0.002 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
bel | +0.004 |
ies | +0.004 |
mons | +0.004 |
suits | +0.004 |
bows | +0.004 |
Neg logit contributions | |
� | -0.005 |
His | -0.005 |
teaches | -0.005 |
penter | -0.005 |
From | -0.005 |
Token | en |
Token ID | 268 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
bel | +1.111 |
Fre | +1.087 |
Hel | +1.066 |
Kay | +1.058 |
Ag | +1.025 |
Neg logit contributions | |
His | -0.999 |
omm | -0.995 |
DVD | -0.992 |
x | -0.987 |
magnet | -0.961 |
Token | had |
Token ID | 550 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
bel | +0.144 |
Fre | +0.144 |
Ag | +0.136 |
Kay | +0.136 |
Hel | +0.135 |
Neg logit contributions | |
His | -0.122 |
oscope | -0.121 |
omm | -0.119 |
x | -0.117 |
penter | -0.116 |
Token | worked |
Token ID | 3111 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
His | +0.006 |
x | +0.006 |
omm | +0.006 |
boo | +0.006 |
apple | +0.006 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.009 |
ora | -0.009 |
Kay | -0.009 |
Hel | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
x | +0.002 |
His | +0.002 |
magnet | +0.002 |
DVD | +0.002 |
omm | +0.002 |
Neg logit contributions | |
Fre | -0.003 |
bel | -0.003 |
ora | -0.003 |
Kay | -0.003 |
Hel | -0.003 |
Token | hard |
Token ID | 1327 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
His | +0.110 |
x | +0.106 |
apple | +0.102 |
omm | +0.102 |
magnet | +0.102 |
Neg logit contributions | |
bel | -0.133 |
Fre | -0.132 |
Kay | -0.125 |
Ag | -0.125 |
ora | -0.123 |
Token | our |
Token ID | 674 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
omm | +0.197 |
His | +0.194 |
oscope | +0.193 |
DVD | +0.191 |
x | +0.191 |
Neg logit contributions | |
Fre | -0.237 |
bel | -0.234 |
Kay | -0.227 |
Hel | -0.227 |
Ag | -0.221 |
Token | game |
Token ID | 983 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
omm | +0.096 |
His | +0.095 |
x | +0.095 |
oscope | +0.095 |
DVD | +0.094 |
Neg logit contributions | |
bel | -0.090 |
Fre | -0.087 |
Kay | -0.084 |
Hel | -0.083 |
Ag | -0.082 |
Token | ". |
Token ID | 1911 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
x | +0.041 |
omm | +0.041 |
His | +0.040 |
oscope | +0.040 |
DVD | +0.040 |
Neg logit contributions | |
bel | -0.052 |
Fre | -0.050 |
Kay | -0.048 |
Hel | -0.048 |
Ag | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
His | +0.099 |
Your | +0.079 |
DVD | +0.079 |
magnet | +0.078 |
That | +0.077 |
Neg logit contributions | |
bel | -0.165 |
Fre | -0.157 |
ies | -0.149 |
Kay | -0.145 |
uttering | -0.145 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
bel | +0.002 |
Fre | +0.002 |
ies | +0.002 |
Kay | +0.002 |
Ag | +0.002 |
Neg logit contributions | |
His | -0.001 |
DVD | -0.001 |
x | -0.001 |
omm | -0.001 |
magnet | -0.001 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
ies | +0.001 |
bel | +0.001 |
mons | +0.001 |
bows | +0.001 |
uttering | +0.001 |
Neg logit contributions | |
teaches | -0.002 |
His | -0.002 |
� | -0.002 |
penter | -0.002 |
From | -0.002 |
Token | en |
Token ID | 268 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
bel | +1.065 |
Fre | +1.059 |
Hel | +1.054 |
Kay | +1.029 |
Ag | +0.998 |
Neg logit contributions | |
x | -1.030 |
omm | -1.023 |
His | -1.018 |
DVD | -1.011 |
microwave | -0.995 |
Token | was |
Token ID | 373 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
bel | +0.134 |
Fre | +0.131 |
Kay | +0.126 |
Hel | +0.125 |
Ag | +0.124 |
Neg logit contributions | |
His | -0.128 |
omm | -0.127 |
oscope | -0.126 |
x | -0.126 |
DVD | -0.125 |
Token | so |
Token ID | 523 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
x | +0.027 |
oscope | +0.027 |
magnet | +0.026 |
omm | +0.026 |
motorcycle | +0.026 |
Neg logit contributions | |
Fre | -0.026 |
bel | -0.026 |
Kay | -0.026 |
Hel | -0.025 |
Ag | -0.025 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
His | +0.123 |
omm | +0.119 |
DVD | +0.119 |
x | +0.118 |
oscope | +0.116 |
Neg logit contributions | |
bel | -0.123 |
Fre | -0.120 |
Hel | -0.116 |
Kay | -0.115 |
Ag | -0.114 |
Token | she |
Token ID | 673 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
His | +0.047 |
omm | +0.042 |
penter | +0.042 |
motorcycle | +0.042 |
magnet | +0.041 |
Neg logit contributions | |
Fre | -0.083 |
bel | -0.083 |
Hel | -0.080 |
Kay | -0.078 |
Ag | -0.077 |
Token | be |
Token ID | 307 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
bel | +0.183 |
Fre | +0.179 |
Kay | +0.174 |
Hel | +0.173 |
Ag | +0.170 |
Neg logit contributions | |
omm | -0.124 |
DVD | -0.122 |
His | -0.121 |
x | -0.120 |
oscope | -0.120 |
Token | together |
Token ID | 1978 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
Fre | +0.019 |
bel | +0.018 |
Kay | +0.017 |
ora | +0.017 |
Jay | +0.017 |
Neg logit contributions | |
His | -0.014 |
x | -0.013 |
DVD | -0.013 |
penter | -0.013 |
oscope | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
bel | +0.290 |
Fre | +0.286 |
Kay | +0.276 |
Hel | +0.273 |
Ag | +0.271 |
Neg logit contributions | |
His | -0.259 |
DVD | -0.256 |
oscope | -0.256 |
x | -0.255 |
omm | -0.250 |
Token |
|
Token ID | 198 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
bel | +0.033 |
Fre | +0.031 |
ymes | +0.029 |
Ag | +0.029 |
Kay | +0.029 |
Neg logit contributions | |
His | -0.018 |
Your | -0.014 |
omm | -0.014 |
penter | -0.014 |
magnet | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
His | +0.001 |
It | +0.000 |
Your | +0.000 |
From | +0.000 |
DVD | +0.000 |
Neg logit contributions | |
bel | -0.001 |
Fre | -0.001 |
ies | -0.001 |
ymes | -0.001 |
bows | -0.001 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
His | +0.000 |
� | +0.000 |
penter | +0.000 |
From | +0.000 |
teaches | +0.000 |
Neg logit contributions | |
bel | -0.000 |
ymes | -0.000 |
ies | -0.000 |
mons | -0.000 |
bows | -0.000 |
Token | en |
Token ID | 268 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
bel | +1.146 |
Fre | +1.123 |
Kay | +1.086 |
Hel | +1.086 |
Ag | +1.060 |
Neg logit contributions | |
omm | -0.951 |
His | -0.946 |
x | -0.946 |
DVD | -0.942 |
oscope | -0.929 |
Token | 's |
Token ID | 338 |
Feature activation | +7.74e+00 |
Pos logit contributions | |
bel | +0.130 |
Fre | +0.127 |
Ag | +0.118 |
Kay | +0.118 |
Hel | +0.117 |
Neg logit contributions | |
His | -0.131 |
oscope | -0.123 |
penter | -0.121 |
omm | -0.121 |
x | -0.117 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
omm | +0.522 |
x | +0.520 |
DVD | +0.520 |
oscope | +0.520 |
His | +0.520 |
Neg logit contributions | |
bel | -0.509 |
Fre | -0.492 |
Kay | -0.475 |
Hel | -0.470 |
Ag | -0.462 |
Token | were |
Token ID | 547 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
bel | +0.328 |
Fre | +0.304 |
common | +0.292 |
Ag | +0.284 |
Kay | +0.279 |
Neg logit contributions | |
His | -0.340 |
penter | -0.319 |
oscope | -0.319 |
magnet | -0.314 |
boo | -0.313 |
Token | very |
Token ID | 845 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
bel | +0.341 |
Fre | +0.330 |
Kay | +0.318 |
Hel | +0.317 |
Ag | +0.314 |
Neg logit contributions | |
His | -0.292 |
omm | -0.291 |
x | -0.290 |
DVD | -0.287 |
oscope | -0.286 |
Token | can |
Token ID | 460 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
magnet | +0.038 |
x | +0.037 |
oscope | +0.037 |
His | +0.037 |
DVD | +0.036 |
Neg logit contributions | |
bel | -0.058 |
Fre | -0.058 |
Kay | -0.057 |
Ag | -0.055 |
Hel | -0.055 |
Token | find |
Token ID | 1064 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
His | +0.080 |
x | +0.080 |
omm | +0.079 |
magnet | +0.078 |
oscope | +0.077 |
Neg logit contributions | |
bel | -0.113 |
Fre | -0.113 |
Hel | -0.110 |
Kay | -0.109 |
Ag | -0.108 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
x | +0.045 |
DVD | +0.044 |
His | +0.044 |
omm | +0.044 |
oscope | +0.044 |
Neg logit contributions | |
bel | -0.065 |
Fre | -0.064 |
Kay | -0.062 |
Hel | -0.062 |
Ag | -0.061 |
Token |
|
Token ID | 198 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
bel | +0.028 |
Fre | +0.026 |
uttering | +0.025 |
as | +0.024 |
ies | +0.024 |
Neg logit contributions | |
His | -0.012 |
That | -0.011 |
Your | -0.010 |
It | -0.010 |
's | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +8.27e-02 |
Pos logit contributions | |
His | +0.002 |
� | +0.002 |
It | +0.002 |
teaches | +0.002 |
From | +0.002 |
Neg logit contributions | |
bel | -0.008 |
mons | -0.007 |
ies | -0.007 |
uttering | -0.007 |
Fre | -0.007 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
� | +0.007 |
's | +0.006 |
teaches | +0.006 |
His | +0.006 |
From | +0.006 |
Neg logit contributions | |
bel | -0.004 |
mons | -0.004 |
uttering | -0.004 |
ies | -0.004 |
owers | -0.004 |
Token | en |
Token ID | 268 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
bel | +1.123 |
Fre | +1.100 |
Kay | +1.069 |
Hel | +1.069 |
Ag | +1.040 |
Neg logit contributions | |
His | -0.963 |
omm | -0.962 |
x | -0.959 |
DVD | -0.957 |
oscope | -0.942 |
Token | opened |
Token ID | 4721 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Fre | +0.125 |
bel | +0.124 |
Ag | +0.117 |
Hel | +0.116 |
Kay | +0.116 |
Neg logit contributions | |
His | -0.125 |
omm | -0.122 |
oscope | -0.121 |
x | -0.118 |
penter | -0.117 |
Token | the |
Token ID | 262 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
His | +0.123 |
x | +0.120 |
omm | +0.120 |
magnet | +0.118 |
DVD | +0.117 |
Neg logit contributions | |
bel | -0.163 |
Fre | -0.157 |
Ag | -0.153 |
Hel | -0.152 |
Kay | -0.151 |
Token | cabinet |
Token ID | 13447 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
bel | +0.030 |
Fre | +0.029 |
Kay | +0.028 |
Hel | +0.028 |
Ag | +0.027 |
Neg logit contributions | |
His | -0.018 |
oscope | -0.017 |
omm | -0.017 |
DVD | -0.017 |
x | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
omm | +0.037 |
x | +0.037 |
oscope | +0.037 |
His | +0.037 |
DVD | +0.037 |
Neg logit contributions | |
bel | -0.046 |
Fre | -0.044 |
Kay | -0.043 |
Hel | -0.043 |
J | -0.042 |
Token | marry |
Token ID | 12479 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
bel | +0.091 |
Fre | +0.089 |
Hel | +0.086 |
Kay | +0.086 |
Ag | +0.084 |
Neg logit contributions | |
omm | -0.072 |
DVD | -0.070 |
x | -0.069 |
His | -0.069 |
oscope | -0.069 |
Token | him |
Token ID | 683 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
bel | +0.069 |
Fre | +0.068 |
Ag | +0.066 |
Kay | +0.066 |
Hel | +0.065 |
Neg logit contributions | |
His | -0.041 |
x | -0.041 |
oscope | -0.040 |
DVD | -0.040 |
omm | -0.039 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
omm | +0.092 |
oscope | +0.092 |
His | +0.090 |
Promise | +0.088 |
x | +0.088 |
Neg logit contributions | |
bel | -0.113 |
Fre | -0.110 |
Hel | -0.104 |
ies | -0.102 |
Kay | -0.102 |
Token |
|
Token ID | 198 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
His | +0.185 |
Your | +0.140 |
It | +0.139 |
That | +0.136 |
penter | +0.134 |
Neg logit contributions | |
bel | -0.274 |
Fre | -0.252 |
ymes | -0.250 |
uttering | -0.249 |
as | -0.240 |
Token |
|
