Token | the |
Token ID | 262 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
mill | +0.079 |
ting | +0.078 |
ini | +0.078 |
painter | +0.076 |
paramed | +0.075 |
Neg logit contributions | |
much | -0.060 |
drift | -0.060 |
nap | -0.059 |
dives | -0.057 |
swim | -0.056 |
Token | bird |
Token ID | 6512 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
cles | +0.109 |
laund | +0.108 |
ting | +0.107 |
rom | +0.107 |
years | +0.106 |
Neg logit contributions | |
nap | -0.080 |
much | -0.075 |
long | -0.071 |
swim | -0.069 |
drift | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ting | +0.074 |
mill | +0.074 |
painter | +0.071 |
ini | +0.070 |
office | +0.068 |
Neg logit contributions | |
much | -0.054 |
dives | -0.053 |
drift | -0.053 |
nap | -0.053 |
irm | -0.052 |
Token | said |
Token ID | 531 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.033 |
dives | +0.033 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
mill | -0.048 |
ting | -0.047 |
ini | -0.046 |
painter | -0.046 |
office | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
much | +0.046 |
drift | +0.045 |
dives | +0.045 |
nap | +0.045 |
irm | +0.043 |
Neg logit contributions | |
ting | -0.083 |
mill | -0.083 |
painter | -0.080 |
ini | -0.079 |
paramed | -0.077 |
Token | "' |
Token ID | 24018 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
ini | +0.077 |
mill | +0.076 |
ting | +0.074 |
painter | +0.073 |
office | +0.070 |
Neg logit contributions | |
much | -0.083 |
drift | -0.080 |
dives | -0.078 |
nap | -0.076 |
swim | -0.075 |
Token | Hello |
Token ID | 15496 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
office | +0.360 |
mill | +0.330 |
desks | +0.329 |
porch | +0.329 |
floors | +0.328 |
Neg logit contributions | |
drift | -0.434 |
much | -0.431 |
nap | -0.414 |
swim | -0.404 |
dives | -0.401 |
Token | , |
Token ID | 11 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
ting | +0.013 |
mill | +0.013 |
ini | +0.013 |
painter | +0.013 |
laund | +0.012 |
Neg logit contributions | |
much | -0.009 |
nap | -0.008 |
drift | -0.008 |
dives | -0.008 |
dive | -0.008 |
Token | my |
Token ID | 616 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
ting | +0.086 |
keeping | +0.086 |
cles | +0.086 |
organized | +0.085 |
mill | +0.085 |
Neg logit contributions | |
much | -0.067 |
nap | -0.064 |
drift | -0.061 |
swim | -0.059 |
dive | -0.059 |
Token | name |
Token ID | 1438 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
much | +0.005 |
nap | +0.005 |
drift | +0.005 |
dives | +0.005 |
irm | +0.005 |
Neg logit contributions | |
ting | -0.009 |
mill | -0.008 |
painter | -0.008 |
ini | -0.008 |
laund | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.020 |
dives | +0.020 |
irm | +0.020 |
nap | +0.019 |
Neg logit contributions | |
ting | -0.028 |
mill | -0.028 |
painter | -0.027 |
ini | -0.026 |
office | -0.026 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
mill | +0.075 |
ting | +0.075 |
painter | +0.072 |
ini | +0.072 |
paramed | +0.070 |
Neg logit contributions | |
much | -0.054 |
nap | -0.053 |
drift | -0.053 |
dives | -0.052 |
irm | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -6.96e-03 |
Pos logit contributions | |
ting | +0.024 |
mill | +0.024 |
painter | +0.023 |
ini | +0.023 |
office | +0.022 |
Neg logit contributions | |
much | -0.015 |
drift | -0.015 |
dives | -0.015 |
nap | -0.014 |
irm | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
much | +0.007 |
dives | +0.007 |
drift | +0.007 |
irm | +0.007 |
nap | +0.007 |
Neg logit contributions | |
mill | -0.014 |
ting | -0.014 |
ini | -0.014 |
painter | -0.014 |
cut | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
much | +0.012 |
drift | +0.012 |
dives | +0.012 |
nap | +0.012 |
irm | +0.012 |
Neg logit contributions | |
mill | -0.015 |
ting | -0.015 |
painter | -0.014 |
ini | -0.014 |
paramed | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
much | +0.049 |
dives | +0.043 |
nap | +0.042 |
drift | +0.041 |
swim | +0.039 |
Neg logit contributions | |
ini | -0.098 |
mill | -0.098 |
ting | -0.096 |
painter | -0.093 |
rom | -0.092 |
Token | "' |
Token ID | 24018 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
ini | +0.078 |
mill | +0.076 |
ting | +0.073 |
painter | +0.072 |
floors | +0.070 |
Neg logit contributions | |
much | -0.080 |
drift | -0.076 |
dives | -0.073 |
nap | -0.072 |
swim | -0.071 |
Token | We |
Token ID | 1135 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
mill | +0.343 |
office | +0.332 |
porch | +0.327 |
floors | +0.313 |
paramed | +0.302 |
Neg logit contributions | |
much | -0.437 |
irm | -0.410 |
nap | -0.401 |
ust | -0.400 |
drift | -0.399 |
Token | should |
Token ID | 815 |
Feature activation | +9.13e-02 |
Pos logit contributions | |
drift | +0.033 |
dives | +0.033 |
much | +0.033 |
irm | +0.032 |
nap | +0.031 |
Neg logit contributions | |
mill | -0.048 |
ting | -0.047 |
painter | -0.046 |
ini | -0.045 |
cut | -0.044 |
Token | share |
Token ID | 2648 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
mill | +0.178 |
ting | +0.177 |
painter | +0.172 |
ini | +0.169 |
office | +0.165 |
Neg logit contributions | |
much | -0.100 |
dives | -0.099 |
drift | -0.098 |
nap | -0.096 |
irm | -0.095 |
Token | our |
Token ID | 674 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
mill | +0.051 |
ini | +0.050 |
ting | +0.049 |
paramed | +0.049 |
painter | +0.049 |
Neg logit contributions | |
much | -0.028 |
nap | -0.027 |
dives | -0.026 |
drift | -0.025 |
irm | -0.024 |
Token | special |
Token ID | 2041 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
dives | +0.048 |
nap | +0.047 |
drift | +0.047 |
much | +0.047 |
irm | +0.046 |
Neg logit contributions | |
ting | -0.034 |
mill | -0.033 |
paramed | -0.031 |
painter | -0.031 |
cut | -0.030 |
Token | my |
Token ID | 1820 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
mill | +0.138 |
ting | +0.136 |
painter | +0.124 |
ini | +0.123 |
paramed | +0.122 |
Neg logit contributions | |
much | -0.181 |
drift | -0.180 |
nap | -0.179 |
dives | -0.177 |
irm | -0.175 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
ting | +0.056 |
mill | +0.056 |
ini | +0.054 |
office | +0.053 |
painter | +0.053 |
Neg logit contributions | |
dives | -0.038 |
drift | -0.038 |
much | -0.037 |
nap | -0.037 |
swim | -0.036 |
Token | and |
Token ID | 290 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
ting | +0.016 |
mill | +0.015 |
painter | +0.015 |
ini | +0.014 |
paramed | +0.014 |
Neg logit contributions | |
dives | -0.013 |
nap | -0.013 |
drift | -0.013 |
much | -0.012 |
irm | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
much | +0.036 |
nap | +0.035 |
dives | +0.035 |
drift | +0.034 |
irm | +0.034 |
Neg logit contributions | |
mill | -0.057 |
ting | -0.057 |
painter | -0.054 |
paramed | -0.053 |
ini | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
much | +0.046 |
dives | +0.044 |
drift | +0.044 |
nap | +0.044 |
irm | +0.042 |
Neg logit contributions | |
mill | -0.093 |
ting | -0.093 |
ini | -0.090 |
painter | -0.090 |
office | -0.086 |
Token | "' |
Token ID | 24018 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ini | +0.076 |
mill | +0.075 |
ting | +0.073 |
painter | +0.072 |
office | +0.070 |
Neg logit contributions | |
much | -0.078 |
drift | -0.076 |
dives | -0.073 |
nap | -0.071 |
swim | -0.070 |
Token | Let |
Token ID | 5756 |
Feature activation | +7.77e-02 |
Pos logit contributions | |
office | +0.372 |
mill | +0.352 |
floors | +0.332 |
cut | +0.331 |
homeowner | +0.326 |
Neg logit contributions | |
much | -0.434 |
drift | -0.385 |
ust | -0.371 |
dives | -0.369 |
nap | -0.368 |
Token | 's |
Token ID | 338 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
ting | +0.160 |
mill | +0.159 |
painter | +0.154 |
ini | +0.151 |
paramed | +0.148 |
Neg logit contributions | |
much | -0.078 |
dives | -0.077 |
drift | -0.077 |
nap | -0.076 |
irm | -0.075 |
Token | go |
Token ID | 467 |
Feature activation | -6.44e-02 |
Pos logit contributions | |
nap | +0.030 |
dive | +0.030 |
drift | +0.029 |
swim | +0.029 |
much | +0.029 |
Neg logit contributions | |
ting | -0.054 |
smith | -0.053 |
cut | -0.052 |
years | -0.052 |
ini | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
much | +0.084 |
nap | +0.083 |
dives | +0.083 |
drift | +0.083 |
irm | +0.079 |
Neg logit contributions | |
ting | -0.112 |
mill | -0.112 |
painter | -0.109 |
ini | -0.107 |
cut | -0.106 |
Token | do |
Token ID | 466 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
nap | +0.036 |
dives | +0.035 |
dive | +0.035 |
drift | +0.035 |
swim | +0.035 |
Neg logit contributions | |
ting | -0.059 |
ini | -0.058 |
cut | -0.058 |
smith | -0.058 |
mill | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
mill | +0.075 |
ting | +0.075 |
ini | +0.073 |
painter | +0.073 |
paramed | +0.070 |
Neg logit contributions | |
much | -0.049 |
drift | -0.047 |
nap | -0.047 |
dives | -0.047 |
irm | -0.045 |
Token | said |
Token ID | 531 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
much | +0.047 |
dives | +0.046 |
drift | +0.046 |
nap | +0.045 |
irm | +0.044 |
Neg logit contributions | |
ting | -0.043 |
mill | -0.043 |
ini | -0.042 |
painter | -0.041 |
paramed | -0.040 |
Token | excited |
Token ID | 6568 |
Feature activation | -4.55e-03 |
Pos logit contributions | |
much | +0.048 |
dives | +0.046 |
nap | +0.044 |
drift | +0.044 |
irm | +0.042 |
Neg logit contributions | |
ting | -0.094 |
mill | -0.093 |
ini | -0.091 |
painter | -0.090 |
cut | -0.086 |
Token | ly |
Token ID | 306 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
much | +0.008 |
dives | +0.008 |
drift | +0.008 |
nap | +0.008 |
irm | +0.008 |
Neg logit contributions | |
ting | -0.006 |
mill | -0.006 |
painter | -0.006 |
ini | -0.006 |
office | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
much | +0.018 |
drift | +0.017 |
dives | +0.017 |
nap | +0.017 |
irm | +0.017 |
Neg logit contributions | |
ting | -0.032 |
mill | -0.032 |
painter | -0.031 |
ini | -0.031 |
paramed | -0.030 |
Token | "' |
Token ID | 24018 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
ting | +0.057 |
mill | +0.056 |
painter | +0.053 |
ini | +0.050 |
paramed | +0.049 |
Neg logit contributions | |
much | -0.091 |
nap | -0.091 |
dives | -0.090 |
drift | -0.090 |
irm | -0.089 |
Token | Wow |
Token ID | 22017 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
mill | +0.287 |
office | +0.273 |
cut | +0.264 |
painter | +0.255 |
ting | +0.253 |
Neg logit contributions | |
much | -0.483 |
drift | -0.462 |
nap | -0.455 |
ust | -0.445 |
dives | -0.445 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
irm | +0.136 |
drift | +0.129 |
dives | +0.127 |
hops | +0.125 |
much | +0.125 |
Neg logit contributions | |
mill | -0.122 |
ting | -0.122 |
painter | -0.114 |
ter | -0.108 |
office | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
ting | +0.089 |
mill | +0.087 |
ini | +0.086 |
painter | +0.084 |
cut | +0.082 |
Neg logit contributions | |
much | -0.065 |
nap | -0.063 |
dives | -0.062 |
drift | -0.061 |
dive | -0.059 |
Token | buildings |
Token ID | 6832 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
ting | +0.087 |
ini | +0.080 |
cut | +0.078 |
years | +0.075 |
mill | +0.074 |
Neg logit contributions | |
much | -0.108 |
nap | -0.101 |
drift | -0.100 |
dives | -0.097 |
time | -0.093 |
Token | here |
Token ID | 994 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
ting | +0.084 |
mill | +0.084 |
painter | +0.081 |
ini | +0.080 |
office | +0.077 |
Neg logit contributions | |
much | -0.050 |
drift | -0.049 |
dives | -0.049 |
nap | -0.048 |
irm | -0.047 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.24e-02 |
Pos logit contributions | |
mill | +0.022 |
ting | +0.022 |
ini | +0.021 |
painter | +0.021 |
rom | +0.020 |
Neg logit contributions | |
much | -0.014 |
nap | -0.014 |
drift | -0.014 |
dives | -0.014 |
irm | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
mill | +0.143 |
ting | +0.142 |
painter | +0.138 |
ini | +0.135 |
paramed | +0.132 |
Neg logit contributions | |
much | -0.078 |
drift | -0.077 |
dives | -0.077 |
nap | -0.076 |
irm | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
much | +0.043 |
nap | +0.040 |
drift | +0.040 |
dives | +0.040 |
irm | +0.038 |
Neg logit contributions | |
ting | -0.104 |
mill | -0.103 |
painter | -0.099 |
ini | -0.099 |
paramed | -0.096 |
Token | Joe |
Token ID | 19585 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
much | +0.074 |
nap | +0.071 |
drift | +0.071 |
dives | +0.071 |
irm | +0.069 |
Neg logit contributions | |
ting | -0.071 |
mill | -0.069 |
ini | -0.065 |
painter | -0.064 |
office | -0.062 |
Token | said |
Token ID | 531 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
ting | +0.053 |
mill | +0.053 |
painter | +0.051 |
ini | +0.050 |
paramed | +0.049 |
Neg logit contributions | |
much | -0.038 |
drift | -0.038 |
dives | -0.038 |
nap | -0.037 |
irm | -0.036 |
Token | :" |
Token ID | 11097 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
drift | +0.058 |
nap | +0.058 |
irm | +0.058 |
dives | +0.058 |
much | +0.056 |
Neg logit contributions | |
ting | -0.084 |
mill | -0.083 |
painter | -0.082 |
paramed | -0.079 |
cut | -0.078 |
Token | Don |
Token ID | 3987 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
mill | +0.219 |
ting | +0.218 |
painter | +0.204 |
ini | +0.195 |
paramed | +0.185 |
Neg logit contributions | |
much | -0.522 |
dives | -0.520 |
drift | -0.519 |
nap | -0.515 |
irm | -0.511 |
Token | 't |
Token ID | 470 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
ting | +0.072 |
mill | +0.071 |
ini | +0.069 |
painter | +0.068 |
rom | +0.067 |
Neg logit contributions | |
irm | -0.087 |
dives | -0.084 |
nap | -0.084 |
drift | -0.081 |
hops | -0.080 |
Token | worry |
Token ID | 5490 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
dives | +0.090 |
much | +0.087 |
ls | +0.087 |
irm | +0.086 |
drift | +0.085 |
Neg logit contributions | |
mill | -0.087 |
ting | -0.085 |
painter | -0.084 |
paramed | -0.079 |
ini | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
mill | +0.047 |
painter | +0.046 |
ting | +0.046 |
ini | +0.045 |
office | +0.044 |
Neg logit contributions | |
dives | -0.041 |
irm | -0.041 |
drift | -0.041 |
nap | -0.039 |
hops | -0.039 |
Token | I |
Token ID | 314 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
ting | +0.007 |
mill | +0.007 |
painter | +0.007 |
ini | +0.007 |
paramed | +0.007 |
Neg logit contributions | |
much | -0.005 |
dives | -0.005 |
drift | -0.005 |
nap | -0.005 |
irm | -0.005 |
Token | sad |
Token ID | 6507 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
dives | +0.057 |
drift | +0.056 |
nap | +0.055 |
irm | +0.053 |
hops | +0.053 |
Neg logit contributions | |
mill | -0.079 |
painter | -0.078 |
ting | -0.076 |
ini | -0.076 |
paramed | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
ting | +0.089 |
mill | +0.086 |
painter | +0.082 |
office | +0.081 |
Why | +0.079 |
Neg logit contributions | |
drift | -0.073 |
dives | -0.073 |
irm | -0.070 |
much | -0.070 |
nap | -0.069 |
Token | He |
Token ID | 679 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
much | +0.004 |
drift | +0.003 |
dives | +0.003 |
nap | +0.003 |
irm | +0.003 |
Neg logit contributions | |
ting | -0.012 |
mill | -0.012 |
ini | -0.011 |
painter | -0.011 |
paramed | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
much | +0.013 |
dives | +0.013 |
drift | +0.013 |
nap | +0.012 |
irm | +0.012 |
Neg logit contributions | |
mill | -0.013 |
ting | -0.013 |
painter | -0.012 |
ini | -0.012 |
paramed | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
much | +0.048 |
dives | +0.046 |
nap | +0.046 |
drift | +0.046 |
irm | +0.044 |
Neg logit contributions | |
mill | -0.097 |
ting | -0.097 |
ini | -0.094 |
painter | -0.093 |
rom | -0.090 |
Token | "" |
Token ID | 13538 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ini | +0.084 |
mill | +0.081 |
ting | +0.078 |
painter | +0.076 |
keeping | +0.076 |
Neg logit contributions | |
much | -0.079 |
drift | -0.074 |
nap | -0.071 |
dives | -0.070 |
swim | -0.069 |
Token | I |
Token ID | 40 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
mill | +0.266 |
ting | +0.254 |
office | +0.231 |
painter | +0.230 |
ini | +0.229 |
Neg logit contributions | |
much | -0.483 |
drift | -0.469 |
nap | -0.463 |
irm | -0.461 |
dives | -0.460 |
Token | hope |
Token ID | 2911 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
mill | +0.033 |
painter | +0.033 |
ini | +0.032 |
paramed | +0.031 |
ting | +0.031 |
Neg logit contributions | |
drift | -0.026 |
dives | -0.026 |
irm | -0.026 |
much | -0.025 |
ls | -0.025 |
Token | something |
Token ID | 1223 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
ting | +0.056 |
mill | +0.056 |
painter | +0.053 |
ini | +0.053 |
paramed | +0.052 |
Neg logit contributions | |
much | -0.033 |
drift | -0.032 |
nap | -0.032 |
dives | -0.031 |
irm | -0.030 |
Token | will |
Token ID | 481 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
irm | +0.075 |
drift | +0.070 |
dives | +0.069 |
fins | +0.068 |