Token ID | 198 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
His | +0.003 |
It | +0.002 |
From | +0.002 |
Your | +0.002 |
He | +0.002 |
Neg logit contributions | |
bel | -0.008 |
ies | -0.008 |
ymes | -0.007 |
bows | -0.007 |
uttering | -0.007 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
His | +0.006 |
� | +0.006 |
penter | +0.005 |
From | +0.005 |
's | +0.005 |
Neg logit contributions | |
bel | -0.004 |
mons | -0.003 |
ies | -0.003 |
uttering | -0.003 |
ymes | -0.003 |
Token | en |
Token ID | 268 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
bel | +1.059 |
Fre | +1.057 |
Hel | +1.038 |
Kay | +1.022 |
ora | +0.990 |
Neg logit contributions | |
DVD | -1.019 |
x | -1.007 |
His | -1.006 |
omm | -1.004 |
magnet | -0.977 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bel | +0.132 |
Fre | +0.129 |
Kay | +0.121 |
Ag | +0.121 |
Hel | +0.120 |
Neg logit contributions | |
His | -0.121 |
omm | -0.115 |
oscope | -0.114 |
penter | -0.112 |
x | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
bel | +0.093 |
Fre | +0.091 |
Kay | +0.088 |
Hel | +0.087 |
Ag | +0.086 |
Neg logit contributions | |
omm | -0.067 |
x | -0.067 |
His | -0.067 |
oscope | -0.066 |
DVD | -0.066 |
Token | said |
Token ID | 531 |
Feature activation | -6.57e-01 |
Pos logit contributions | |
His | +0.088 |
omm | +0.083 |
x | +0.082 |
DVD | +0.082 |
penter | +0.081 |
Neg logit contributions | |
bel | -0.093 |
Fre | -0.090 |
Hel | -0.086 |
Kay | -0.085 |
Ag | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
bel | +0.049 |
Fre | +0.048 |
Kay | +0.046 |
Hel | +0.046 |
Ag | +0.045 |
Neg logit contributions | |
His | -0.041 |
omm | -0.038 |
magnet | -0.037 |
seventy | -0.037 |
Your | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
omm | +0.258 |
oscope | +0.255 |
x | +0.245 |
DVD | +0.245 |
penter | +0.240 |
Neg logit contributions | |
bel | -0.236 |
Kay | -0.225 |
J | -0.225 |
ora | -0.224 |
Fre | -0.221 |
Token | |
Token ID | 220 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
bel | +0.024 |
Fre | +0.024 |
Kay | +0.023 |
Ag | +0.023 |
Hel | +0.023 |
Neg logit contributions | |
His | -0.012 |
omm | -0.011 |
x | -0.011 |
DVD | -0.011 |
oscope | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
oscope | +0.087 |
x | +0.085 |
omm | +0.085 |
DVD | +0.085 |
magnet | +0.084 |
Neg logit contributions | |
bel | -0.084 |
Fre | -0.082 |
Kay | -0.081 |
Hel | -0.080 |
Ag | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
His | +0.005 |
DVD | +0.005 |
omm | +0.004 |
Your | +0.004 |
x | +0.004 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.009 |
ies | -0.009 |
ora | -0.009 |
Ag | -0.009 |
Token | " |
Token ID | 1 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
His | +0.006 |
� | +0.006 |
teaches | +0.006 |
Your | +0.006 |
penter | +0.006 |
Neg logit contributions | |
bel | -0.007 |
ies | -0.007 |
Fre | -0.007 |
ora | -0.006 |
mons | -0.006 |
Token | Hel |
Token ID | 12621 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
omm | +0.109 |
His | +0.109 |
x | +0.108 |
oscope | +0.108 |
DVD | +0.107 |
Neg logit contributions | |
bel | -0.078 |
Fre | -0.076 |
Kay | -0.073 |
Hel | -0.072 |
Ag | -0.071 |
Token | en |
Token ID | 268 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
Fre | +0.991 |
ies | +0.968 |
Kay | +0.963 |
Hel | +0.952 |
ora | +0.939 |
Neg logit contributions | |
DVD | -1.119 |
His | -1.096 |
microwave | -1.092 |
magnet | -1.064 |
Promise | -1.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
bel | +0.126 |
Fre | +0.121 |
Kay | +0.116 |
Hel | +0.115 |
Ag | +0.113 |
Neg logit contributions | |
omm | -0.118 |
x | -0.118 |
His | -0.117 |
DVD | -0.116 |
oscope | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Fre | +0.088 |
bel | +0.083 |
Kay | +0.083 |
Hel | +0.080 |
J | +0.079 |
Neg logit contributions | |
omm | -0.090 |
His | -0.089 |
penter | -0.089 |
DVD | -0.089 |
oscope | -0.087 |
Token | is |
Token ID | 318 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
omm | +0.106 |
DVD | +0.100 |
penter | +0.099 |
His | +0.098 |
x | +0.097 |
Neg logit contributions | |
bel | -0.146 |
Fre | -0.144 |
ies | -0.142 |
Hel | -0.139 |
Kay | -0.139 |
Token | not |
Token ID | 407 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
oscope | +0.141 |
DVD | +0.133 |
His | +0.131 |
penter | +0.128 |
motorcycle | +0.128 |
Neg logit contributions | |
Fre | -0.096 |
common | -0.096 |
bel | -0.090 |
Jud | -0.088 |
Kay | -0.088 |
Token | flowers |
Token ID | 12734 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
bel | +0.432 |
Hel | +0.416 |
Fre | +0.415 |
Kay | +0.410 |
Ag | +0.405 |
Neg logit contributions | |
x | -0.331 |
His | -0.328 |
apple | -0.325 |
DVD | -0.322 |
magnet | -0.313 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bel | +0.559 |
Kay | +0.547 |
Fre | +0.545 |
J | +0.545 |
Hel | +0.542 |
Neg logit contributions | |
apple | -0.335 |
His | -0.330 |
oscope | -0.330 |
magnet | -0.327 |
x | -0.326 |
Token | cookies |
Token ID | 14746 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
apple | +0.067 |
His | +0.066 |
oscope | +0.065 |
x | +0.064 |
magnet | +0.064 |
Neg logit contributions | |
bel | -0.068 |
Fre | -0.068 |
Ag | -0.068 |
Kay | -0.068 |
J | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
oscope | +0.091 |
x | +0.089 |
apple | +0.089 |
DVD | +0.089 |
His | +0.089 |
Neg logit contributions | |
bel | -0.142 |
Fre | -0.142 |
Kay | -0.139 |
Hel | -0.139 |
Ag | -0.135 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
apple | +0.066 |
His | +0.065 |
oscope | +0.065 |
x | +0.064 |
magnet | +0.064 |
Neg logit contributions | |
bel | -0.068 |
Fre | -0.068 |
Kay | -0.067 |
Ag | -0.067 |
Hel | -0.067 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.132 |
Hel | +0.119 |
J | +0.118 |
Kay | +0.116 |
Jay | +0.114 |
Neg logit contributions | |
oscope | -0.268 |
icle | -0.258 |
penter | -0.252 |
DVD | -0.249 |
apple | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
Fre | +1.245 |
Kay | +1.202 |
bel | +1.202 |
Hel | +1.193 |
Ag | +1.180 |
Neg logit contributions | |
DVD | -0.791 |
apple | -0.789 |
oscope | -0.785 |
magnet | -0.771 |
penter | -0.750 |
Token | She |
Token ID | 1375 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Fre | +0.041 |
bel | +0.041 |
Hel | +0.040 |
Kay | +0.040 |
Ag | +0.039 |
Neg logit contributions | |
x | -0.036 |
oscope | -0.036 |
DVD | -0.035 |
omm | -0.035 |
boo | -0.035 |
Token | could |
Token ID | 714 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
bel | +0.195 |
Fre | +0.186 |
Ag | +0.185 |
Kay | +0.183 |
Hel | +0.182 |
Neg logit contributions | |
oscope | -0.158 |
His | -0.158 |
boo | -0.150 |
teaches | -0.150 |
omm | -0.149 |
Token | smell |
Token ID | 8508 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
His | +0.056 |
x | +0.056 |
oscope | +0.055 |
omm | +0.054 |
boo | +0.053 |
Neg logit contributions | |
bel | -0.062 |
Hel | -0.060 |
Fre | -0.060 |
Ag | -0.060 |
J | -0.060 |
Token | when |
Token ID | 618 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
bel | +0.441 |
Hel | +0.426 |
Fre | +0.420 |
Kay | +0.417 |
Ag | +0.413 |
Neg logit contributions | |
apple | -0.324 |
x | -0.324 |
His | -0.321 |
DVD | -0.313 |
magnet | -0.303 |
Token | inside |
Token ID | 2641 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
x | +0.237 |
His | +0.231 |
DVD | +0.230 |
oscope | +0.229 |
magnet | +0.229 |
Neg logit contributions | |
bel | -0.281 |
Fre | -0.279 |
Kay | -0.270 |
Ag | -0.270 |
Hel | -0.268 |
Token | the |
Token ID | 262 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
His | +0.044 |
x | +0.043 |
DVD | +0.043 |
omm | +0.043 |
oscope | +0.042 |
Neg logit contributions | |
bel | -0.058 |
Fre | -0.058 |
Kay | -0.055 |
Hel | -0.055 |
Ag | -0.055 |
Token | cave |
Token ID | 11527 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
bel | +0.052 |
Fre | +0.051 |
Kay | +0.049 |
Hel | +0.049 |
Ag | +0.049 |
Neg logit contributions | |
x | -0.039 |
His | -0.038 |
DVD | -0.038 |
omm | -0.038 |
oscope | -0.038 |
Token | as |
Token ID | 355 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
Fre | +0.144 |
bel | +0.143 |
Kay | +0.138 |
Hel | +0.138 |
Ag | +0.137 |
Neg logit contributions | |
His | -0.115 |
x | -0.111 |
omm | -0.111 |
oscope | -0.111 |
DVD | -0.110 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
His | +0.177 |
x | +0.175 |
magnet | +0.172 |
DVD | +0.168 |
omm | +0.166 |
Neg logit contributions | |
bel | -0.302 |
Fre | -0.302 |
Kay | -0.292 |
Ag | -0.292 |
Hel | -0.288 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.216 |
Kay | +0.197 |
Hel | +0.195 |
common | +0.194 |
J | +0.193 |
Neg logit contributions | |
oscope | -0.175 |
icle | -0.174 |
penter | -0.173 |
His | -0.173 |
x | -0.164 |
Token | appeared |
Token ID | 4120 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
Fre | +1.164 |
bel | +1.149 |
Kay | +1.114 |
Hel | +1.104 |
Ag | +1.083 |
Neg logit contributions | |
His | -0.851 |
DVD | -0.840 |
oscope | -0.838 |
x | -0.828 |
magnet | -0.826 |
Token | in |
Token ID | 287 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
Fre | +0.248 |
bel | +0.246 |
Kay | +0.237 |
Hel | +0.233 |
Ag | +0.232 |
Neg logit contributions | |
His | -0.191 |
x | -0.187 |
oscope | -0.185 |
omm | -0.185 |
magnet | -0.183 |
Token | the |
Token ID | 262 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
bel | +0.077 |
Fre | +0.075 |
Ag | +0.072 |
Hel | +0.072 |
Kay | +0.072 |
Neg logit contributions | |
His | -0.051 |
x | -0.050 |
magnet | -0.050 |
DVD | -0.049 |
omm | -0.048 |
Token | sky |
Token ID | 6766 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
bel | +0.041 |
Fre | +0.039 |
Hel | +0.038 |
Kay | +0.038 |
Ag | +0.037 |
Neg logit contributions | |
omm | -0.048 |
His | -0.047 |
x | -0.047 |
oscope | -0.047 |
DVD | -0.046 |
Token | after |
Token ID | 706 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Fre | +0.298 |
bel | +0.297 |
Kay | +0.284 |
Hel | +0.283 |
Ag | +0.281 |
Neg logit contributions | |
His | -0.253 |
oscope | -0.244 |
DVD | -0.244 |
x | -0.242 |
omm | -0.241 |
Token | . |
Token ID | 13 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
bel | +0.210 |
Fre | +0.198 |
Kay | +0.187 |
Hel | +0.187 |
Ag | +0.186 |
Neg logit contributions | |
omm | -0.242 |
His | -0.241 |
x | -0.234 |
oscope | -0.232 |
DVD | -0.229 |
Token | Because |
Token ID | 4362 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Hel | +0.040 |
Fre | +0.039 |
Like | +0.039 |
Ag | +0.037 |
Kay | +0.037 |
Neg logit contributions | |
oscope | -0.035 |
urger | -0.033 |
motorcycle | -0.033 |
ingu | -0.032 |
affle | -0.032 |
Token | I |
Token ID | 314 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
His | +0.063 |
x | +0.063 |
omm | +0.062 |
DVD | +0.062 |
oscope | +0.061 |
Neg logit contributions | |
bel | -0.087 |
Fre | -0.085 |
Kay | -0.082 |
Hel | -0.082 |
Ag | -0.081 |
Token | like |
Token ID | 588 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
x | +0.233 |
His | +0.232 |
oscope | +0.230 |
DVD | +0.226 |
magnet | +0.224 |