inn | +0.067 |
Neg logit contributions | |
mill | -0.107 |
ting | -0.106 |
painter | -0.105 |
Why | -0.102 |
office | -0.100 |
Token | change |
Token ID | 1487 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
mill | +0.155 |
ting | +0.153 |
painter | +0.149 |
ini | +0.147 |
office | +0.143 |
Neg logit contributions | |
dives | -0.094 |
much | -0.093 |
irm | -0.091 |
drift | -0.091 |
nap | -0.090 |
Token | lesson |
Token ID | 11483 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
much | +0.048 |
nap | +0.047 |
dives | +0.047 |
drift | +0.047 |
irm | +0.045 |
Neg logit contributions | |
ting | -0.074 |
mill | -0.073 |
painter | -0.070 |
ini | -0.069 |
paramed | -0.067 |
Token | � |
Token ID | 6184 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
drift | +0.013 |
dives | +0.013 |
nap | +0.013 |
much | +0.012 |
irm | +0.012 |
Neg logit contributions | |
ting | -0.017 |
mill | -0.017 |
painter | -0.016 |
ini | -0.016 |
office | -0.015 |
Token | � |
Token ID | 95 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
much | +0.031 |
nap | +0.030 |
dives | +0.030 |
drift | +0.030 |
irm | +0.029 |
Neg logit contributions | |
mill | -0.038 |
ting | -0.038 |
painter | -0.036 |
ini | -0.036 |
paramed | -0.035 |
Token | € |
Token ID | 26391 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ting | +0.076 |
mill | +0.075 |
painter | +0.073 |
ini | +0.068 |
cut | +0.067 |
Neg logit contributions | |
much | -0.081 |
dives | -0.077 |
drift | -0.077 |
irm | -0.077 |
nap | -0.076 |
Token | � |
Token ID | 447 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
drift | +0.016 |
much | +0.016 |
dives | +0.016 |
nap | +0.016 |
irm | +0.016 |
Neg logit contributions | |
mill | -0.021 |
ting | -0.020 |
painter | -0.020 |
ini | -0.020 |
office | -0.019 |
Token | � |
Token ID | 250 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
much | +0.020 |
drift | +0.018 |
nap | +0.018 |
dives | +0.018 |
irm | +0.017 |
Neg logit contributions | |
ting | -0.030 |
painter | -0.030 |
mill | -0.029 |
ini | -0.029 |
floors | -0.028 |
Token | never |
Token ID | 1239 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
mill | +0.310 |
ting | +0.302 |
painter | +0.288 |
office | +0.277 |
ini | +0.277 |
Neg logit contributions | |
much | -0.432 |
drift | -0.410 |
nap | -0.408 |
irm | -0.407 |
dives | -0.406 |
Token | be |
Token ID | 307 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
drift | +0.032 |
much | +0.032 |
irm | +0.031 |
dives | +0.031 |
ls | +0.031 |
Neg logit contributions | |
ting | -0.053 |
mill | -0.053 |
painter | -0.051 |
office | -0.049 |
paramed | -0.048 |
Token | rude |
Token ID | 22066 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
ting | +0.016 |
mill | +0.015 |
painter | +0.015 |
ini | +0.015 |
office | +0.014 |
Neg logit contributions | |
drift | -0.010 |
nap | -0.010 |
dives | -0.010 |
irm | -0.010 |
much | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-03 |
Pos logit contributions | |
mill | +0.079 |
ini | +0.075 |
ting | +0.075 |
painter | +0.074 |
laund | +0.073 |
Neg logit contributions | |
much | -0.042 |
nap | -0.039 |
dives | -0.038 |
drift | -0.037 |
irm | -0.037 |
Token | Fortunately |
Token ID | 20525 |
Feature activation | +2.11e-03 |
Pos logit contributions | |
drift | +0.002 |
dives | +0.002 |
nap | +0.002 |
much | +0.002 |
irm | +0.002 |
Neg logit contributions | |
ting | -0.003 |
mill | -0.003 |
painter | -0.003 |
ini | -0.003 |
paramed | -0.003 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
dives | +0.072 |
irm | +0.070 |
drift | +0.069 |
nap | +0.069 |
ls | +0.066 |
Neg logit contributions | |
ting | -0.105 |
painter | -0.100 |
mill | -0.100 |
paramed | -0.094 |
office | -0.094 |
Token | � |
Token ID | 6184 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
ting | +0.005 |
painter | +0.004 |
mill | +0.004 |
ini | +0.004 |
Why | +0.004 |
Neg logit contributions | |
dives | -0.003 |
drift | -0.003 |
irm | -0.003 |
nap | -0.003 |
hops | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | +5.14e-02 |
Pos logit contributions | |
much | +0.034 |
dives | +0.033 |
drift | +0.033 |
nap | +0.033 |
irm | +0.033 |
Neg logit contributions | |
mill | -0.033 |
ting | -0.033 |
painter | -0.031 |
ini | -0.030 |
office | -0.030 |
Token | € |
Token ID | 26391 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
mill | +0.075 |
ting | +0.074 |
painter | +0.071 |
ini | +0.070 |
cut | +0.067 |
Neg logit contributions | |
much | -0.082 |
drift | -0.081 |
dives | -0.080 |
nap | -0.080 |
irm | -0.080 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
drift | +0.018 |
dives | +0.018 |
much | +0.017 |
nap | +0.017 |
irm | +0.017 |
Neg logit contributions | |
mill | -0.019 |
ting | -0.019 |
painter | -0.018 |
ini | -0.018 |
office | -0.017 |
Token | � |
Token ID | 250 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
much | +0.023 |
drift | +0.022 |
nap | +0.022 |
dives | +0.021 |
irm | +0.021 |
Neg logit contributions | |
ting | -0.034 |
painter | -0.034 |
mill | -0.034 |
ini | -0.033 |
office | -0.032 |
Token | she |
Token ID | 673 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
mill | +0.298 |
ting | +0.278 |
painter | +0.273 |
office | +0.266 |
ini | +0.259 |
Neg logit contributions | |
much | -0.452 |
drift | -0.434 |
ust | -0.429 |
nap | -0.429 |
irm | -0.426 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
drift | +0.060 |
dives | +0.060 |
nap | +0.060 |
much | +0.060 |
irm | +0.060 |
Neg logit contributions | |
mill | -0.087 |
ting | -0.086 |
painter | -0.083 |
ini | -0.082 |
office | -0.081 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ting | +0.075 |
mill | +0.073 |
painter | +0.070 |
ini | +0.069 |
cut | +0.067 |
Neg logit contributions | |
dives | -0.051 |
drift | -0.051 |
nap | -0.050 |
irm | -0.049 |
much | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
ting | +0.034 |
mill | +0.034 |
painter | +0.033 |
ini | +0.032 |
paramed | +0.031 |
Neg logit contributions | |
much | -0.024 |
drift | -0.023 |
dives | -0.023 |
nap | -0.023 |
irm | -0.023 |
Token | She |
Token ID | 1375 |
Feature activation | +3.27e-04 |
Pos logit contributions | |
much | +0.005 |
drift | +0.004 |
dives | +0.004 |
nap | +0.004 |
irm | +0.004 |
Neg logit contributions | |
mill | -0.007 |
ting | -0.007 |
painter | -0.006 |
ini | -0.006 |
paramed | -0.006 |
Token | important |
Token ID | 1593 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
dives | +0.070 |
drift | +0.070 |
much | +0.069 |
nap | +0.069 |
irm | +0.069 |
Neg logit contributions | |
mill | -0.108 |
ting | -0.108 |
painter | -0.104 |
ini | -0.101 |
office | -0.099 |
Token | � |
Token ID | 6184 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ini | +0.083 |
mill | +0.083 |
paramed | +0.083 |
painter | +0.081 |
ting | +0.081 |
Neg logit contributions | |
much | -0.043 |
nap | -0.039 |
drift | -0.037 |
dives | -0.037 |
hops | -0.035 |
Token | � |
Token ID | 95 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
nap | +0.033 |
much | +0.033 |
dives | +0.033 |
drift | +0.033 |
dive | +0.032 |
Neg logit contributions | |
ting | -0.036 |
mill | -0.035 |
painter | -0.034 |
ini | -0.034 |
cut | -0.034 |
Token | € |
Token ID | 26391 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
mill | +0.078 |
ting | +0.078 |
cut | +0.075 |
painter | +0.073 |
ini | +0.071 |
Neg logit contributions | |
much | -0.070 |
nap | -0.070 |
drift | -0.069 |
irm | -0.069 |
dives | -0.069 |
Token | � |
Token ID | 447 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
much | +0.016 |
dives | +0.016 |
nap | +0.016 |
drift | +0.016 |
irm | +0.015 |
Neg logit contributions | |
ting | -0.020 |
mill | -0.020 |
painter | -0.019 |
ini | -0.018 |
cut | -0.018 |
Token | � |
Token ID | 250 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
much | +0.022 |
nap | +0.021 |
drift | +0.021 |
dives | +0.021 |
ls | +0.020 |
Neg logit contributions | |
ting | -0.031 |
mill | -0.030 |
painter | -0.030 |
cut | -0.030 |
ini | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
mill | +0.306 |
ting | +0.288 |
painter | +0.278 |
office | +0.277 |
cut | +0.270 |
Neg logit contributions | |
much | -0.448 |
ust | -0.428 |
nap | -0.417 |
drift | -0.415 |
irm | -0.409 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ting | +0.105 |
ini | +0.098 |
mill | +0.097 |
rom | +0.095 |
years | +0.093 |
Neg logit contributions | |
nap | -0.099 |
much | -0.093 |
time | -0.086 |
drift | -0.085 |
dives | -0.083 |
Token | had |
Token ID | 550 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
ting | +0.037 |
mill | +0.036 |
painter | +0.035 |
ini | +0.034 |
paramed | +0.034 |
Neg logit contributions | |
much | -0.021 |
drift | -0.020 |
nap | -0.020 |
dives | -0.020 |
irm | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
mill | +0.077 |
ting | +0.077 |
painter | +0.074 |
ini | +0.072 |
office | +0.071 |
Neg logit contributions | |
drift | -0.052 |
dives | -0.052 |
much | -0.051 |
irm | -0.051 |
nap | -0.050 |
Token | price |
Token ID | 2756 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
much | +0.080 |
nap | +0.078 |
drift | +0.077 |
dives | +0.076 |
irm | +0.072 |
Neg logit contributions | |
ting | -0.135 |
mill | -0.131 |
painter | -0.126 |
ini | -0.126 |
cut | -0.122 |
Token | peace |
Token ID | 4167 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
nap | +0.044 |
much | +0.044 |
drift | +0.043 |
dives | +0.043 |
irm | +0.041 |
Neg logit contributions | |
ting | -0.052 |
mill | -0.050 |
ini | -0.049 |
painter | -0.048 |
paramed | -0.047 |
Token | � |
Token ID | 6184 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
much | +0.070 |
dives | +0.069 |
drift | +0.069 |
nap | +0.067 |
irm | +0.067 |
Neg logit contributions | |
ting | -0.107 |
mill | -0.106 |
painter | -0.102 |
ini | -0.100 |
office | -0.098 |
Token | � |
Token ID | 95 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
much | +0.041 |
drift | +0.040 |
nap | +0.040 |
dives | +0.040 |
irm | +0.039 |
Neg logit contributions | |
mill | -0.038 |
ting | -0.038 |
painter | -0.037 |
ini | -0.036 |
cut | -0.034 |
Token | € |
Token ID | 26391 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
mill | +0.071 |
painter | +0.068 |
ting | +0.068 |
cut | +0.066 |
ini | +0.065 |
Neg logit contributions | |
much | -0.081 |
drift | -0.078 |
irm | -0.076 |
nap | -0.076 |
dives | -0.075 |
Token | � |
Token ID | 447 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
much | +0.011 |
drift | +0.011 |
dives | +0.011 |
nap | +0.010 |
irm | +0.010 |
Neg logit contributions | |
ting | -0.018 |
mill | -0.018 |
painter | -0.018 |
ini | -0.017 |
paramed | -0.017 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.020 |
nap | +0.019 |
drift | +0.019 |
dives | +0.018 |
irm | +0.018 |
Neg logit contributions | |
ting | -0.041 |
mill | -0.040 |
painter | -0.039 |
ini | -0.039 |
floors | -0.038 |
Token | she |
Token ID | 673 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
mill | +0.302 |
ting | +0.296 |
painter | +0.279 |
ini | +0.273 |
office | +0.265 |
Neg logit contributions | |
much | -0.438 |
drift | -0.426 |
nap | -0.426 |
dives | -0.420 |
irm | -0.417 |
Token | just |
Token ID | 655 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
drift | +0.053 |
dives | +0.053 |
irm | +0.053 |
nap | +0.052 |
much | +0.052 |
Neg logit contributions | |
mill | -0.081 |
ting | -0.080 |
painter | -0.078 |
ini | -0.077 |
office | -0.076 |
Token | needs |
Token ID | 2476 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
much | +0.116 |
dives | +0.116 |
nap | +0.115 |
drift | +0.115 |
irm | +0.114 |
Neg logit contributions | |
ting | -0.231 |
mill | -0.229 |
painter | -0.220 |
ini | -0.213 |
office | -0.212 |
Token | to |
Token ID | 284 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
mill | +0.071 |
ting | +0.071 |
ini | +0.069 |
painter | +0.069 |
paramed | +0.066 |
Neg logit contributions | |
much | -0.045 |
nap | -0.043 |
drift | -0.043 |
dives | -0.042 |
irm | -0.040 |
Token | remember |
Token ID | 3505 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
mill | +0.083 |
ting | +0.083 |
painter | +0.080 |
ini | +0.079 |
office | +0.077 |
Neg logit contributions | |
much | -0.045 |
dives | -0.044 |
drift | -0.043 |
nap | -0.043 |
irm | -0.042 |
Token | hugged |
Token ID | 41130 |
Feature activation | -9.27e-03 |
Pos logit contributions | |
ting | +0.050 |
mill | +0.049 |
painter | +0.048 |
ini | +0.046 |
office | +0.045 |
Neg logit contributions | |
much | -0.039 |
drift | -0.039 |
dives | -0.039 |
nap | -0.038 |
irm | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
much | +0.012 |
nap | +0.011 |
drift | +0.011 |
irm | +0.011 |
dives | +0.011 |
Neg logit contributions | |
mill | -0.017 |
ini | -0.017 |
painter | -0.017 |
ting | -0.016 |
office | -0.016 |
Token | cat |
Token ID | 3797 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
much | +0.046 |
nap | +0.045 |
drift | +0.044 |
dives | +0.044 |
irm | +0.042 |
Neg logit contributions | |
ting | -0.075 |
mill | -0.073 |
painter | -0.070 |
ini | -0.070 |
paramed | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ting | +0.137 |
mill | +0.131 |
painter | +0.127 |
office | +0.126 |
cut | +0.125 |
Neg logit contributions | |
dives | -0.126 |
drift | -0.123 |
irm | -0.119 |
ust | -0.118 |
ls | -0.116 |
Token | said |
Token ID | 531 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
much | +0.035 |
drift | +0.035 |
dives | +0.035 |
nap | +0.035 |
irm | +0.034 |
Neg logit contributions | |
mill | -0.058 |
ting | -0.057 |
painter | -0.055 |
ini | -0.054 |
paramed | -0.053 |
Token | :" |
Token ID | 11097 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
irm | +0.043 |
drift | +0.043 |
nap | +0.043 |
dives | +0.042 |
ust | +0.040 |
Neg logit contributions | |
ting | -0.084 |
mill | -0.083 |
painter | -0.081 |
paramed | -0.079 |
cut | -0.079 |
Token | Thank |
Token ID | 10449 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ting | +0.245 |
mill | +0.236 |
painter | +0.225 |
ini | +0.219 |
paramed | +0.205 |
Neg logit contributions | |
dives | -0.489 |
much | -0.488 |
drift | -0.484 |
nap | -0.483 |
irm | -0.479 |
Token | you |
Token ID | 345 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
mill | +0.054 |
painter | +0.052 |
ting | +0.052 |
ini | +0.051 |
paramed | +0.050 |
Neg logit contributions | |
much | -0.024 |
nap | -0.023 |
dives | -0.023 |
drift | -0.023 |
irm | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
drift | +0.066 |
dives | +0.066 |
much | +0.065 |
nap | +0.065 |
irm | +0.064 |
Neg logit contributions | |
mill | -0.122 |
ting | -0.122 |
painter | -0.118 |
ini | -0.116 |
office | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ini | +0.076 |
smith | +0.073 |
rom | +0.071 |
mill | +0.070 |
pavement | +0.069 |
Neg logit contributions | |
much | -0.056 |
nap | -0.050 |
swim | -0.049 |
good | -0.048 |
dive | -0.047 |
Token | delicious |
Token ID | 12625 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ting | +0.125 |
mill | +0.124 |
painter | +0.120 |
ini | +0.119 |
rom | +0.116 |
Neg logit contributions | |
much | -0.063 |
nap | -0.062 |
drift | -0.061 |
dives | -0.061 |
irm | -0.058 |
Token | at |
Token ID | 379 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
dives | +0.089 |
drift | +0.087 |
much | +0.087 |
nap | +0.087 |
irm | +0.085 |
Neg logit contributions | |
ting | -0.157 |
mill | -0.155 |
painter | -0.149 |
ini | -0.142 |
office | -0.141 |
Token | her |
Token ID | 607 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
much | +0.040 |
nap | +0.038 |
time | +0.034 |
drift | +0.033 |
irm | +0.032 |
Neg logit contributions | |
paramed | -0.081 |
ini | -0.080 |
mill | -0.076 |
cles | -0.076 |
cut | -0.076 |
Token | Mum |
Token ID | 38367 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
nap | +0.049 |
much | +0.048 |
dives | +0.048 |
drift | +0.047 |
irm | +0.045 |
Neg logit contributions | |
ting | -0.061 |
mill | -0.057 |
ini | -0.056 |
paramed | -0.055 |
cut | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
mill | +0.144 |
ting | +0.143 |
painter | +0.139 |
ini | +0.137 |
paramed | +0.133 |
Neg logit contributions | |
much | -0.084 |
drift | -0.083 |
dives | -0.082 |
nap | -0.082 |
irm | -0.079 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
much | +0.035 |
drift | +0.035 |
dives | +0.034 |
nap | +0.034 |
irm | +0.032 |
Neg logit contributions | |
ting | -0.057 |
mill | -0.057 |
ini | -0.057 |
painter | -0.054 |
office | -0.054 |
Token | :" |
Token ID | 11097 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ini | +0.053 |
mill | +0.052 |
painter | +0.049 |
pavement | +0.049 |
ting | +0.048 |
Neg logit contributions | |
much | -0.025 |
nap | -0.021 |
drift | -0.020 |
okay | -0.020 |
dives | -0.019 |
Token | Is |
Token ID | 3792 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
mill | +0.240 |
ini | +0.231 |
office | +0.228 |
floors | +0.216 |
painter | +0.208 |
Neg logit contributions | |
much | -0.505 |
drift | -0.486 |
nap | -0.486 |
dives | -0.472 |
OK | -0.464 |
Token | it |