Neg logit contributions | |
bel | -0.272 |
Fre | -0.266 |
Kay | -0.261 |
Hel | -0.256 |
Ag | -0.253 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
bel | +0.223 |
Fre | +0.217 |
Hel | +0.208 |
Kay | +0.206 |
Ag | +0.204 |
Neg logit contributions | |
omm | -0.235 |
oscope | -0.231 |
His | -0.229 |
x | -0.228 |
DVD | -0.227 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.199 |
bel | +0.194 |
Hel | +0.193 |
Kay | +0.193 |
Jud | +0.191 |
Neg logit contributions | |
oscope | -0.188 |
DVD | -0.187 |
icle | -0.183 |
x | -0.183 |
omm | -0.182 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
bel | +1.114 |
Fre | +1.085 |
Kay | +1.055 |
Hel | +1.048 |
Ag | +1.036 |
Neg logit contributions | |
His | -0.900 |
omm | -0.897 |
DVD | -0.895 |
x | -0.894 |
oscope | -0.890 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bel | +0.118 |
Fre | +0.116 |
Hel | +0.112 |
Ag | +0.111 |
Kay | +0.111 |
Neg logit contributions | |
omm | -0.109 |
oscope | -0.107 |
DVD | -0.106 |
His | -0.105 |
x | -0.105 |
Token | they |
Token ID | 484 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
His | +0.071 |
x | +0.071 |
omm | +0.071 |
oscope | +0.070 |
DVD | +0.070 |
Neg logit contributions | |
bel | -0.065 |
Fre | -0.063 |
Kay | -0.061 |
Hel | -0.060 |
Ag | -0.060 |
Token | make |
Token ID | 787 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
bel | +0.246 |
Fre | +0.243 |
Kay | +0.242 |
J | +0.237 |
Ag | +0.235 |
Neg logit contributions | |
oscope | -0.186 |
x | -0.183 |
magnet | -0.180 |
DVD | -0.178 |
boo | -0.176 |
Token | me |
Token ID | 502 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
bel | +0.084 |
Fre | +0.083 |
Kay | +0.079 |
Hel | +0.078 |
Ag | +0.077 |
Neg logit contributions | |
x | -0.087 |
His | -0.086 |
DVD | -0.086 |
omm | -0.086 |
oscope | -0.085 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
Fre | +0.546 |
bel | +0.533 |
Kay | +0.525 |
Hel | +0.522 |
Ag | +0.515 |
Neg logit contributions | |
DVD | -0.353 |
oscope | -0.351 |
His | -0.350 |
magnet | -0.349 |
x | -0.348 |
Token | stars |
Token ID | 5788 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
Fre | +0.115 |
bel | +0.112 |
Kay | +0.110 |
Ag | +0.108 |
Hel | +0.107 |
Neg logit contributions | |
oscope | -0.114 |
x | -0.114 |
His | -0.114 |
DVD | -0.112 |
magnet | -0.111 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
bel | +0.362 |
Fre | +0.358 |
Kay | +0.349 |
Ag | +0.342 |
Hel | +0.342 |
Neg logit contributions | |
DVD | -0.271 |
His | -0.269 |
oscope | -0.269 |
x | -0.266 |
omm | -0.264 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Fre | +0.130 |
Kay | +0.126 |
bel | +0.126 |
Ag | +0.124 |
ora | +0.121 |
Neg logit contributions | |
oscope | -0.103 |
x | -0.099 |
apple | -0.098 |
His | -0.098 |
seventy | -0.096 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
x | +0.066 |
oscope | +0.065 |
His | +0.065 |
apple | +0.064 |
magnet | +0.064 |
Neg logit contributions | |
Fre | -0.070 |
Kay | -0.067 |
bel | -0.067 |
Ag | -0.065 |
ora | -0.065 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.147 |
Kay | +0.127 |
Jud | +0.126 |
Hel | +0.124 |
Ag | +0.124 |
Neg logit contributions | |
oscope | -0.261 |
DVD | -0.252 |
penter | -0.248 |
icle | -0.247 |
x | -0.246 |
Token | . |
Token ID | 13 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
Fre | +1.142 |
bel | +1.129 |
Kay | +1.105 |
Ag | +1.086 |
Hel | +1.085 |
Neg logit contributions | |
DVD | -0.901 |
oscope | -0.889 |
x | -0.863 |
magnet | -0.861 |
apple | -0.854 |
Token | They |
Token ID | 1119 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
bel | +0.042 |
Fre | +0.041 |
Kay | +0.039 |
Hel | +0.039 |
Ag | +0.039 |
Neg logit contributions | |
omm | -0.035 |
x | -0.034 |
His | -0.034 |
oscope | -0.034 |
DVD | -0.034 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Fre | +0.225 |
bel | +0.221 |
uttering | +0.219 |
Ag | +0.218 |
Kay | +0.213 |
Neg logit contributions | |
teaches | -0.175 |
oscope | -0.173 |
magnet | -0.172 |
penter | -0.171 |
His | -0.169 |
Token | and |
Token ID | 290 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
bel | +0.112 |
Fre | +0.110 |
Kay | +0.106 |
Hel | +0.105 |
Ag | +0.104 |
Neg logit contributions | |
His | -0.089 |
omm | -0.089 |
x | -0.088 |
DVD | -0.087 |
oscope | -0.087 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
His | +0.060 |
DVD | +0.058 |
teaches | +0.057 |
boo | +0.056 |
oscope | +0.055 |
Neg logit contributions | |
Fre | -0.077 |
bel | -0.074 |
Kay | -0.071 |
perspective | -0.071 |
Ag | -0.070 |
Token | animals |
Token ID | 4695 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
oscope | +0.072 |
apple | +0.071 |
x | +0.071 |
magnet | +0.070 |
boo | +0.069 |
Neg logit contributions | |
Fre | -0.065 |
Kay | -0.063 |
Ag | -0.062 |
bel | -0.062 |
uttering | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Fre | +0.410 |
bel | +0.409 |
Kay | +0.400 |
Ag | +0.394 |
Hel | +0.383 |
Neg logit contributions | |
DVD | -0.318 |
oscope | -0.316 |
magnet | -0.310 |
His | -0.309 |
x | -0.306 |
Token | stars |
Token ID | 5788 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
oscope | +0.071 |
x | +0.070 |
magnet | +0.070 |
apple | +0.070 |
His | +0.069 |
Neg logit contributions | |
Fre | -0.067 |
Kay | -0.065 |
Ag | -0.064 |
bel | -0.063 |
Jay | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Fre | +0.350 |
bel | +0.347 |
Kay | +0.341 |
Ag | +0.334 |
Hel | +0.329 |
Neg logit contributions | |
DVD | -0.283 |
oscope | -0.278 |
His | -0.274 |
magnet | -0.272 |
x | -0.271 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
oscope | +0.069 |
x | +0.068 |
apple | +0.068 |
magnet | +0.067 |
boo | +0.067 |
Neg logit contributions | |
Fre | -0.069 |
Kay | -0.067 |
Ag | -0.065 |
bel | -0.065 |
Jay | -0.064 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.140 |
Jay | +0.115 |
Jud | +0.115 |
Kay | +0.114 |
Ag | +0.112 |
Neg logit contributions | |
oscope | -0.270 |
DVD | -0.262 |
penter | -0.259 |
icle | -0.254 |
x | -0.252 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Fre | +1.189 |
bel | +1.158 |
Kay | +1.144 |
Ag | +1.128 |
Hel | +1.111 |
Neg logit contributions | |
DVD | -0.876 |
oscope | -0.846 |
magnet | -0.830 |
apple | -0.826 |
x | -0.816 |
Token | people |
Token ID | 661 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
oscope | +0.070 |
x | +0.069 |
apple | +0.069 |
boo | +0.069 |
magnet | +0.068 |
Neg logit contributions | |
Fre | -0.068 |
Kay | -0.066 |
bel | -0.065 |
uttering | -0.064 |
Jay | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Fre | +0.574 |
bel | +0.554 |
Kay | +0.546 |
Ag | +0.543 |
J | +0.527 |
Neg logit contributions | |
DVD | -0.460 |
oscope | -0.454 |
His | -0.439 |
magnet | -0.435 |
x | -0.433 |
Token | houses |
Token ID | 7777 |
Feature activation | -7.76e+00 |
Pos logit contributions | |
oscope | +0.070 |
boo | +0.069 |
magnet | +0.069 |
x | +0.069 |
apple | +0.068 |
Neg logit contributions | |
Fre | -0.070 |
Kay | -0.068 |
Ag | -0.066 |
bel | -0.065 |
Jay | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Fre | +0.652 |
Kay | +0.612 |
Ag | +0.611 |
bel | +0.599 |
Hel | +0.598 |
Neg logit contributions | |
oscope | -0.406 |
DVD | -0.405 |
His | -0.389 |
magnet | -0.388 |
x | -0.388 |
Token | colorful |
Token ID | 20239 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
His | +0.070 |
omm | +0.069 |
oll | +0.069 |
DVD | +0.067 |
boo | +0.066 |
Neg logit contributions | |
perspective | -0.139 |
Hel | -0.137 |
Fre | -0.133 |
Jay | -0.132 |
Jud | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
bel | +0.359 |
Fre | +0.357 |
Hel | +0.350 |
Kay | +0.347 |
Ag | +0.336 |
Neg logit contributions | |
DVD | -0.185 |
x | -0.180 |
apple | -0.180 |
omm | -0.180 |
magnet | -0.179 |
Token | like |
Token ID | 588 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
bel | +0.124 |
Fre | +0.123 |
Hel | +0.119 |
Kay | +0.118 |
Jay | +0.115 |
Neg logit contributions | |
apple | -0.102 |
His | -0.102 |
x | -0.102 |
DVD | -0.101 |
omm | -0.100 |
Token | bright |
Token ID | 6016 |
Feature activation | -6.37e+00 |
Pos logit contributions | |
bel | +0.248 |
Fre | +0.245 |
Hel | +0.236 |
ora | +0.234 |
Kay | +0.232 |
Neg logit contributions | |
His | -0.208 |
x | -0.207 |
DVD | -0.203 |
omm | -0.203 |
apple | -0.203 |
Token | rain |
Token ID | 6290 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
bel | +0.508 |
Fre | +0.500 |
Kay | +0.480 |
Hel | +0.472 |
Ag | +0.469 |
Neg logit contributions | |
DVD | -0.361 |
apple | -0.361 |
magnet | -0.357 |
His | -0.346 |
omm | -0.343 |
Token | bows |
Token ID | 25435 |
Feature activation | -1.51e+01 |
Pos logit contributions | |
Fre | +0.127 |
bel | +0.112 |
Hel | +0.111 |
Kay | +0.109 |
J | +0.107 |
Neg logit contributions | |
oscope | -0.266 |
penter | -0.263 |
DVD | -0.263 |
icle | -0.263 |
omm | -0.262 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Fre | +1.312 |
bel | +1.304 |
Kay | +1.267 |
Hel | +1.258 |
Ag | +1.244 |
Neg logit contributions | |
DVD | -0.735 |
apple | -0.726 |
magnet | -0.704 |
oscope | -0.692 |
penter | -0.687 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Fre | +0.038 |
bel | +0.038 |
Hel | +0.038 |
Kay | +0.037 |
Ag | +0.036 |
Neg logit contributions | |
x | -0.038 |
oscope | -0.037 |
omm | -0.036 |
magnet | -0.036 |
DVD | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
bel | +0.018 |
Fre | +0.018 |
Ag | +0.017 |
Kay | +0.017 |
Hel | +0.017 |
Neg logit contributions | |
His | -0.011 |
DVD | -0.010 |
x | -0.010 |
omm | -0.010 |
oscope | -0.010 |
Token | One |
Token ID | 3198 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
bel | +0.016 |
Fre | +0.014 |
ies | +0.014 |
Ag | +0.014 |
Kay | +0.013 |
Neg logit contributions | |
His | -0.013 |
x | -0.013 |
DVD | -0.013 |
omm | -0.013 |
oscope | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
bel | +0.047 |
Fre | +0.045 |
Kay | +0.043 |
Hel | +0.043 |
J | +0.042 |
Neg logit contributions | |
omm | -0.055 |
oscope | -0.054 |
His | -0.054 |
x | -0.054 |
DVD | -0.053 |
Token | Look |
Token ID | 6803 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Fre | +0.046 |
Hel | +0.044 |
Kay | +0.044 |
Ag | +0.043 |
ora | +0.042 |
Neg logit contributions | |
motorcycle | -0.030 |
trailer | -0.028 |
oscope | -0.027 |
microwave | -0.027 |
pistol | -0.027 |
Token | over |
Token ID | 625 |
Feature activation | +4.89e+00 |
Pos logit contributions | |
omm | +0.159 |
His | +0.158 |
oscope | +0.158 |
x | +0.157 |
DVD | +0.157 |
Neg logit contributions | |
bel | -0.162 |
Fre | -0.158 |
Kay | -0.152 |
Hel | -0.151 |
Ag | -0.148 |
Token | there |
Token ID | 612 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
x | +0.317 |
His | +0.316 |
omm | +0.314 |
DVD | +0.309 |
oscope | +0.308 |
Neg logit contributions | |
bel | -0.338 |
Fre | -0.314 |
Hel | -0.309 |
Kay | -0.308 |
Ag | -0.305 |
Token | . |
Token ID | 13 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
bel | +0.212 |
Fre | +0.207 |
Kay | +0.199 |
Hel | +0.198 |
Ag | +0.196 |
Neg logit contributions | |