Token ID | 340 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ting | +0.061 |
mill | +0.060 |
ini | +0.060 |
painter | +0.058 |
cut | +0.057 |
Neg logit contributions | |
much | -0.051 |
nap | -0.049 |
dives | -0.049 |
drift | -0.047 |
ls | -0.046 |
Token | ready |
Token ID | 3492 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
irm | +0.021 |
dives | +0.020 |
drift | +0.020 |
hops | +0.019 |
much | +0.019 |
Neg logit contributions | |
mill | -0.028 |
ting | -0.027 |
painter | -0.027 |
ini | -0.026 |
office | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
much | +0.126 |
drift | +0.124 |
dives | +0.124 |
nap | +0.123 |
irm | +0.120 |
Neg logit contributions | |
ting | -0.174 |
mill | -0.174 |
painter | -0.167 |
ini | -0.165 |
paramed | -0.160 |
Token | Mum |
Token ID | 38367 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
ting | +0.085 |
mill | +0.085 |
painter | +0.082 |
ini | +0.081 |
paramed | +0.078 |
Neg logit contributions | |
much | -0.068 |
drift | -0.067 |
dives | -0.067 |
nap | -0.067 |
irm | -0.065 |
Token | special |
Token ID | 2041 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
much | +0.032 |
drift | +0.032 |
dives | +0.032 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
mill | -0.033 |
ting | -0.033 |
painter | -0.031 |
ini | -0.031 |
office | -0.030 |
Token | things |
Token ID | 1243 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
much | +0.019 |
dives | +0.019 |
nap | +0.018 |
drift | +0.018 |
irm | +0.018 |
Neg logit contributions | |
ting | -0.017 |
mill | -0.017 |
painter | -0.016 |
ini | -0.016 |
paramed | -0.016 |
Token | â |
Token ID | 22940 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ting | +0.016 |
mill | +0.015 |
painter | +0.014 |
cut | +0.014 |
office | +0.014 |
Neg logit contributions | |
dives | -0.013 |
irm | -0.013 |
drift | -0.013 |
nap | -0.013 |
much | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ting | +0.028 |
mill | +0.027 |
painter | +0.026 |
ini | +0.026 |
office | +0.025 |
Neg logit contributions | |
much | -0.029 |
dives | -0.028 |
drift | -0.028 |
nap | -0.028 |
irm | -0.027 |
Token | � |
Token ID | 447 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
drift | +0.016 |
dives | +0.016 |
much | +0.016 |
irm | +0.016 |
nap | +0.016 |
Neg logit contributions | |
mill | -0.022 |
ting | -0.022 |
painter | -0.021 |
ini | -0.021 |
office | -0.021 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.026 |
drift | +0.025 |
dives | +0.025 |
nap | +0.025 |
irm | +0.024 |
Neg logit contributions | |
ting | -0.030 |
mill | -0.030 |
painter | -0.029 |
ini | -0.029 |
cut | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
mill | +0.310 |
ting | +0.288 |
painter | +0.284 |
office | +0.277 |
paramed | +0.273 |
Neg logit contributions | |
much | -0.435 |
drift | -0.416 |
nap | -0.414 |
ust | -0.411 |
irm | -0.408 |
Token | stones |
Token ID | 14966 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
mill | +0.037 |
ting | +0.037 |
painter | +0.036 |
ini | +0.036 |
paramed | +0.035 |
Neg logit contributions | |
much | -0.028 |
nap | -0.028 |
dives | -0.028 |
drift | -0.028 |
irm | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.020 |
nap | +0.020 |
dives | +0.020 |
irm | +0.018 |
Neg logit contributions | |
mill | -0.034 |
ting | -0.034 |
painter | -0.033 |
ini | -0.033 |
paramed | -0.032 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
ting | +0.100 |
mill | +0.099 |
painter | +0.096 |
ini | +0.095 |
paramed | +0.093 |
Neg logit contributions | |
much | -0.063 |
nap | -0.061 |
drift | -0.060 |
dives | -0.060 |
irm | -0.057 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
mill | +0.039 |
ting | +0.039 |
ini | +0.038 |
painter | +0.038 |
paramed | +0.037 |
Neg logit contributions | |
much | -0.029 |
dives | -0.028 |
nap | -0.028 |
drift | -0.028 |
hops | -0.027 |
Token | strange |
Token ID | 6283 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
dives | +0.073 |
drift | +0.072 |
irm | +0.072 |
nap | +0.072 |
much | +0.072 |
Neg logit contributions | |
ting | -0.106 |
mill | -0.106 |
painter | -0.101 |
ini | -0.099 |
cut | -0.096 |
Token | � |
Token ID | 6184 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
mill | +0.029 |
ting | +0.029 |
ini | +0.028 |
painter | +0.028 |
paramed | +0.028 |
Neg logit contributions | |
much | -0.017 |
drift | -0.016 |
dives | -0.016 |
nap | -0.016 |
irm | -0.015 |
Token | � |
Token ID | 95 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
dives | +0.032 |
drift | +0.031 |
nap | +0.031 |
much | +0.031 |
dive | +0.031 |
Neg logit contributions | |
ting | -0.033 |
mill | -0.033 |
painter | -0.033 |
ini | -0.033 |
cut | -0.032 |
Token | € |
Token ID | 26391 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
mill | +0.077 |
painter | +0.075 |
ting | +0.074 |
ini | +0.072 |
cut | +0.072 |
Neg logit contributions | |
dives | -0.072 |
drift | -0.071 |
much | -0.070 |
irm | -0.069 |
nap | -0.069 |
Token | � |
Token ID | 447 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.020 |
dives | +0.020 |
nap | +0.020 |
irm | +0.020 |
Neg logit contributions | |
mill | -0.020 |
ting | -0.020 |
painter | -0.019 |
ini | -0.019 |
office | -0.018 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.026 |
drift | +0.025 |
dives | +0.025 |
nap | +0.025 |
irm | +0.024 |
Neg logit contributions | |
ting | -0.031 |
mill | -0.030 |
painter | -0.030 |
ini | -0.029 |
cut | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
mill | +0.307 |
ting | +0.289 |
painter | +0.282 |
office | +0.278 |
cut | +0.271 |
Neg logit contributions | |
much | -0.437 |
drift | -0.423 |
ust | -0.420 |
nap | -0.419 |
dives | -0.414 |
Token | k |
Token ID | 479 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
ini | +0.099 |
ting | +0.099 |
mill | +0.098 |
painter | +0.097 |
rom | +0.094 |
Neg logit contributions | |
nap | -0.093 |
much | -0.093 |
drift | -0.089 |
dives | -0.087 |
hops | -0.086 |
Token | itty |
Token ID | 9760 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
much | +0.003 |
dives | +0.003 |
nap | +0.003 |
hops | +0.003 |
ls | +0.003 |
Neg logit contributions | |
mill | -0.003 |
painter | -0.003 |
ting | -0.003 |
floors | -0.003 |
paramed | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
ting | +0.091 |
mill | +0.090 |
painter | +0.087 |
ini | +0.086 |
paramed | +0.084 |
Neg logit contributions | |
much | -0.055 |
drift | -0.053 |
dives | -0.053 |
nap | -0.053 |
irm | -0.051 |
Token | wearing |
Token ID | 5762 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
ting | +0.064 |
mill | +0.064 |
painter | +0.061 |
ini | +0.060 |
office | +0.059 |
Neg logit contributions | |
drift | -0.039 |
dives | -0.039 |
much | -0.039 |
nap | -0.039 |
irm | -0.038 |
Token | him |
Token ID | 683 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
much | +0.007 |
nap | +0.007 |
drift | +0.007 |
dives | +0.007 |
irm | +0.006 |
Neg logit contributions | |
mill | -0.007 |
ini | -0.007 |
painter | -0.007 |
ting | -0.007 |
office | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
dives | +0.017 |
drift | +0.017 |
nap | +0.016 |
irm | +0.016 |
much | +0.016 |
Neg logit contributions | |
ting | -0.022 |
painter | -0.020 |
mill | -0.019 |
office | -0.019 |
cut | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
mill | +0.011 |
ting | +0.011 |
ini | +0.011 |
painter | +0.011 |
cut | +0.010 |
Neg logit contributions | |
much | -0.006 |
nap | -0.006 |
drift | -0.006 |
dives | -0.006 |
irm | -0.006 |
Token | says |
Token ID | 1139 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
mill | +0.021 |
ting | +0.020 |
office | +0.019 |
painter | +0.019 |
paramed | +0.019 |
Neg logit contributions | |
ust | -0.017 |
much | -0.017 |
drift | -0.016 |
irm | -0.016 |
nap | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
drift | +0.051 |
much | +0.051 |
dives | +0.051 |
nap | +0.050 |
irm | +0.050 |
Neg logit contributions | |
ting | -0.093 |
mill | -0.093 |
painter | -0.090 |
ini | -0.088 |
paramed | -0.087 |
Token | " |
Token ID | 366 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ini | +0.094 |
mill | +0.089 |
ting | +0.088 |
cles | +0.087 |
floors | +0.086 |
Neg logit contributions | |
much | -0.081 |
drift | -0.078 |
nap | -0.077 |
dives | -0.074 |
OK | -0.073 |
Token | I |
Token ID | 40 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
mill | +0.301 |
ini | +0.282 |
office | +0.279 |
painter | +0.277 |
ting | +0.275 |
Neg logit contributions | |
nap | -0.448 |
drift | -0.436 |
much | -0.433 |
dives | -0.418 |
irm | -0.417 |