omm | -0.172 |
His | -0.172 |
x | -0.171 |
oscope | -0.170 |
DVD | -0.169 |
Token | There |
Token ID | 1318 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Fre | +0.046 |
Hel | +0.044 |
Kay | +0.042 |
Ag | +0.042 |
Like | +0.040 |
Neg logit contributions | |
motorcycle | -0.033 |
oscope | -0.031 |
urger | -0.030 |
pistol | -0.030 |
x | -0.029 |
Token | 's |
Token ID | 338 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
His | +0.127 |
x | +0.126 |
omm | +0.126 |
oscope | +0.123 |
DVD | +0.122 |
Neg logit contributions | |
bel | -0.303 |
Fre | -0.296 |
Kay | -0.289 |
Hel | -0.287 |
Ag | -0.286 |
Token | a |
Token ID | 257 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
omm | +0.454 |
DVD | +0.433 |
His | +0.431 |
penter | +0.424 |
oscope | +0.418 |
Neg logit contributions | |
Fre | -0.537 |
bel | -0.524 |
Hel | -0.506 |
Kay | -0.500 |
common | -0.496 |
Token | huge |
Token ID | 3236 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
x | +0.058 |
omm | +0.057 |
DVD | +0.057 |
His | +0.057 |
oscope | +0.057 |
Neg logit contributions | |
bel | -0.058 |
Fre | -0.056 |
Kay | -0.055 |
Hel | -0.054 |
Ag | -0.053 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Fre | +0.028 |
bel | +0.028 |
Kay | +0.027 |
Hel | +0.027 |
Ag | +0.027 |
Neg logit contributions | |
omm | -0.029 |
His | -0.029 |
oscope | -0.027 |
DVD | -0.027 |
x | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
omm | +0.091 |
His | +0.090 |
x | +0.089 |
oscope | +0.088 |
DVD | +0.088 |
Neg logit contributions | |
bel | -0.094 |
Fre | -0.090 |
Kay | -0.086 |
Hel | -0.086 |
Ag | -0.085 |
Token | lots |
Token ID | 6041 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
bel | +0.099 |
Fre | +0.096 |
Kay | +0.093 |
Hel | +0.093 |
Ag | +0.092 |
Neg logit contributions | |
omm | -0.078 |
His | -0.078 |
x | -0.078 |
oscope | -0.077 |
DVD | -0.077 |
Token | 't |
Token ID | 470 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Kay | +0.127 |
Fre | +0.124 |
bel | +0.123 |
Ag | +0.122 |
Hel | +0.119 |
Neg logit contributions | |
DVD | -0.193 |
oscope | -0.190 |
boo | -0.188 |
microwave | -0.184 |
seventy | -0.179 |
Token | stir |
Token ID | 11240 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
omm | +0.033 |
His | +0.033 |
x | +0.033 |
oscope | +0.033 |
DVD | +0.033 |
Neg logit contributions | |
bel | -0.029 |
Fre | -0.028 |
Kay | -0.027 |
Hel | -0.026 |
Ag | -0.026 |
Token | up |
Token ID | 510 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
x | +0.208 |
omm | +0.208 |
His | +0.208 |
oscope | +0.206 |
DVD | +0.206 |
Neg logit contributions | |
bel | -0.243 |
Fre | -0.236 |
Kay | -0.229 |
Hel | -0.228 |
Ag | -0.226 |
Token | trouble |
Token ID | 5876 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
omm | +0.212 |
His | +0.209 |
oscope | +0.208 |
x | +0.207 |
DVD | +0.206 |
Neg logit contributions | |
bel | -0.256 |
Fre | -0.250 |
Kay | -0.239 |
Hel | -0.238 |
Ag | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
bel | +0.217 |
Fre | +0.211 |
Kay | +0.202 |
Hel | +0.202 |
Ag | +0.199 |
Neg logit contributions | |
omm | -0.209 |
His | -0.208 |
x | -0.206 |
oscope | -0.205 |
DVD | -0.204 |
Token | Your |
Token ID | 3406 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
Fre | +0.017 |
Hel | +0.017 |
bel | +0.016 |
Like | +0.016 |
Kay | +0.016 |
Neg logit contributions | |
motorcycle | -0.011 |
DVD | -0.010 |
apple | -0.010 |
pistol | -0.010 |
magnet | -0.010 |
Token | passport |
Token ID | 17981 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
x | +0.477 |
oscope | +0.473 |
omm | +0.468 |
DVD | +0.468 |
His | +0.465 |
Neg logit contributions | |
bel | -0.673 |
Fre | -0.670 |
Kay | -0.651 |
Hel | -0.649 |
Ag | -0.643 |
Token | is |
Token ID | 318 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
omm | +0.159 |
His | +0.159 |
DVD | +0.155 |
x | +0.152 |
seventy | +0.149 |
Neg logit contributions | |
bel | -0.199 |
Fre | -0.184 |
Hel | -0.179 |
Kay | -0.178 |
Ag | -0.175 |
Token | right |
Token ID | 826 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
omm | +0.120 |
His | +0.120 |
oscope | +0.115 |
DVD | +0.114 |
x | +0.111 |
Neg logit contributions | |
bel | -0.122 |
Fre | -0.113 |
common | -0.110 |
Hel | -0.108 |
Kay | -0.108 |
Token | here |
Token ID | 994 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
omm | +0.103 |
x | +0.102 |
His | +0.102 |
oscope | +0.101 |
DVD | +0.100 |
Neg logit contributions | |
bel | -0.145 |
Fre | -0.141 |
Kay | -0.137 |
Hel | -0.137 |
Ag | -0.136 |
Token | in |
Token ID | 287 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
omm | +0.207 |
His | +0.206 |
x | +0.205 |
oscope | +0.204 |
DVD | +0.203 |
Neg logit contributions | |
bel | -0.254 |
Fre | -0.247 |
Kay | -0.238 |
Hel | -0.237 |
Ag | -0.233 |
Token | . |
Token ID | 13 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
omm | +0.013 |
oscope | +0.013 |
DVD | +0.013 |
x | +0.013 |
penter | +0.013 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.010 |
Kay | -0.010 |
J | -0.010 |
Hel | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
bel | +0.037 |
J | +0.036 |
Fre | +0.034 |
Hel | +0.034 |
Kay | +0.034 |
Neg logit contributions | |
oscope | -0.042 |
x | -0.039 |
oll | -0.039 |
penter | -0.038 |
urger | -0.038 |
Token | held |
Token ID | 2714 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
omm | +0.188 |
DVD | +0.187 |
x | +0.186 |
oscope | +0.184 |
icle | +0.184 |
Neg logit contributions | |
bel | -0.135 |
Fre | -0.127 |
J | -0.123 |
Kay | -0.123 |
Hel | -0.122 |
Token | his |
Token ID | 465 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
oscope | +0.126 |
omm | +0.123 |
penter | +0.117 |
Promise | +0.115 |
boo | +0.111 |
Neg logit contributions | |
bel | -0.115 |
Jay | -0.112 |
common | -0.112 |
ora | -0.110 |
J | -0.109 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
omm | +0.196 |
Your | +0.189 |
penter | +0.185 |
Tomorrow | +0.182 |
oll | +0.179 |
Neg logit contributions | |
bel | -0.294 |
common | -0.273 |
ies | -0.264 |
Fre | -0.264 |
Jay | -0.248 |
Token | 's |
Token ID | 338 |
Feature activation | +7.52e+00 |
Pos logit contributions | |
omm | +0.122 |
icle | +0.107 |
Promise | +0.104 |
microwave | +0.097 |
teaches | +0.096 |
Neg logit contributions | |
bel | -0.181 |
ies | -0.172 |
J | -0.165 |
as | -0.162 |
Kay | -0.161 |
Token | hand |
Token ID | 1021 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
omm | +0.451 |
penter | +0.421 |
oll | +0.420 |
Your | +0.411 |
teaches | +0.406 |
Neg logit contributions | |
bel | -0.586 |
common | -0.502 |
Fre | -0.495 |
Kay | -0.491 |
Hel | -0.486 |
Token | tight |
Token ID | 5381 |
Feature activation | +5.44e+00 |
Pos logit contributions | |
omm | +0.383 |
Promise | +0.344 |
x | +0.342 |
teaches | +0.341 |
DVD | +0.340 |
Neg logit contributions | |
bel | -0.234 |
ies | -0.206 |
uttering | -0.201 |
Hel | -0.197 |
J | -0.196 |
Token | . |
Token ID | 13 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
omm | +0.410 |
x | +0.390 |
DVD | +0.387 |
His | +0.382 |
oscope | +0.379 |
Neg logit contributions | |
bel | -0.320 |
Fre | -0.289 |
Hel | -0.288 |
Kay | -0.278 |
J | -0.277 |
Token |
|
Token ID | 198 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
bel | +0.040 |
J | +0.038 |
Fre | +0.037 |
Hel | +0.037 |
Kay | +0.036 |
Neg logit contributions | |
oscope | -0.040 |
x | -0.036 |
penter | -0.035 |
seventy | -0.034 |
oll | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
bel | +0.013 |
Fre | +0.013 |
Kay | +0.013 |
J | +0.012 |
Hel | +0.012 |
Neg logit contributions | |
oscope | -0.014 |
x | -0.014 |
omm | -0.014 |
DVD | -0.014 |
magnet | -0.014 |
Token | balloon |
Token ID | 21190 |
Feature activation | +6.90e+00 |
Pos logit contributions | |
bel | +0.017 |
ora | +0.016 |
ies | +0.016 |
Fre | +0.016 |
Kay | +0.016 |
Neg logit contributions | |
teaches | -0.016 |
oscope | -0.016 |
penter | -0.015 |
omm | -0.015 |
Promise | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
omm | +0.603 |
Promise | +0.586 |
x | +0.575 |
oscope | +0.574 |
seventy | +0.572 |
Neg logit contributions | |
bel | -0.355 |
ies | -0.292 |
uttering | -0.282 |
ora | -0.275 |
J | -0.274 |
Token | She |
Token ID | 1375 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
bel | +0.025 |
J | +0.024 |
Kay | +0.024 |
Hel | +0.023 |
Fre | +0.023 |
Neg logit contributions | |
oscope | -0.032 |
x | -0.031 |
penter | -0.030 |
DVD | -0.030 |
motorcycle | -0.030 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
bel | +0.152 |
Fre | +0.147 |
Kay | +0.141 |
Hel | +0.140 |
Ag | +0.138 |
Neg logit contributions | |
omm | -0.182 |
x | -0.181 |
His | -0.180 |
oscope | -0.179 |
DVD | -0.179 |
Token | her |
Token ID | 607 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
bel | +0.068 |
Fre | +0.066 |
Kay | +0.063 |
Hel | +0.063 |
Ag | +0.062 |
Neg logit contributions | |
His | -0.083 |
x | -0.082 |
omm | -0.082 |
DVD | -0.081 |
oscope | -0.081 |
Token | balloon |
Token ID | 21190 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
bel | +0.102 |
common | +0.096 |
Fre | +0.095 |
Kay | +0.093 |
Hel | +0.093 |
Neg logit contributions | |
omm | -0.108 |
oscope | -0.107 |
x | -0.103 |
oll | -0.100 |
penter | -0.098 |
Token | so |
Token ID | 523 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
omm | +0.518 |
x | +0.510 |
oscope | +0.503 |
His | +0.500 |
DVD | +0.495 |
Neg logit contributions | |
bel | -0.407 |
Fre | -0.376 |
Kay | -0.362 |
ies | -0.358 |
Hel | -0.358 |
Token | much |
Token ID | 881 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
His | +0.108 |
omm | +0.102 |
DVD | +0.101 |
apple | +0.100 |
x | +0.100 |
Neg logit contributions | |
bel | -0.136 |
Fre | -0.135 |
Hel | -0.129 |
Ag | -0.128 |
Kay | -0.127 |
Token | that |
Token ID | 326 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
omm | +0.072 |
His | +0.072 |
x | +0.072 |
oscope | +0.071 |
DVD | +0.071 |
Neg logit contributions | |
bel | -0.086 |
Fre | -0.084 |
Kay | -0.082 |
Hel | -0.081 |
Ag | -0.080 |
Token | she |
Token ID | 673 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
x | +0.180 |
omm | +0.180 |
oscope | +0.179 |
DVD | +0.175 |
His | +0.175 |
Neg logit contributions | |
bel | -0.057 |
Fre | -0.052 |
Hel | -0.050 |
Kay | -0.050 |
J | -0.050 |
Token | held |
Token ID | 2714 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
bel | +0.208 |
Fre | +0.197 |
Hel | +0.191 |
Kay | +0.189 |
Ag | +0.188 |
Neg logit contributions | |
omm | -0.244 |
x | -0.240 |
His | -0.238 |
DVD | -0.236 |
oscope | -0.235 |
Token | of |
Token ID | 286 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
omm | +0.102 |
His | +0.101 |
x | +0.101 |
oscope | +0.101 |
DVD | +0.100 |
Neg logit contributions | |
bel | -0.095 |
Fre | -0.092 |
Kay | -0.088 |
Hel | -0.087 |
Ag | -0.086 |
Token | her |
Token ID | 607 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
omm | +0.209 |
oscope | +0.209 |
x | +0.203 |
DVD | +0.200 |
His | +0.200 |
Neg logit contributions | |
bel | -0.245 |
Fre | -0.240 |
Kay | -0.235 |
Hel | -0.233 |
Ag | -0.229 |
Token | flowers |
Token ID | 12734 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
bel | +0.100 |
Fre | +0.100 |
Hel | +0.095 |
Kay | +0.095 |
Ag | +0.093 |
Neg logit contributions | |
His | -0.086 |
x | -0.086 |
DVD | -0.085 |
omm | -0.084 |
oscope | -0.084 |
Token | for |
Token ID | 329 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
bel | +0.429 |
Fre | +0.419 |
Kay | +0.403 |
Hel | +0.401 |
Ag | +0.394 |
Neg logit contributions | |
His | -0.430 |
omm | -0.430 |
x | -0.428 |
oscope | -0.426 |
DVD | -0.425 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
x | +0.226 |
His | +0.225 |
omm | +0.222 |
DVD | +0.220 |
oscope | +0.219 |
Neg logit contributions | |
bel | -0.266 |
Fre | -0.258 |
Kay | -0.246 |
Hel | -0.246 |
Ag | -0.242 |
Token | 's |
Token ID | 338 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
omm | +0.314 |
x | +0.303 |
His | +0.300 |
DVD | +0.298 |
oscope | +0.296 |
Neg logit contributions | |
bel | -0.246 |
Fre | -0.233 |
Hel | -0.225 |
Kay | -0.224 |
Ag | -0.222 |
Token | toy |
Token ID | 13373 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
His | +0.446 |
x | +0.446 |
omm | +0.445 |
oscope | +0.442 |
DVD | +0.439 |
Neg logit contributions | |
bel | -0.594 |
Fre | -0.585 |
Kay | -0.563 |
Hel | -0.562 |
Ag | -0.553 |
Token | car |
Token ID | 1097 |
Feature activation | +5.62e+00 |
Pos logit contributions | |
His | +0.405 |
omm | +0.403 |
x | +0.403 |
oscope | +0.400 |
DVD | +0.399 |
Neg logit contributions | |
bel | -0.401 |
Fre | -0.392 |
Kay | -0.377 |
Hel | -0.374 |
Ag | -0.368 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
omm | +0.429 |
x | +0.418 |
His | +0.412 |
DVD | +0.412 |
oscope | +0.409 |
Neg logit contributions | |
bel | -0.334 |
Fre | -0.301 |
Kay | -0.294 |
Hel | -0.292 |
Ag | -0.291 |
Token | She |
Token ID | 1375 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
bel | +0.014 |
Hel | +0.013 |
Ag | +0.013 |
Kay | +0.013 |
ways | +0.013 |
Neg logit contributions | |
oscope | -0.019 |
x | -0.018 |
icle | -0.018 |
omm | -0.017 |
DVD | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
bel | +0.130 |
J | +0.122 |
Kay | +0.119 |
Fre | +0.118 |
Hel | +0.116 |
Neg logit contributions | |
DVD | -0.184 |
omm | -0.182 |
x | -0.181 |
oscope | -0.180 |
Promise | -0.176 |
Token | And |
Token ID | 843 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
Hel | +0.034 |
Ag | +0.033 |
Fre | +0.033 |
Like | +0.033 |
common | +0.033 |
Neg logit contributions | |
urger | -0.033 |
oscope | -0.033 |
apple | -0.032 |
motorcycle | -0.032 |
magnet | -0.032 |
Token | let |
Token ID | 1309 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
omm | +0.300 |
DVD | +0.288 |
oscope | +0.281 |
x | +0.275 |
icle | +0.273 |
Neg logit contributions | |
bel | -0.326 |
Fre | -0.305 |
Kay | -0.289 |
Ag | -0.289 |
Hel | -0.285 |
Token | me |
Token ID | 502 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
DVD | +0.262 |
oscope | +0.261 |
omm | +0.254 |
magnet | +0.253 |
penter | +0.252 |
Neg logit contributions | |
Fre | -0.416 |
ies | -0.414 |
Kay | -0.412 |
J | -0.407 |
ora | -0.407 |
Token | fix |
Token ID | 4259 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
omm | +0.017 |
DVD | +0.016 |
His | +0.016 |
seventy | +0.015 |
oscope | +0.015 |
Neg logit contributions | |
bel | -0.017 |
ies | -0.015 |
Fre | -0.015 |
ora | -0.014 |
Kay | -0.014 |
Token | your |
Token ID | 534 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
omm | +0.322 |
oscope | +0.318 |
His | +0.312 |
x | +0.304 |
DVD | +0.303 |
Neg logit contributions | |
bel | -0.306 |
Fre | -0.304 |
Kay | -0.294 |
Jay | -0.288 |
J | -0.288 |
Token | bike |
Token ID | 7161 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
omm | +0.024 |
His | +0.024 |
penter | +0.024 |
icle | +0.022 |
DVD | +0.021 |
Neg logit contributions | |
bel | -0.087 |
ies | -0.081 |
common | -0.076 |
Fre | -0.075 |
ymes | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
omm | +0.175 |
His | +0.169 |
DVD | +0.165 |
x | +0.163 |
Promise | +0.162 |
Neg logit contributions | |
bel | -0.134 |
ies | -0.113 |
Fre | -0.112 |
Kay | -0.112 |
J | -0.110 |
Token | It |
Token ID | 632 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Hel | +0.035 |
Like | +0.034 |
Ag | +0.034 |
Fre | +0.034 |
common | +0.033 |
Neg logit contributions | |
urger | -0.032 |
oscope | -0.032 |
motorcycle | -0.032 |
apple | -0.032 |
forehead | -0.031 |
Token | is |
Token ID | 318 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
omm | +0.249 |
His | +0.244 |
icle | +0.240 |
DVD | +0.240 |
x | +0.235 |
Neg logit contributions | |
bel | -0.165 |
ies | -0.148 |
Fre | -0.138 |
Hel | -0.135 |
Ag | -0.134 |
Token | not |
Token ID | 407 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
omm | +0.113 |
oscope | +0.113 |
His | +0.111 |
ishly | +0.108 |
affe | +0.107 |
Neg logit contributions | |
common | -0.076 |
bel | -0.069 |
fun | -0.065 |
ies | -0.064 |
Ag | -0.061 |
Token | broken |
Token ID | 5445 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
bel | +0.069 |
Fre | +0.063 |
Hel | +0.063 |
ies | +0.063 |
Kay | +0.062 |
Neg logit contributions | |
omm | -0.079 |
His | -0.075 |
DVD | -0.075 |
oscope | -0.074 |
x | -0.073 |
Token | He |
Token ID | 679 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
Fre | +0.039 |
Ag | +0.038 |
Kay | +0.038 |
Hel | +0.037 |
bel | +0.037 |
Neg logit contributions | |
x | -0.033 |
oscope | -0.033 |
DVD | -0.030 |
seventy | -0.029 |
boo | -0.029 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
omm | +0.184 |
x | +0.183 |
DVD | +0.180 |
icle | +0.178 |
oscope | +0.176 |
Neg logit contributions | |
bel | -0.147 |
Fre | -0.144 |
Kay | -0.138 |
Hel | -0.138 |
Ag | -0.135 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
oscope | +0.094 |
omm | +0.092 |
penter | +0.089 |
DVD | +0.088 |
Promise | +0.086 |
Neg logit contributions | |
J | -0.077 |
Fre | -0.076 |
bel | -0.076 |
Kay | -0.074 |
Ag | -0.073 |
Token | shield |
Token ID | 7614 |
Feature activation | +6.53e+00 |
Pos logit contributions | |
bel | +0.057 |
Hel | +0.054 |
Fre | +0.053 |
ies | +0.053 |
perspective | +0.052 |
Neg logit contributions | |
omm | -0.028 |
His | -0.025 |
icle | -0.023 |
DVD | -0.023 |
oscope | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
omm | +0.476 |
x | +0.452 |
DVD | +0.443 |
His | +0.438 |
oscope | +0.428 |
Neg logit contributions | |
bel | -0.433 |
Fre | -0.375 |
Hel | -0.368 |
ies | -0.367 |
Kay | -0.365 |
Token | held |
Token ID | 2714 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
omm | +0.072 |
x | +0.071 |
oscope | +0.070 |
DVD | +0.070 |
His | +0.070 |
Neg logit contributions | |
bel | -0.070 |
Fre | -0.066 |
Kay | -0.065 |
Hel | -0.064 |
Ag | -0.063 |
Token | it |
Token ID | 340 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
omm | +0.158 |
oscope | +0.157 |
penter | +0.151 |
x | +0.150 |
DVD | +0.148 |
Neg logit contributions | |
J | -0.089 |
bel | -0.086 |
Jay | -0.086 |
Kay | -0.084 |
Fre | -0.084 |
Token | in |
Token ID | 287 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
bel | +0.015 |
Fre | +0.014 |
Hel | +0.014 |
Kay | +0.014 |
Ag | +0.014 |
Neg logit contributions | |
omm | -0.013 |
x | -0.013 |
DVD | -0.013 |
oscope | -0.013 |
His | -0.013 |
Token | front |
Token ID | 2166 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
bel | +0.079 |
Fre | +0.078 |
Kay | +0.077 |
J | +0.077 |
Hel | +0.076 |
Neg logit contributions | |
oscope | -0.042 |
omm | -0.042 |
x | -0.041 |
DVD | -0.040 |
penter | -0.039 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
omm | +0.127 |
x | +0.123 |
oscope | +0.123 |
DVD | +0.123 |
His | +0.122 |
Neg logit contributions | |
bel | -0.176 |
Fre | -0.168 |
Kay | -0.165 |
Hel | -0.163 |
Ag | -0.161 |
Token | him |
Token ID | 683 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
omm | +0.164 |
oscope | +0.164 |
x | +0.161 |
DVD | +0.159 |
penter | +0.155 |
Neg logit contributions | |
bel | -0.251 |
Fre | -0.249 |
Kay | -0.245 |
J | -0.242 |
Hel | -0.242 |
Token | the |
Token ID | 262 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
bel | +0.104 |
Fre | +0.101 |
Kay | +0.098 |
Hel | +0.097 |
Ag | +0.096 |
Neg logit contributions | |
omm | -0.082 |
oscope | -0.081 |
His | -0.081 |
x | -0.081 |
DVD | -0.080 |
Token | same |
Token ID | 976 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
bel | +0.045 |
Fre | +0.043 |
Hel | +0.042 |
Kay | +0.041 |
Ag | +0.041 |
Neg logit contributions | |
omm | -0.043 |
His | -0.042 |
DVD | -0.040 |
oscope | -0.040 |
x | -0.039 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
bel | +0.185 |
Fre | +0.170 |
J | +0.167 |
ies | +0.167 |
Kay | +0.165 |
Neg logit contributions | |
omm | -0.202 |
His | -0.194 |
DVD | -0.185 |
oscope | -0.185 |
seventy | -0.183 |
Token | again |
Token ID | 757 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
bel | +0.064 |
Fre | +0.057 |
Kay | +0.056 |
Hel | +0.055 |
J | +0.055 |
Neg logit contributions | |
omm | -0.081 |
His | -0.076 |
x | -0.076 |
oscope | -0.075 |
DVD | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
His | +0.165 |
x | +0.160 |
oscope | +0.160 |
magnet | +0.155 |
DVD | +0.154 |
Neg logit contributions | |
bel | -0.202 |
Fre | -0.200 |
Kay | -0.192 |
Ag | -0.192 |
Hel | -0.192 |
Token | again |
Token ID | 757 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
omm | +0.066 |
His | +0.062 |
oscope | +0.062 |
DVD | +0.061 |
x | +0.061 |
Neg logit contributions | |
bel | -0.076 |
Fre | -0.070 |
Hel | -0.068 |
Kay | -0.068 |
Ag | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
His | +0.156 |
magnet | +0.147 |
x | +0.144 |
DVD | +0.143 |
boo | +0.141 |
Neg logit contributions | |
Fre | -0.214 |
bel | -0.210 |
Kay | -0.206 |
Hel | -0.202 |
Ag | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
bel | +0.047 |
Fre | +0.046 |
J | +0.046 |
Hel | +0.046 |
Kay | +0.045 |
Neg logit contributions | |
oscope | -0.030 |
x | -0.028 |
omm | -0.027 |
DVD | -0.027 |
boo | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
bel | +0.014 |
Fre | +0.014 |
Kay | +0.013 |
Hel | +0.013 |
J | +0.013 |
Neg logit contributions | |
omm | -0.013 |
oscope | -0.013 |
x | -0.013 |
DVD | -0.013 |
His | -0.012 |
Token | Ben |
Token ID | 11696 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
bel | +0.013 |
Fre | +0.013 |
Kay | +0.012 |
Hel | +0.012 |
Ag | +0.012 |
Neg logit contributions | |
His | -0.015 |
x | -0.014 |
omm | -0.014 |
DVD | -0.014 |
oscope | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
bel | +0.445 |
Fre | +0.440 |
Hel | +0.423 |
Kay | +0.419 |
Ag | +0.411 |
Neg logit contributions | |
omm | -0.372 |
His | -0.364 |
x | -0.362 |
DVD | -0.358 |
oscope | -0.358 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
His | +0.078 |
oscope | +0.077 |
x | +0.077 |
magnet | +0.077 |
apple | +0.076 |
Neg logit contributions | |
Fre | -0.075 |
bel | -0.075 |
Kay | -0.074 |
Ag | -0.071 |
Hel | -0.071 |
Token | very |
Token ID | 845 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