Token | am |
Token ID | 716 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
mill | +0.043 |
painter | +0.042 |
paramed | +0.041 |
ting | +0.041 |
ini | +0.040 |
Neg logit contributions | |
drift | -0.041 |
irm | -0.040 |
dives | -0.040 |
much | -0.039 |
ust | -0.039 |
Token | sorry |
Token ID | 7926 |
Feature activation | -7.61e-04 |
Pos logit contributions | |
ting | +0.113 |
mill | +0.113 |
painter | +0.110 |
paramed | +0.108 |
office | +0.107 |
Neg logit contributions | |
dives | -0.062 |
drift | -0.061 |
irm | -0.058 |
hops | -0.057 |
nap | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
irm | +0.001 |
drift | +0.001 |
dives | +0.001 |
ust | +0.001 |
nap | +0.001 |
Neg logit contributions | |
ting | -0.001 |
painter | -0.001 |
mill | -0.001 |
office | -0.001 |
Why | -0.001 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
ting | +0.092 |
mill | +0.092 |
painter | +0.088 |
paramed | +0.083 |
ter | +0.081 |
Neg logit contributions | |
irm | -0.069 |
dives | -0.069 |
much | -0.068 |
drift | -0.068 |
ust | -0.065 |
Token | about |
Token ID | 546 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
much | +0.047 |
drift | +0.047 |
dives | +0.046 |
nap | +0.046 |
irm | +0.045 |
Neg logit contributions | |
ting | -0.075 |
mill | -0.074 |
painter | -0.072 |
ini | -0.070 |
office | -0.068 |
Token | him |
Token ID | 683 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
mill | +0.005 |
ini | +0.005 |
ting | +0.005 |
painter | +0.005 |
paramed | +0.005 |
Neg logit contributions | |
much | -0.004 |
nap | -0.004 |
drift | -0.004 |
dives | -0.004 |
swim | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
much | +0.022 |
drift | +0.022 |
dives | +0.022 |
nap | +0.022 |
irm | +0.021 |
Neg logit contributions | |
ting | -0.036 |
mill | -0.036 |
painter | -0.034 |
ini | -0.034 |
office | -0.033 |
Token | he |
Token ID | 339 |
Feature activation | -5.51e-02 |
Pos logit contributions | |
mill | +0.094 |
ting | +0.093 |
painter | +0.090 |
ini | +0.089 |
paramed | +0.086 |
Neg logit contributions | |
much | -0.062 |
drift | -0.060 |
dives | -0.060 |
nap | -0.060 |
irm | -0.058 |
Token | said |
Token ID | 531 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
much | +0.078 |
drift | +0.077 |
dives | +0.077 |
nap | +0.077 |
irm | +0.076 |
Neg logit contributions | |
ting | -0.090 |
mill | -0.089 |
painter | -0.086 |
ini | -0.084 |
office | -0.081 |
Token | :" |
Token ID | 11097 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.050 |
drift | +0.049 |
dives | +0.049 |
nap | +0.049 |
irm | +0.047 |
Neg logit contributions | |
ting | -0.090 |
mill | -0.090 |
painter | -0.087 |
ini | -0.085 |
paramed | -0.083 |
Token | My |
Token ID | 3666 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ting | +0.267 |
mill | +0.262 |
painter | +0.248 |
ini | +0.242 |
paramed | +0.228 |
Neg logit contributions | |
much | -0.464 |
dives | -0.461 |
drift | -0.460 |
nap | -0.458 |
irm | -0.451 |
Token | name |
Token ID | 1438 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
much | +0.043 |
nap | +0.042 |
dives | +0.041 |
drift | +0.041 |
irm | +0.039 |
Neg logit contributions | |
ting | -0.056 |
mill | -0.054 |
ini | -0.052 |
painter | -0.052 |
paramed | -0.050 |
Token | is |
Token ID | 318 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.020 |
nap | +0.020 |
dives | +0.020 |
irm | +0.019 |
Neg logit contributions | |
mill | -0.033 |
ting | -0.033 |
painter | -0.032 |
ini | -0.031 |
paramed | -0.031 |
Token | L |
Token ID | 406 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
ting | +0.053 |
mill | +0.053 |
painter | +0.051 |
ini | +0.050 |
paramed | +0.049 |
Neg logit contributions | |
drift | -0.036 |
dives | -0.036 |
much | -0.036 |
irm | -0.036 |
nap | -0.036 |
Token | enny |
Token ID | 11870 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
ting | +0.028 |
mill | +0.028 |
painter | +0.027 |
ini | +0.027 |
paramed | +0.026 |
Neg logit contributions | |
much | -0.018 |
drift | -0.018 |
dives | -0.018 |
nap | -0.018 |
irm | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
mill | +0.052 |
ting | +0.052 |
painter | +0.050 |
ini | +0.048 |
office | +0.048 |
Neg logit contributions | |
dives | -0.039 |
drift | -0.039 |
irm | -0.039 |
much | -0.039 |
nap | -0.039 |
Token | � |
Token ID | 6184 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.032 |
dives | +0.032 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
ting | -0.049 |
mill | -0.049 |
painter | -0.047 |
ini | -0.046 |
office | -0.045 |
Token | � |
Token ID | 95 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
much | +0.041 |
drift | +0.040 |
dives | +0.040 |
nap | +0.040 |
irm | +0.039 |
Neg logit contributions | |
ting | -0.045 |
mill | -0.044 |
painter | -0.042 |
ini | -0.042 |
paramed | -0.040 |
Token | € |
Token ID | 26391 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
mill | +0.077 |
ting | +0.077 |
painter | +0.072 |
ini | +0.070 |
cut | +0.070 |
Neg logit contributions | |
much | -0.065 |
irm | -0.062 |
drift | -0.061 |
dives | -0.061 |
nap | -0.061 |
Token | � |
Token ID | 447 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
much | +0.018 |
dives | +0.017 |
drift | +0.017 |
nap | +0.017 |
irm | +0.017 |
Neg logit contributions | |
ting | -0.023 |
mill | -0.023 |
painter | -0.022 |
ini | -0.022 |
paramed | -0.021 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.025 |
nap | +0.023 |
drift | +0.022 |
irm | +0.022 |
dives | +0.021 |
Neg logit contributions | |
ting | -0.045 |
mill | -0.044 |
painter | -0.044 |
floors | -0.043 |
ini | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
mill | +0.287 |
ting | +0.274 |
painter | +0.258 |
ini | +0.247 |
office | +0.247 |
Neg logit contributions | |
much | -0.457 |
drift | -0.433 |
nap | -0.433 |
irm | -0.432 |
ust | -0.430 |
Token | always |
Token ID | 1464 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
ting | +0.085 |
mill | +0.084 |
ini | +0.081 |
painter | +0.080 |
paramed | +0.078 |
Neg logit contributions | |
much | -0.052 |
nap | -0.051 |
drift | -0.051 |
dives | -0.049 |
irm | -0.048 |
Token | be |
Token ID | 307 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
ls | +0.009 |
dives | +0.009 |
much | +0.009 |
drift | +0.009 |
irm | +0.009 |
Neg logit contributions | |
mill | -0.015 |
ting | -0.015 |
painter | -0.015 |
office | -0.015 |
ini | -0.014 |
Token | careful |
Token ID | 8161 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
mill | +0.016 |
ting | +0.016 |
painter | +0.015 |
ini | +0.015 |
rom | +0.015 |
Neg logit contributions | |
much | -0.009 |
dives | -0.008 |
drift | -0.008 |
irm | -0.008 |
nap | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
mill | +0.090 |
ting | +0.089 |
painter | +0.085 |
ini | +0.084 |
laund | +0.083 |
Neg logit contributions | |
much | -0.053 |
drift | -0.048 |
nap | -0.047 |
dives | -0.047 |
irm | -0.046 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ting | +0.009 |
mill | +0.009 |
ini | +0.009 |
painter | +0.008 |
rom | +0.008 |
Neg logit contributions | |
nap | -0.007 |
much | -0.007 |
dives | -0.007 |
drift | -0.007 |
irm | -0.006 |
Token | � |
Token ID | 6184 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
mill | +0.036 |
ini | +0.035 |
ting | +0.035 |
painter | +0.035 |
paramed | +0.034 |
Neg logit contributions | |
much | -0.018 |
nap | -0.017 |
drift | -0.016 |
dives | -0.015 |
irm | -0.015 |
Token | � |
Token ID | 95 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.032 |
dives | +0.032 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
ting | -0.034 |
mill | -0.034 |
painter | -0.033 |
ini | -0.032 |
paramed | -0.031 |
Token | € |
Token ID | 26391 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
mill | +0.076 |
ting | +0.074 |
painter | +0.070 |
ini | +0.068 |
floors | +0.068 |
Neg logit contributions | |
much | -0.078 |
irm | -0.075 |
dives | -0.074 |
nap | -0.074 |
drift | -0.074 |
Token | � |
Token ID | 447 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
much | +0.019 |
dives | +0.019 |
drift | +0.019 |
nap | +0.019 |
irm | +0.018 |
Neg logit contributions | |
ting | -0.023 |
mill | -0.023 |
painter | -0.022 |
ini | -0.021 |
paramed | -0.021 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.019 |
nap | +0.017 |
drift | +0.017 |
dives | +0.017 |
irm | +0.016 |
Neg logit contributions | |
ting | -0.042 |
mill | -0.040 |
painter | -0.040 |
ini | -0.039 |
keeping | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
mill | +0.305 |
ting | +0.292 |
painter | +0.276 |
office | +0.271 |
ini | +0.268 |
Neg logit contributions | |
much | -0.440 |
nap | -0.415 |
ust | -0.413 |
irm | -0.413 |
drift | -0.412 |
Token | 's |
Token ID | 338 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
nap | +0.020 |
drift | +0.019 |
irm | +0.019 |
dives | +0.019 |
much | +0.019 |
Neg logit contributions | |
ting | -0.027 |
mill | -0.027 |
painter | -0.026 |
ini | -0.026 |
cut | -0.026 |
Token | easy |
Token ID | 2562 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
dives | +0.023 |
drift | +0.022 |
nap | +0.021 |
ls | +0.021 |
irm | +0.021 |
Neg logit contributions | |
mill | -0.051 |
ting | -0.050 |
painter | -0.049 |
office | -0.048 |
paramed | -0.047 |
Token | then |
Token ID | 788 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
much | +0.015 |
nap | +0.014 |
dives | +0.014 |
drift | +0.014 |
irm | +0.013 |
Neg logit contributions | |
ting | -0.026 |
mill | -0.026 |
ini | -0.025 |
painter | -0.025 |
paramed | -0.024 |
Token | !" |
Token ID | 2474 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
ting | +0.045 |
mill | +0.045 |
painter | +0.043 |
ini | +0.043 |
office | +0.042 |
Neg logit contributions | |
much | -0.029 |
drift | -0.028 |
dives | -0.028 |
nap | -0.028 |
irm | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
much | +0.005 |
nap | +0.005 |
drift | +0.004 |
irm | +0.004 |
swim | +0.004 |
Neg logit contributions | |
mill | -0.010 |
ini | -0.009 |
painter | -0.009 |
laund | -0.009 |
cut | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
dives | +0.044 |
drift | +0.041 |
dive | +0.041 |
irm | +0.040 |
ust | +0.040 |
Neg logit contributions | |
ting | -0.044 |
painter | -0.040 |
cut | -0.040 |
office | -0.039 |
mill | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | +9.88e-04 |
Pos logit contributions | |
mill | +0.013 |
ting | +0.013 |
painter | +0.013 |
ini | +0.013 |
paramed | +0.012 |
Neg logit contributions | |
much | -0.006 |
drift | -0.006 |
dives | -0.006 |
nap | -0.006 |
irm | -0.006 |
Token | says |
Token ID | 1139 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
mill | +0.002 |
ting | +0.002 |
office | +0.002 |
painter | +0.001 |
paramed | +0.001 |
Neg logit contributions | |
ust | -0.001 |
much | -0.001 |
drift | -0.001 |
irm | -0.001 |
ver | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
much | +0.049 |
drift | +0.049 |
dives | +0.048 |
nap | +0.048 |
irm | +0.047 |
Neg logit contributions | |
ting | -0.095 |
mill | -0.095 |
painter | -0.092 |
ini | -0.090 |
paramed | -0.088 |
Token | " |
Token ID | 366 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ting | +0.187 |
mill | +0.187 |
ini | +0.179 |
painter | +0.178 |
office | +0.171 |
Neg logit contributions | |
much | -0.132 |
drift | -0.128 |
dives | -0.128 |
nap | -0.128 |
irm | -0.122 |
Token | I |
Token ID | 40 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
mill | +0.260 |
ting | +0.257 |
painter | +0.241 |
ini | +0.235 |
office | +0.224 |
Neg logit contributions | |
much | -0.475 |
drift | -0.470 |
nap | -0.468 |
dives | -0.468 |
irm | -0.461 |
Token | am |
Token ID | 716 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
mill | +0.040 |
paramed | +0.039 |
painter | +0.038 |
ini | +0.037 |
ting | +0.036 |
Neg logit contributions | |
drift | -0.043 |
irm | -0.043 |
ls | -0.043 |
dives | -0.043 |
ust | -0.042 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
ting | +0.110 |
mill | +0.110 |
painter | +0.107 |
paramed | +0.106 |
office | +0.105 |
Neg logit contributions | |
dives | -0.061 |
drift | -0.059 |
irm | -0.057 |
ust | -0.057 |
nap | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
drift | +0.002 |
dives | +0.002 |
irm | +0.002 |
nap | +0.002 |
ust | +0.002 |
Neg logit contributions | |
ting | -0.003 |
painter | -0.003 |
mill | -0.003 |
office | -0.003 |
ini | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ting | +0.101 |
mill | +0.101 |
painter | +0.097 |
ini | +0.096 |
paramed | +0.093 |
Neg logit contributions | |
much | -0.057 |
drift | -0.056 |
dives | -0.055 |
nap | -0.055 |
irm | -0.053 |
Token | rocked |
Token ID | 36872 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
much | +0.047 |
ust | +0.047 |
dives | +0.044 |
irm | +0.044 |
nap | +0.043 |
Neg logit contributions | |
ting | -0.065 |
mill | -0.061 |
painter | -0.058 |
cut | -0.057 |
pavement | -0.056 |
Token | � |
Token ID | 6184 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
much | +0.050 |
drift | +0.041 |
nap | +0.041 |
irm | +0.038 |
dives | +0.037 |
Neg logit contributions | |
mill | -0.125 |
painter | -0.121 |
ini | -0.120 |
paramed | -0.116 |
office | -0.115 |
Token | � |
Token ID | 95 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
much | +0.048 |
dives | +0.046 |
drift | +0.046 |
ls | +0.046 |
nap | +0.045 |
Neg logit contributions | |
ting | -0.049 |
mill | -0.049 |
painter | -0.046 |
paramed | -0.045 |
rom | -0.045 |
Token | € |
Token ID | 26391 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
mill | +0.074 |
ting | +0.073 |
painter | +0.070 |
ini | +0.069 |
cut | +0.067 |
Neg logit contributions | |
much | -0.065 |
dives | -0.064 |
drift | -0.064 |
nap | -0.063 |
irm | -0.063 |
Token | � |
Token ID | 447 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
drift | +0.019 |
dives | +0.019 |
nap | +0.019 |
irm | +0.019 |
much | +0.019 |
Neg logit contributions | |
mill | -0.026 |
ting | -0.026 |
painter | -0.025 |
ini | -0.025 |
office | -0.025 |
Token | � |
Token ID | 250 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
much | +0.028 |
drift | +0.028 |
nap | +0.027 |
dives | +0.027 |
irm | +0.027 |
Neg logit contributions | |
ting | -0.036 |
mill | -0.036 |
painter | -0.035 |
ini | -0.035 |
office | -0.033 |
Token | higher |
Token ID | 2440 |
Feature activation | -7.22e-02 |
Pos logit contributions | |
mill | +0.298 |
ting | +0.297 |
painter | +0.281 |
ini | +0.275 |
paramed | +0.262 |
Neg logit contributions | |
much | -0.430 |
drift | -0.425 |
dives | -0.424 |
nap | -0.422 |
irm | -0.415 |
Token | and |
Token ID | 290 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
much | +0.086 |
drift | +0.084 |
dives | +0.084 |
nap | +0.084 |
irm | +0.081 |
Neg logit contributions | |
ting | -0.134 |
mill | -0.134 |
painter | -0.129 |
ini | -0.128 |
paramed | -0.124 |
Token | higher |
Token ID | 2440 |
Feature activation | -7.32e-02 |
Pos logit contributions | |
much | +0.040 |
nap | +0.039 |
drift | +0.039 |
dives | +0.039 |
irm | +0.039 |
Neg logit contributions | |
ting | -0.066 |
mill | -0.065 |
painter | -0.062 |
ini | -0.061 |
cut | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-04 |
Pos logit contributions | |
much | +0.088 |
drift | +0.086 |
dives | +0.086 |
nap | +0.085 |
irm | +0.083 |
Neg logit contributions | |
ting | -0.135 |
mill | -0.135 |
painter | -0.130 |
ini | -0.129 |
paramed | -0.125 |
Token | His |
Token ID | 2399 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
much | +0.001 |
drift | +0.001 |
dives | +0.001 |
nap | +0.001 |
irm | +0.001 |
Neg logit contributions | |
ting | -0.001 |
mill | -0.001 |
painter | -0.001 |
ini | -0.001 |
paramed | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
dives | +0.025 |
drift | +0.024 |
nap | +0.024 |
much | +0.024 |
irm | +0.024 |
Neg logit contributions | |
ting | -0.037 |
mill | -0.036 |
painter | -0.035 |
cut | -0.034 |
ini | -0.034 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
dives | +0.037 |
drift | +0.037 |
much | +0.036 |
irm | +0.036 |
nap | +0.036 |
Neg logit contributions | |
mill | -0.041 |
ting | -0.041 |
painter | -0.040 |
ini | -0.039 |
office | -0.038 |
Token | my |
Token ID | 1820 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
mill | +0.150 |
ting | +0.142 |
painter | +0.134 |
ini | +0.133 |
laund | +0.132 |
Neg logit contributions | |
much | -0.174 |
drift | -0.169 |
nap | -0.165 |
irm | -0.158 |
ust | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | -4.75e-03 |
Pos logit contributions | |
ting | +0.053 |
mill | +0.053 |
painter | +0.051 |
ini | +0.050 |
paramed | +0.049 |
Neg logit contributions | |
dives | -0.032 |
much | -0.032 |
nap | -0.031 |
drift | -0.031 |
irm | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
much | +0.007 |
drift | +0.006 |
nap | +0.006 |
dives | +0.006 |
irm | +0.006 |
Neg logit contributions | |
ini | -0.008 |
mill | -0.008 |
ting | -0.008 |
painter | -0.008 |
cut | -0.007 |
Token | Looks |
Token ID | 41102 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
mill | +0.330 |
office | +0.314 |
ting | +0.306 |
painter | +0.291 |