Fre | +0.229 |
bel | +0.225 |
Kay | +0.219 |
Hel | +0.217 |
J | +0.213 |
Neg logit contributions | |
His | -0.170 |
magnet | -0.167 |
DVD | -0.167 |
apple | -0.165 |
x | -0.164 |
Token | complicated |
Token ID | 8253 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
magnet | +0.023 |
His | +0.022 |
tank | +0.022 |
boo | +0.021 |
apple | +0.021 |
Neg logit contributions | |
Fre | -0.028 |
Hel | -0.027 |
Kay | -0.027 |
bel | -0.026 |
Jud | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
bel | +0.307 |
Fre | +0.301 |
Kay | +0.289 |
Hel | +0.288 |
Ag | +0.283 |
Neg logit contributions | |
x | -0.313 |
His | -0.313 |
omm | -0.312 |
oscope | -0.310 |
DVD | -0.309 |
Token |
|
Token ID | 198 |
Feature activation | -6.75e-02 |
Pos logit contributions | |
bel | +0.035 |
Fre | +0.034 |
Kay | +0.033 |
Hel | +0.033 |
Ag | +0.033 |
Neg logit contributions | |
His | -0.023 |
omm | -0.023 |
x | -0.022 |
oscope | -0.022 |
DVD | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
bel | +0.006 |
Fre | +0.006 |
Ag | +0.006 |
Hel | +0.005 |
ies | +0.005 |
Neg logit contributions | |
His | -0.003 |
x | -0.003 |
omm | -0.003 |
DVD | -0.003 |
oscope | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
bel | +0.005 |
ies | +0.005 |
common | +0.005 |
Fre | +0.005 |
Ag | +0.005 |
Neg logit contributions | |
His | -0.005 |
x | -0.004 |
oscope | -0.004 |
apple | -0.004 |
penter | -0.004 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
bel | +0.142 |
Fre | +0.141 |
Hel | +0.139 |
Ag | +0.135 |
J | +0.134 |
Neg logit contributions | |
omm | -0.114 |
DVD | -0.113 |
His | -0.112 |
icle | -0.108 |
oscope | -0.107 |
Token | was |
Token ID | 373 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
His | +0.113 |
oscope | +0.110 |
x | +0.110 |
omm | +0.109 |
magnet | +0.108 |
Neg logit contributions | |
bel | -0.098 |
Fre | -0.095 |
Kay | -0.091 |
Hel | -0.089 |
Ag | -0.089 |
Token | curious |
Token ID | 11040 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
omm | +0.025 |
His | +0.024 |
DVD | +0.024 |
oscope | +0.024 |
x | +0.024 |
Neg logit contributions | |
bel | -0.023 |
Fre | -0.023 |
Kay | -0.022 |
Hel | -0.022 |
Ag | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
bel | +0.213 |
Fre | +0.205 |
Hel | +0.200 |
Kay | +0.199 |
Ag | +0.195 |
Neg logit contributions | |
omm | -0.159 |
DVD | -0.155 |
x | -0.154 |
oscope | -0.154 |
His | -0.151 |
Token | he |
Token ID | 339 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
bel | +0.224 |
Fre | +0.215 |
J | +0.215 |
Hel | +0.210 |
Ag | +0.210 |
Neg logit contributions | |
omm | -0.205 |
DVD | -0.201 |
oscope | -0.201 |
x | -0.193 |
microwave | -0.189 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
omm | +0.114 |
His | +0.114 |
x | +0.114 |
oscope | +0.113 |
DVD | +0.113 |
Neg logit contributions | |
bel | -0.125 |
Fre | -0.122 |
Kay | -0.117 |
Hel | -0.117 |
Ag | -0.115 |
Token | 't |
Token ID | 470 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Fre | +0.000 |
Kay | +0.000 |
Ag | +0.000 |
Hel | +0.000 |
Jay | +0.000 |
Neg logit contributions | |
urger | -0.001 |
oscope | -0.001 |
forehead | -0.001 |
DVD | -0.001 |
motorcycle | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
x | +0.009 |
His | +0.009 |
oscope | +0.009 |
omm | +0.008 |
DVD | +0.008 |
Neg logit contributions | |
bel | -0.010 |
Fre | -0.009 |
Kay | -0.009 |
Hel | -0.009 |
Ag | -0.009 |
Token | if |
Token ID | 611 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
bel | +0.195 |
Fre | +0.193 |
Kay | +0.183 |
Hel | +0.182 |
J | +0.181 |
Neg logit contributions | |
omm | -0.154 |
DVD | -0.148 |
oscope | -0.143 |
penter | -0.143 |
His | -0.141 |
Token | he |
Token ID | 339 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
His | +0.121 |
x | +0.118 |
omm | +0.114 |
magnet | +0.112 |
oscope | +0.112 |
Neg logit contributions | |
bel | -0.221 |
Fre | -0.215 |
Kay | -0.210 |
Hel | -0.207 |
Ag | -0.205 |
Token | could |
Token ID | 714 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
His | +0.112 |
oscope | +0.111 |
x | +0.111 |
omm | +0.109 |
magnet | +0.105 |
Neg logit contributions | |
bel | -0.129 |
Fre | -0.124 |
Kay | -0.120 |
Hel | -0.119 |
Ag | -0.119 |
Token | do |
Token ID | 466 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
x | +0.053 |
His | +0.052 |
oscope | +0.052 |
omm | +0.051 |
boo | +0.050 |
Neg logit contributions | |
bel | -0.074 |
Fre | -0.071 |
Kay | -0.069 |
Hel | -0.069 |
Ag | -0.069 |
Token | it |
Token ID | 340 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
bel | +0.103 |
Fre | +0.100 |
Kay | +0.096 |
Hel | +0.096 |
Ag | +0.094 |
Neg logit contributions | |
His | -0.102 |
x | -0.101 |
omm | -0.100 |
oscope | -0.100 |
DVD | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
bel | +0.013 |
Fre | +0.012 |
Kay | +0.012 |
Hel | +0.012 |
Ag | +0.012 |
Neg logit contributions | |
omm | -0.013 |
His | -0.013 |
x | -0.013 |
oscope | -0.013 |
DVD | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
bel | +0.040 |
Fre | +0.040 |
Hel | +0.039 |
Kay | +0.038 |
J | +0.038 |
Neg logit contributions | |
oscope | -0.032 |
x | -0.032 |
DVD | -0.032 |
omm | -0.031 |
boo | -0.030 |
Token | Bob |
Token ID | 5811 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
bel | +0.031 |
Fre | +0.030 |
Kay | +0.029 |
Hel | +0.029 |
Ag | +0.029 |
Neg logit contributions | |
His | -0.022 |
omm | -0.022 |
x | -0.021 |
DVD | -0.021 |
oscope | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
His | +0.031 |
omm | +0.030 |
oscope | +0.030 |
x | +0.030 |
DVD | +0.030 |
Neg logit contributions | |
bel | -0.042 |
Fre | -0.040 |
Kay | -0.039 |
Hel | -0.039 |
Ag | -0.039 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
omm | +0.060 |
DVD | +0.060 |
x | +0.059 |
oscope | +0.059 |
magnet | +0.055 |
Neg logit contributions | |
bel | -0.102 |
Fre | -0.101 |
Kay | -0.100 |
Hel | -0.097 |
J | -0.097 |
Token | still |
Token ID | 991 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
His | +0.189 |
oscope | +0.180 |
boo | +0.178 |
apple | +0.176 |
magnet | +0.176 |
Neg logit contributions | |
bel | -0.193 |
Fre | -0.184 |
Kay | -0.173 |
Ag | -0.173 |
common | -0.169 |
Token | decided |
Token ID | 3066 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
His | +0.066 |
boo | +0.062 |
oscope | +0.062 |
DVD | +0.058 |
magnet | +0.058 |
Neg logit contributions | |
Fre | -0.068 |
bel | -0.067 |
Kay | -0.064 |
Ag | -0.063 |
Hel | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
His | +0.061 |
motorcycle | +0.057 |
apple | +0.055 |
boo | +0.055 |
Your | +0.054 |
Neg logit contributions | |
Fre | -0.071 |
bel | -0.070 |
ora | -0.066 |
Hel | -0.066 |
Jay | -0.065 |
Token | play |
Token ID | 711 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
bel | +0.172 |
Fre | +0.169 |
Kay | +0.165 |
Hel | +0.162 |
Ag | +0.160 |
Neg logit contributions | |
omm | -0.136 |
DVD | -0.135 |
oscope | -0.131 |
His | -0.130 |
x | -0.130 |
Token | with |
Token ID | 351 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
x | +0.044 |
His | +0.043 |
DVD | +0.043 |
oscope | +0.042 |
magnet | +0.042 |
Neg logit contributions | |
Fre | -0.051 |
bel | -0.051 |
Kay | -0.049 |
Hel | -0.048 |
Ag | -0.047 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
bel | +0.087 |
Fre | +0.084 |
Hel | +0.082 |
Ag | +0.081 |
Kay | +0.081 |
Neg logit contributions | |
His | -0.066 |
x | -0.065 |
DVD | -0.063 |
magnet | -0.063 |
apple | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
bel | +0.000 |
Fre | +0.000 |
Kay | +0.000 |
Hel | +0.000 |
Ag | +0.000 |
Neg logit contributions | |
omm | -0.000 |
His | -0.000 |
x | -0.000 |
oscope | -0.000 |
DVD | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -9.09e-03 |
Pos logit contributions | |
bel | +0.027 |
Fre | +0.027 |
Kay | +0.026 |
Hel | +0.026 |
Ag | +0.025 |
Neg logit contributions | |
x | -0.023 |
omm | -0.023 |
oscope | -0.023 |
DVD | -0.023 |
His | -0.022 |
Token | Da |
Token ID | 26531 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
His | +0.003 |
apple | +0.003 |
omm | +0.002 |
magnet | +0.002 |
penter | +0.002 |
Neg logit contributions | |
bel | -0.002 |
Fre | -0.001 |
ies | -0.001 |
Ag | -0.001 |
Kay | -0.001 |
Token | isy |
Token ID | 13560 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
bel | +0.477 |
Fre | +0.467 |
Kay | +0.456 |
Hel | +0.456 |
Ag | +0.445 |
Neg logit contributions | |
x | -0.287 |
DVD | -0.286 |
omm | -0.283 |
His | -0.281 |
magnet | -0.274 |
Token | watched |
Token ID | 7342 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
x | +0.219 |
omm | +0.217 |
DVD | +0.216 |
oscope | +0.210 |
His | +0.209 |
Neg logit contributions | |
bel | -0.199 |
Fre | -0.190 |
Hel | -0.185 |
Kay | -0.184 |
J | -0.179 |
Token | as |
Token ID | 355 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
bel | +0.160 |
ies | +0.142 |
Fre | +0.141 |
Kay | +0.141 |
Hel | +0.139 |
Neg logit contributions | |
oscope | -0.273 |
omm | -0.272 |
DVD | -0.268 |
penter | -0.263 |
microwave | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
His | +0.255 |
omm | +0.250 |
x | +0.249 |
magnet | +0.246 |
apple | +0.245 |
Neg logit contributions | |
bel | -0.267 |
Fre | -0.249 |
Ag | -0.242 |
Kay | -0.241 |
Hel | -0.240 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
bel | +0.033 |
Fre | +0.031 |
Hel | +0.030 |
Kay | +0.030 |
Ag | +0.030 |
Neg logit contributions | |
omm | -0.020 |
x | -0.020 |
oscope | -0.020 |
His | -0.020 |
penter | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Fre | +0.131 |
bel | +0.129 |
Kay | +0.125 |
Hel | +0.124 |
Ag | +0.122 |
Neg logit contributions | |
His | -0.116 |
oscope | -0.116 |
DVD | -0.115 |
omm | -0.115 |
x | -0.113 |
Token | warm |
Token ID | 5814 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
His | +0.077 |
apple | +0.076 |
boo | +0.074 |
magnet | +0.073 |
oscope | +0.073 |
Neg logit contributions | |
Fre | -0.097 |
bel | -0.095 |
Ag | -0.093 |
Kay | -0.092 |
Hel | -0.092 |
Token | water |
Token ID | 1660 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
apple | +0.042 |
His | +0.041 |
icle | +0.041 |
oscope | +0.040 |
DVD | +0.040 |
Neg logit contributions | |
Fre | -0.063 |
bel | -0.061 |
Hel | -0.059 |
Kay | -0.059 |
J | -0.059 |
Token | melted |
Token ID | 24178 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
Fre | +0.083 |
Kay | +0.078 |
Hel | +0.078 |
bel | +0.077 |
J | +0.076 |
Neg logit contributions | |
His | -0.064 |
DVD | -0.063 |
oscope | -0.062 |
icle | -0.062 |
apple | -0.062 |
Token | away |
Token ID | 1497 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
apple | +0.179 |
magnet | +0.170 |
icle | +0.166 |
x | +0.166 |
DVD | +0.165 |
Neg logit contributions | |
Fre | -0.297 |
bel | -0.292 |
Kay | -0.283 |
Hel | -0.279 |
Ag | -0.278 |
Token | it |
Token ID | 340 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
bel | +0.439 |
Fre | +0.429 |
Kay | +0.414 |
Hel | +0.411 |
Ag | +0.403 |
Neg logit contributions | |
omm | -0.373 |
His | -0.364 |
oscope | -0.364 |
DVD | -0.361 |
x | -0.359 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
bel | +0.006 |
Fre | +0.006 |
Kay | +0.006 |
Hel | +0.006 |
Ag | +0.006 |
Neg logit contributions | |
omm | -0.008 |
oscope | -0.008 |
DVD | -0.007 |
His | -0.007 |
x | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
His | +0.078 |
apple | +0.068 |
x | +0.066 |
oscope | +0.066 |
motorcycle | +0.065 |
Neg logit contributions | |
bel | -0.115 |
Fre | -0.115 |
Ag | -0.113 |
Hel | -0.111 |
Kay | -0.109 |
Token | " |
Token ID | 366 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
bel | +0.038 |
Fre | +0.037 |
Hel | +0.036 |
Kay | +0.036 |
Ag | +0.035 |
Neg logit contributions | |
His | -0.025 |
omm | -0.025 |
x | -0.023 |
DVD | -0.023 |
oscope | -0.023 |
Token | No |
Token ID | 2949 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
oscope | +0.220 |
His | +0.219 |
x | +0.213 |
DVD | +0.207 |
apple | +0.207 |
Neg logit contributions | |
bel | -0.237 |
ies | -0.232 |
Fre | -0.222 |
Ag | -0.209 |
uttering | -0.206 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Fre | +0.245 |
Kay | +0.233 |
ies | +0.232 |
bel | +0.228 |
common | +0.225 |
Neg logit contributions | |
DVD | -0.356 |
oscope | -0.351 |
omm | -0.350 |
penter | -0.343 |
His | -0.343 |
Token | it |
Token ID | 340 |
Feature activation | -9.03e-02 |
Pos logit contributions | |
Fre | +0.095 |
Jay | +0.085 |
insects | +0.084 |
J | +0.083 |
Kay | +0.083 |
Neg logit contributions | |
oscope | -0.117 |
penter | -0.116 |
DVD | -0.113 |
omm | -0.108 |
His | -0.108 |
Token | is |
Token ID | 318 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
bel | +0.008 |
Fre | +0.007 |
ies | +0.007 |
Hel | +0.007 |
ora | +0.007 |
Neg logit contributions | |
omm | -0.004 |
DVD | -0.004 |
His | -0.004 |
icle | -0.004 |
oscope | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
omm | +0.101 |
DVD | +0.097 |
His | +0.097 |
oscope | +0.096 |
oll | +0.092 |
Neg logit contributions | |
common | -0.107 |
bel | -0.105 |
Fre | -0.105 |
Kay | -0.100 |
Hel | -0.100 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
bel | +0.066 |
Fre | +0.065 |
Hel | +0.062 |
Kay | +0.062 |
Ag | +0.061 |
Neg logit contributions | |
omm | -0.065 |
DVD | -0.062 |
His | -0.062 |
oscope | -0.061 |
x | -0.060 |
Token | pile |
Token ID | 14540 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
omm | +0.055 |
x | +0.055 |
His | +0.055 |
oscope | +0.054 |
DVD | +0.054 |
Neg logit contributions | |
bel | -0.079 |
Fre | -0.077 |
Kay | -0.075 |
Hel | -0.075 |
Ag | -0.074 |
Token | a |
Token ID | 64 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
bel | +0.071 |
Fre | +0.069 |
Hel | +0.065 |
Ag | +0.065 |
Kay | +0.064 |
Neg logit contributions | |
His | -0.168 |
omm | -0.168 |
oscope | -0.167 |
x | -0.167 |
DVD | -0.165 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
bel | +0.325 |
Fre | +0.307 |
Hel | +0.297 |
Kay | +0.296 |
J | +0.293 |
Neg logit contributions | |
omm | -0.386 |
x | -0.384 |
DVD | -0.384 |
oscope | -0.377 |
magnet | -0.375 |
Token | feeling |
Token ID | 4203 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
bel | +0.112 |
Fre | +0.107 |
Hel | +0.106 |
Kay | +0.106 |
J | +0.104 |
Neg logit contributions | |
omm | -0.095 |
x | -0.093 |
DVD | -0.092 |
oscope | -0.091 |
oll | -0.089 |
Token | sorry |
Token ID | 7926 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
bel | +0.172 |
Fre | +0.169 |
Hel | +0.164 |
Ag | +0.162 |
Kay | +0.161 |
Neg logit contributions | |
omm | -0.154 |
oscope | -0.148 |
icle | -0.146 |
x | -0.146 |
DVD | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
omm | +0.290 |
oscope | +0.287 |
x | +0.286 |
DVD | +0.286 |
His | +0.279 |
Neg logit contributions | |
bel | -0.353 |
Fre | -0.334 |
Hel | -0.329 |
Kay | -0.324 |
ies | -0.324 |
Token | She |
Token ID | 1375 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
bel | +0.037 |
Fre | +0.036 |
Kay | +0.036 |
Hel | +0.036 |
Ag | +0.035 |
Neg logit contributions | |
x | -0.021 |
DVD | -0.021 |
oscope | -0.021 |
omm | -0.020 |
magnet | -0.020 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
Hel | +0.113 |
bel | +0.112 |
Kay | +0.112 |
J | +0.111 |
Fre | +0.110 |
Neg logit contributions | |
DVD | -0.218 |
omm | -0.209 |
icle | -0.208 |
x | -0.206 |
oscope | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
bel | +0.009 |
Fre | +0.009 |
Kay | +0.008 |
Hel | +0.008 |
Ag | +0.008 |
Neg logit contributions | |
His | -0.012 |
x | -0.012 |
omm | -0.012 |
oscope | -0.012 |
DVD | -0.012 |
Token | make |
Token ID | 787 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
bel | +0.159 |
Kay | +0.155 |
Fre | +0.153 |
common | +0.149 |
Ag | +0.148 |
Neg logit contributions | |
omm | -0.162 |
DVD | -0.158 |
microwave | -0.153 |
oscope | -0.153 |
oll | -0.150 |
Token | the |
Token ID | 262 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Fre | +0.064 |
Kay | +0.063 |
bel | +0.062 |
Ag | +0.061 |
Hel | +0.061 |
Neg logit contributions | |
oscope | -0.082 |
omm | -0.081 |
seventy | -0.078 |
penter | -0.078 |
His | -0.078 |
Token | dog |
Token ID | 3290 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
bel | +0.033 |
Fre | +0.031 |
Kay | +0.031 |
Hel | +0.030 |
Ag | +0.030 |
Neg logit contributions | |
omm | -0.034 |
oscope | -0.032 |
seventy | -0.032 |
His | -0.032 |
icle | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
His | +0.007 |
omm | +0.007 |
x | +0.007 |
oscope | +0.007 |
DVD | +0.007 |
Neg logit contributions | |
bel | -0.007 |
Fre | -0.007 |
Kay | -0.006 |
Hel | -0.006 |
Ag | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
Kay | +0.016 |
Fre | +0.016 |
Ag | +0.015 |
Hel | +0.015 |
J | +0.015 |
Neg logit contributions | |
x | -0.014 |
oscope | -0.014 |
boo | -0.013 |
magnet | -0.013 |
omm | -0.013 |
Token | ate |
Token ID | 15063 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
bel | +0.177 |
Fre | +0.173 |
Kay | +0.167 |
Ag | +0.165 |
Hel | +0.165 |
Neg logit contributions | |
His | -0.178 |
oscope | -0.177 |
DVD | -0.175 |
magnet | -0.174 |
x | -0.174 |
Token | and |
Token ID | 290 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
His | +0.321 |
x | +0.318 |
omm | +0.317 |
DVD | +0.317 |
oscope | +0.313 |
Neg logit contributions | |
bel | -0.369 |
Fre | -0.362 |
Hel | -0.349 |
Kay | -0.349 |
Ag | -0.343 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
His | +0.076 |
DVD | +0.076 |
oscope | +0.076 |
magnet | +0.074 |
apple | +0.074 |
Neg logit contributions | |
Fre | -0.099 |
bel | -0.098 |
Kay | -0.094 |
Hel | -0.093 |
Ag | -0.092 |
Token | together |
Token ID | 1978 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
bel | +0.097 |
Fre | +0.092 |
Hel | +0.090 |
Kay | +0.090 |
Ag | +0.089 |
Neg logit contributions | |
omm | -0.093 |
x | -0.093 |
oscope | -0.091 |
His | -0.089 |
DVD | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
bel | +0.277 |
Fre | +0.270 |
Kay | +0.260 |
Hel | +0.258 |
Ag | +0.255 |
Neg logit contributions | |
His | -0.273 |
omm | -0.272 |
x | -0.271 |
oscope | -0.269 |
DVD | -0.269 |
Token | and |
Token ID | 290 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
bel | +0.107 |
Fre | +0.103 |
Kay | +0.100 |
Hel | +0.099 |
Ag | +0.098 |
Neg logit contributions | |
omm | -0.093 |
x | -0.092 |
His | -0.091 |
oscope | -0.091 |
DVD | -0.090 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
His | +0.077 |
DVD | +0.076 |
oscope | +0.075 |
x | +0.075 |
omm | +0.075 |
Neg logit contributions | |
bel | -0.083 |
Fre | -0.083 |
Kay | -0.079 |
Hel | -0.078 |
Ag | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
bel | +0.113 |
Fre | +0.108 |
uttering | +0.103 |
Hel | +0.102 |
Kay | +0.100 |
Neg logit contributions | |
His | -0.087 |
apple | -0.083 |
DVD | -0.080 |
omm | -0.079 |
magnet | -0.078 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
bel | +0.037 |
Fre | +0.036 |
Kay | +0.035 |
Hel | +0.034 |
Ag | +0.034 |
Neg logit contributions | |
x | -0.031 |
DVD | -0.030 |
oscope | -0.030 |
magnet | -0.030 |
omm | -0.030 |
Token | very |
Token ID | 845 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
omm | +0.013 |
His | +0.013 |
oscope | +0.012 |
DVD | +0.012 |
x | +0.012 |
Neg logit contributions | |
bel | -0.014 |
Fre | -0.014 |
Kay | -0.013 |
Hel | -0.013 |
Ag | -0.013 |
Token | kind |
Token ID | 1611 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
His | +0.014 |
x | +0.014 |
magnet | +0.013 |
boo | +0.013 |
omm | +0.013 |
Neg logit contributions | |
bel | -0.018 |
Fre | -0.018 |
Hel | -0.018 |
Kay | -0.017 |
Ag | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
bel | +0.085 |
Fre | +0.084 |
Kay | +0.081 |
Hel | +0.080 |
Ag | +0.079 |
Neg logit contributions | |
His | -0.065 |
omm | -0.064 |
x | -0.064 |
oscope | -0.064 |
DVD | -0.063 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
omm | +0.068 |
x | +0.066 |
oscope | +0.066 |
DVD | +0.066 |
His | +0.066 |
Neg logit contributions | |
bel | -0.069 |
Fre | -0.066 |
Kay | -0.064 |
Hel | -0.063 |
Ag | -0.063 |
Token | all |
Token ID | 477 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Fre | +0.099 |
bel | +0.099 |
Kay | +0.097 |
Hel | +0.095 |
ora | +0.094 |
Neg logit contributions | |
His | -0.074 |
x | -0.074 |
magnet | -0.072 |
apple | -0.071 |
DVD | -0.069 |
Token | creatures |
Token ID | 8109 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
bel | +0.095 |
Fre | +0.093 |
Kay | +0.089 |
Hel | +0.089 |
Ag | +0.088 |
Neg logit contributions | |
His | -0.080 |
x | -0.079 |
DVD | -0.078 |
omm | -0.078 |
oscope | -0.078 |
Token | , |
Token ID | 11 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
bel | +0.785 |
Fre | +0.779 |
Kay | +0.760 |
Hel | +0.743 |
J | +0.734 |
Neg logit contributions | |
DVD | -0.645 |
His | -0.644 |
magnet | -0.635 |
oscope | -0.632 |
x | -0.620 |
Token | even |
Token ID | 772 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
bel | +0.130 |
Fre | +0.127 |
Kay | +0.123 |
Hel | +0.122 |
Ag | +0.120 |
Neg logit contributions | |
His | -0.098 |
x | -0.097 |
omm | -0.096 |
oscope | -0.096 |
DVD | -0.095 |
Token | the |
Token ID | 262 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
x | +0.047 |
His | +0.045 |
apple | +0.045 |
magnet | +0.045 |
oscope | +0.044 |
Neg logit contributions | |
Fre | -0.060 |
Kay | -0.060 |
bel | -0.059 |
Hel | -0.058 |
Ag | -0.058 |
Token | dead |
Token ID | 2636 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
bel | +0.052 |
Fre | +0.049 |
Kay | +0.048 |
Ag | +0.047 |
Hel | +0.047 |
Neg logit contributions | |
x | -0.041 |
apple | -0.040 |
magnet | -0.040 |
oscope | -0.040 |
boo | -0.039 |
Token | ones |
Token ID | 3392 |
Feature activation | -9.53e+00 |
Pos logit contributions | |
apple | +0.131 |
magnet | +0.125 |
oscope | +0.121 |
His | +0.118 |
engine | +0.118 |
Neg logit contributions | |
Fre | -0.269 |
bel | -0.268 |
Kay | -0.259 |
J | -0.258 |
Ag | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
bel | +0.045 |
Fre | +0.043 |
Kay | +0.042 |
Hel | +0.041 |
Ag | +0.041 |
Neg logit contributions | |
x | -0.054 |
oscope | -0.054 |
omm | -0.053 |
DVD | -0.053 |
His | -0.053 |
Token | " |
Token ID | 366 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
bel | +0.113 |
Fre | +0.112 |
Hel | +0.109 |
Kay | +0.107 |
J | +0.106 |
Neg logit contributions | |
x | -0.082 |
DVD | -0.080 |
oscope | -0.080 |
magnet | -0.076 |
omm | -0.076 |
Token | The |
Token ID | 464 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
His | +0.246 |
oscope | +0.243 |
penter | +0.243 |
Your | +0.238 |
icle | +0.233 |
Neg logit contributions | |
Fre | -0.205 |
common | -0.200 |
ies | -0.199 |
Jay | -0.198 |
bel | -0.195 |
Token | animals |
Token ID | 4695 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
bel | +0.126 |
Kay | +0.117 |
Fre | +0.116 |
J | +0.114 |
Ag | +0.114 |
Neg logit contributions | |
x | -0.127 |
His | -0.126 |
oscope | -0.126 |
omm | -0.122 |
magnet | -0.121 |
Token | take |
Token ID | 1011 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
bel | +0.387 |
Fre | +0.378 |
Kay | +0.371 |
J | +0.369 |
Ag | +0.365 |
Neg logit contributions | |
oscope | -0.309 |
x | -0.309 |
His | -0.301 |
magnet | -0.300 |
DVD | -0.298 |
Token | care |
Token ID | 1337 |
Feature activation | -8.77e+00 |
Pos logit contributions | |
x | +0.262 |
oscope | +0.258 |
His | +0.254 |
DVD | +0.253 |
apple | +0.247 |
Neg logit contributions | |
bel | -0.264 |
Fre | -0.257 |
Kay | -0.250 |
J | -0.244 |
Ag | -0.244 |
Token | of |
Token ID | 286 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
bel | +0.685 |
Fre | +0.665 |
Hel | +0.641 |
Kay | +0.638 |
Ag | +0.629 |
Neg logit contributions | |
omm | -0.487 |
x | -0.485 |
His | -0.479 |
oscope | -0.475 |
DVD | -0.474 |
Token | their |
Token ID | 511 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
x | +0.208 |
oscope | +0.201 |
DVD | +0.199 |
His | +0.199 |
apple | +0.197 |
Neg logit contributions | |
bel | -0.249 |
Fre | -0.233 |
Kay | -0.231 |
Ag | -0.228 |
J | -0.227 |
Token | home |
Token ID | 1363 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
bel | +0.183 |
Fre | +0.183 |
Kay | +0.182 |
J | +0.181 |
Ag | +0.180 |
Neg logit contributions | |
x | -0.194 |
His | -0.193 |
oscope | -0.190 |
apple | -0.189 |
motorcycle | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
bel | +0.084 |
Fre | +0.082 |
Kay | +0.079 |
Hel | +0.079 |
Ag | +0.077 |
Neg logit contributions | |
omm | -0.066 |
His | -0.065 |
x | -0.065 |
DVD | -0.064 |
oscope | -0.064 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
His | +0.072 |
x | +0.071 |
oscope | +0.071 |
magnet | +0.070 |
boo | +0.070 |
Neg logit contributions | |
Fre | -0.096 |
bel | -0.095 |
Kay | -0.093 |
J | -0.092 |
Hel | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
bel | +0.089 |
Ag | +0.085 |
Fre | +0.085 |
Hel | +0.083 |
Kay | +0.083 |
Neg logit contributions | |
apple | -0.038 |
magnet | -0.037 |
x | -0.036 |
tank | -0.036 |
His | -0.033 |
Token | dirt |
Token ID | 13647 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
bel | +0.049 |
Fre | +0.048 |
Kay | +0.047 |
Hel | +0.045 |
Ag | +0.045 |
Neg logit contributions | |
apple | -0.041 |
magnet | -0.041 |
microwave | -0.039 |
His | -0.039 |
x | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Fre | +0.171 |
bel | +0.170 |
Kay | +0.168 |
Hel | +0.167 |
Ag | +0.164 |
Neg logit contributions | |
oscope | -0.113 |
His | -0.112 |
x | -0.112 |
magnet | -0.112 |
DVD | -0.110 |
Token | look |
Token ID | 804 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
magnet | +0.056 |
apple | +0.055 |
His | +0.055 |
boo | +0.053 |
oscope | +0.052 |
Neg logit contributions | |
Fre | -0.084 |
Kay | -0.082 |
Ag | -0.082 |
Hel | -0.080 |
bel | -0.080 |
Token | for |
Token ID | 329 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
bel | +0.446 |
Fre | +0.445 |
Kay | +0.434 |
Hel | +0.430 |
Ag | +0.429 |
Neg logit contributions | |
His | -0.144 |
DVD | -0.140 |
x | -0.140 |
magnet | -0.134 |
omm | -0.133 |
Token | bugs |
Token ID | 11316 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
apple | +0.248 |
magnet | +0.238 |
x | +0.237 |
bone | +0.234 |
tank | +0.225 |
Neg logit contributions | |
bel | -0.223 |
Fre | -0.212 |
Kay | -0.210 |
Hel | -0.210 |
Ag | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
bel | +0.659 |
Fre | +0.656 |
Kay | +0.652 |
Hel | +0.642 |
Ag | +0.624 |
Neg logit contributions | |
oscope | -0.470 |
apple | -0.459 |
DVD | -0.455 |
magnet | -0.454 |
x | -0.449 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
bel | +0.045 |
Fre | +0.044 |
Kay | +0.043 |
Hel | +0.043 |
Ag | +0.043 |
Neg logit contributions | |
oscope | -0.032 |
x | -0.031 |
omm | -0.031 |
DVD | -0.030 |
magnet | -0.030 |
Token | found |
Token ID | 1043 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
His | +0.099 |
oscope | +0.098 |
x | +0.096 |
magnet | +0.095 |
omm | +0.095 |
Neg logit contributions | |
bel | -0.093 |
Fre | -0.090 |
Kay | -0.086 |
Ag | -0.085 |
Hel | -0.084 |
Token | a |
Token ID | 257 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
bel | +0.249 |
Fre | +0.242 |
Kay | +0.236 |
Hel | +0.234 |
Ag | +0.232 |
Neg logit contributions | |
x | -0.140 |
His | -0.140 |
omm | -0.136 |
apple | -0.133 |
DVD | -0.133 |
Token | big |
Token ID | 1263 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
magnet | +0.058 |
x | +0.056 |
apple | +0.055 |
bone | +0.054 |
boo | +0.054 |
Neg logit contributions | |
bel | -0.061 |
Fre | -0.059 |
Kay | -0.059 |
Hel | -0.058 |
Ag | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
bel | +0.175 |
Fre | +0.173 |
Kay | +0.171 |
common | +0.169 |
Hel | +0.164 |
Neg logit contributions | |
omm | -0.150 |
DVD | -0.136 |
penter | -0.136 |
oscope | -0.134 |
magnet | -0.134 |
Token | memories |
Token ID | 9846 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
bel | +0.043 |
Fre | +0.041 |
Kay | +0.039 |
Hel | +0.039 |
Ag | +0.039 |
Neg logit contributions | |
omm | -0.034 |
His | -0.034 |
oscope | -0.033 |
DVD | -0.032 |
penter | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
bel | +0.414 |
Fre | +0.387 |
Kay | +0.378 |
Hel | +0.376 |
Ag | +0.374 |
Neg logit contributions | |
omm | -0.339 |
x | -0.330 |
oscope | -0.326 |
His | -0.325 |
DVD | -0.320 |
Token | his |
Token ID | 465 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
omm | +0.189 |
oscope | +0.184 |
His | +0.184 |
x | +0.183 |
DVD | +0.182 |
Neg logit contributions | |
bel | -0.234 |
Fre | -0.230 |
Kay | -0.223 |
Hel | -0.221 |
Ag | -0.218 |
Token | wander |
Token ID | 27776 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
x | +0.238 |
His | +0.237 |
DVD | +0.234 |
magnet | +0.233 |
oscope | +0.233 |
Neg logit contributions | |
bel | -0.254 |
Fre | -0.253 |
Kay | -0.244 |
Hel | -0.242 |
Ag | -0.239 |
Token | ings |
Token ID | 654 |
Feature activation | -9.10e+00 |
Pos logit contributions | |
Fre | +0.205 |
bel | +0.204 |
Kay | +0.196 |
Hel | +0.194 |
Ag | +0.191 |
Neg logit contributions | |
His | -0.182 |
oscope | -0.181 |
x | -0.180 |
DVD | -0.179 |
omm | -0.177 |
Token | ! |
Token ID | 0 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
bel | +0.546 |
Fre | +0.510 |
Hel | +0.503 |
Kay | +0.499 |
Ag | +0.498 |
Neg logit contributions | |
omm | -0.666 |
x | -0.654 |
oscope | -0.637 |
DVD | -0.635 |
boo | -0.633 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
Kay | +0.122 |
Fre | +0.117 |
J | +0.116 |
Hel | +0.116 |
Ag | +0.116 |
Neg logit contributions | |
x | -0.166 |
oscope | -0.165 |
boo | -0.160 |
forehead | -0.150 |
magnet | -0.150 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
omm | +0.288 |
His | +0.287 |
x | +0.286 |
oscope | +0.284 |
DVD | +0.284 |
Neg logit contributions | |
bel | -0.239 |
Fre | -0.231 |
Kay | -0.222 |
Hel | -0.220 |
Ag | -0.217 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
His | +0.182 |
omm | +0.178 |
x | +0.175 |
DVD | +0.175 |
magnet | +0.174 |
Neg logit contributions | |
bel | -0.068 |
Fre | -0.065 |
Kay | -0.059 |
Hel | -0.059 |
Ag | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
bel | +0.494 |
Fre | +0.479 |
Kay | +0.466 |
Hel | +0.464 |
J | +0.457 |
Neg logit contributions | |
omm | -0.397 |
oscope | -0.382 |
x | -0.381 |
His | -0.380 |
DVD | -0.379 |
Token | having |
Token ID | 1719 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
bel | +0.339 |
Fre | +0.331 |
Kay | +0.318 |
Hel | +0.317 |
Ag | +0.313 |
Neg logit contributions | |
omm | -0.326 |
His | -0.325 |
x | -0.325 |
oscope | -0.322 |
DVD | -0.321 |
Token | lunch |
Token ID | 9965 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
bel | +0.029 |
Fre | +0.027 |
ora | +0.026 |
Kay | +0.026 |
ies | +0.026 |
Neg logit contributions | |
His | -0.015 |
DVD | -0.014 |
x | -0.014 |
apple | -0.013 |
oscope | -0.013 |
Token | together |
Token ID | 1978 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
His | +0.199 |
DVD | +0.197 |
x | +0.193 |
oscope | +0.193 |
penter | +0.191 |
Neg logit contributions | |
Fre | -0.253 |
Hel | -0.242 |
bel | -0.242 |
Kay | -0.241 |
Ag | -0.229 |
Token | . |
Token ID | 13 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
bel | +0.312 |
Fre | +0.305 |
Kay | +0.295 |
Hel | +0.295 |
Ag | +0.289 |
Neg logit contributions | |
His | -0.275 |
oscope | -0.269 |
DVD | -0.269 |
x | -0.268 |
omm | -0.267 |
Token | Lib |
Token ID | 7980 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
bel | +0.043 |
Fre | +0.042 |
Kay | +0.040 |
Hel | +0.040 |
Ag | +0.039 |
Neg logit contributions | |
x | -0.036 |
omm | -0.036 |
oscope | -0.035 |
DVD | -0.035 |
His | -0.035 |
Token | by |
Token ID | 1525 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
bel | +0.054 |
Fre | +0.048 |
Ag | +0.048 |
Hel | +0.045 |
Kay | +0.045 |
Neg logit contributions | |
His | -0.106 |
omm | -0.105 |
seventy | -0.105 |
oscope | -0.104 |
x | -0.103 |
Token | had |
Token ID | 550 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
bel | +0.532 |
Fre | +0.519 |
Kay | +0.492 |
Hel | +0.492 |
J | +0.484 |
Neg logit contributions | |
x | -0.636 |
omm | -0.627 |
DVD | -0.625 |
oscope | -0.617 |
His | -0.611 |
Token | a |
Token ID | 257 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
bel | +0.003 |
Fre | +0.003 |
Kay | +0.003 |
ora | +0.003 |
Hel | +0.003 |
Neg logit contributions | |
His | -0.002 |
oscope | -0.002 |
x | -0.002 |
DVD | -0.002 |
omm | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
omm | +0.066 |
His | +0.066 |
oscope | +0.065 |
x | +0.065 |
DVD | +0.064 |
Neg logit contributions | |
bel | -0.048 |
Fre | -0.047 |
Kay | -0.045 |
Hel | -0.044 |
Ag | -0.044 |
Token | bowl |
Token ID | 9396 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
Fre | +0.148 |
bel | +0.146 |
Kay | +0.140 |
common | +0.140 |
Ag | +0.138 |
Neg logit contributions | |
omm | -0.153 |
oscope | -0.152 |
His | -0.151 |
x | -0.147 |
DVD | -0.147 |
Token | of |
Token ID | 286 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
omm | +0.394 |
x | +0.392 |
His | +0.382 |
oscope | +0.381 |
DVD | +0.379 |
Neg logit contributions | |
bel | -0.461 |
Fre | -0.427 |
Kay | -0.414 |
J | -0.412 |
Ag | -0.406 |