cles | +0.291 |
Neg logit contributions | |
much | -0.393 |
ust | -0.377 |
drift | -0.351 |
irm | -0.351 |
nap | -0.347 |
Token | like |
Token ID | 588 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
drift | +0.266 |
nap | +0.256 |
ls | +0.256 |
dives | +0.252 |
dive | +0.247 |
Neg logit contributions | |
ting | -0.291 |
painter | -0.275 |
mill | -0.273 |
pavement | -0.264 |
floors | -0.264 |
Token | the |
Token ID | 262 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
ting | +0.078 |
ini | +0.076 |
mill | +0.075 |
cut | +0.074 |
rom | +0.073 |
Neg logit contributions | |
much | -0.050 |
nap | -0.048 |
dives | -0.047 |
drift | -0.046 |
dive | -0.045 |
Token | wave |
Token ID | 6769 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
ting | +0.080 |
mill | +0.079 |
painter | +0.075 |
ini | +0.074 |
paramed | +0.071 |
Neg logit contributions | |
much | -0.103 |
drift | -0.102 |
dives | -0.102 |
nap | -0.101 |
irm | -0.099 |
Token | destroyed |
Token ID | 6572 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
much | +0.069 |
drift | +0.069 |
dives | +0.068 |
nap | +0.068 |
irm | +0.068 |
Neg logit contributions | |
ting | -0.111 |
mill | -0.111 |
painter | -0.107 |
ini | -0.105 |
office | -0.102 |
Token | all |
Token ID | 477 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ting | +0.140 |
mill | +0.139 |
painter | +0.139 |
ini | +0.138 |
paramed | +0.137 |
Neg logit contributions | |
much | -0.092 |
nap | -0.089 |
dives | -0.087 |
drift | -0.086 |
dive | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
ust | +0.044 |
dives | +0.042 |
nap | +0.042 |
drift | +0.042 |
ares | +0.041 |
Neg logit contributions | |
ting | -0.052 |
mill | -0.049 |
painter | -0.046 |
paramed | -0.045 |
Why | -0.044 |
Token | owner |
Token ID | 4870 |
Feature activation | +8.02e-02 |
Pos logit contributions | |
ting | +0.079 |
mill | +0.078 |
ini | +0.075 |
painter | +0.075 |
rom | +0.072 |
Neg logit contributions | |
nap | -0.100 |
much | -0.100 |
drift | -0.097 |
dives | -0.097 |
irm | -0.095 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
ting | +0.127 |
mill | +0.122 |
painter | +0.122 |
paramed | +0.117 |
ini | +0.116 |
Neg logit contributions | |
dives | -0.118 |
drift | -0.117 |
much | -0.115 |
irm | -0.115 |
nap | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | -7.45e-03 |
Pos logit contributions | |
ting | +0.011 |
painter | +0.010 |
mill | +0.010 |
ini | +0.010 |
ter | +0.010 |
Neg logit contributions | |
dives | -0.009 |
nap | -0.009 |
drift | -0.009 |
dive | -0.009 |
hops | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
much | +0.010 |
drift | +0.010 |
dives | +0.009 |
nap | +0.009 |
irm | +0.009 |
Neg logit contributions | |
mill | -0.013 |
ting | -0.013 |
painter | -0.013 |
ini | -0.013 |
paramed | -0.012 |
Token | Looks |
Token ID | 41102 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
mill | +0.267 |
ting | +0.255 |
painter | +0.241 |
office | +0.238 |
ini | +0.233 |
Neg logit contributions | |
much | -0.445 |
drift | -0.431 |
nap | -0.427 |
dives | -0.425 |
irm | -0.421 |
Token | like |
Token ID | 588 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ls | +0.311 |
drift | +0.311 |
dive | +0.298 |
nap | +0.296 |
ust | +0.291 |
Neg logit contributions | |
ting | -0.241 |
pavement | -0.215 |
painter | -0.211 |
floors | -0.198 |
Why | -0.196 |
Token | you |
Token ID | 345 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
ting | +0.074 |
mill | +0.073 |
painter | +0.071 |
ini | +0.068 |
office | +0.067 |
Neg logit contributions | |
drift | -0.051 |
dives | -0.051 |
much | -0.051 |
irm | -0.050 |
nap | -0.050 |
Token | two |
Token ID | 734 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
much | +0.070 |
nap | +0.067 |
drift | +0.066 |
dives | +0.065 |
irm | +0.062 |
Neg logit contributions | |
mill | -0.131 |
ting | -0.129 |
ini | -0.125 |
painter | -0.125 |
office | -0.121 |
Token | are |
Token ID | 389 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
irm | +0.089 |
dives | +0.088 |
drift | +0.088 |
ust | +0.086 |
much | +0.085 |
Neg logit contributions | |
ting | -0.109 |
mill | -0.104 |
painter | -0.099 |
ini | -0.096 |
paramed | -0.096 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ting | +0.044 |
mill | +0.042 |
painter | +0.041 |
paramed | +0.039 |
ini | +0.039 |
Neg logit contributions | |
dives | -0.038 |
irm | -0.038 |
drift | -0.037 |
nap | -0.036 |
ust | -0.036 |
Token | print |
Token ID | 3601 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
much | +0.085 |
drift | +0.084 |
dives | +0.083 |
irm | +0.083 |
ust | +0.083 |
Neg logit contributions | |
ting | -0.115 |
mill | -0.114 |
office | -0.106 |
painter | -0.106 |
ini | -0.104 |
Token | so |
Token ID | 523 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
much | +0.028 |
nap | +0.027 |
drift | +0.026 |
dives | +0.026 |
irm | +0.025 |
Neg logit contributions | |
mill | -0.048 |
ting | -0.047 |
painter | -0.046 |
ini | -0.046 |
paramed | -0.044 |
Token | badly |
Token ID | 11234 |
Feature activation | -3.59e-03 |
Pos logit contributions | |
much | +0.046 |
drift | +0.044 |
dives | +0.044 |
nap | +0.044 |
irm | +0.043 |
Neg logit contributions | |
ting | -0.093 |
mill | -0.093 |
painter | -0.090 |
ini | -0.089 |
paramed | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
much | +0.004 |
drift | +0.004 |
dives | +0.004 |
nap | +0.004 |
irm | +0.004 |
Neg logit contributions | |
ting | -0.007 |
mill | -0.007 |
painter | -0.006 |
ini | -0.006 |
office | -0.006 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
much | +0.005 |
irm | +0.005 |
drift | +0.005 |
nap | +0.005 |
dives | +0.005 |
Neg logit contributions | |
ini | -0.010 |
cut | -0.010 |
painter | -0.010 |
ting | -0.010 |
mill | -0.010 |
Token | ust |
Token ID | 436 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
drift | +0.012 |
dives | +0.012 |
nap | +0.011 |
much | +0.011 |
hops | +0.010 |
Neg logit contributions | |
mill | -0.039 |
ini | -0.038 |
ting | -0.038 |
painter | -0.038 |
rom | -0.037 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
nap | +0.270 |
much | +0.261 |
drift | +0.258 |
dives | +0.257 |
irm | +0.249 |
Neg logit contributions | |
mill | -0.295 |
ting | -0.292 |
cut | -0.287 |
ini | -0.284 |
painter | -0.280 |
Token | tears |
Token ID | 10953 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
much | +0.013 |
dives | +0.012 |
drift | +0.012 |
nap | +0.012 |
irm | +0.011 |
Neg logit contributions | |
mill | -0.026 |
ting | -0.026 |
painter | -0.025 |
ini | -0.025 |
paramed | -0.024 |
Token | were |
Token ID | 547 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
much | +0.054 |
drift | +0.053 |
dives | +0.053 |
nap | +0.053 |
irm | +0.052 |
Neg logit contributions | |
ting | -0.080 |
mill | -0.080 |
painter | -0.077 |
ini | -0.076 |
paramed | -0.074 |
Token | well |
Token ID | 880 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
ini | +0.044 |
ting | +0.044 |
painter | +0.044 |
mill | +0.044 |
smith | +0.043 |
Neg logit contributions | |
much | -0.026 |
drift | -0.021 |
nap | -0.021 |
okay | -0.021 |
irm | -0.020 |
Token | ing |
Token ID | 278 |
Feature activation | -7.26e-04 |
Pos logit contributions | |
dives | +0.043 |
drift | +0.042 |
much | +0.042 |
irm | +0.042 |
nap | +0.042 |
Neg logit contributions | |
ting | -0.060 |
mill | -0.058 |
painter | -0.054 |
office | -0.054 |
ini | -0.052 |
Token | laughed |
Token ID | 13818 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
mill | +0.056 |
ini | +0.054 |
ting | +0.054 |
pavement | +0.052 |
office | +0.052 |
Neg logit contributions | |
much | -0.033 |
drift | -0.033 |
dives | -0.032 |
nap | -0.032 |
swim | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
dives | +0.051 |
drift | +0.050 |
nap | +0.050 |
irm | +0.049 |
dive | +0.049 |
Neg logit contributions | |
ting | -0.057 |
mill | -0.052 |
painter | -0.051 |
Why | -0.049 |
paramed | -0.048 |
Token | said |
Token ID | 531 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.032 |
dives | +0.032 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
mill | -0.055 |
ting | -0.054 |
painter | -0.052 |
ini | -0.052 |
office | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +4.82e-02 |
Pos logit contributions | |
much | +0.046 |
nap | +0.041 |
dives | +0.041 |
drift | +0.041 |
dive | +0.037 |
Neg logit contributions | |
mill | -0.095 |
ting | -0.094 |
ini | -0.094 |
painter | -0.091 |
office | -0.090 |
Token | " |
Token ID | 366 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ini | +0.076 |
mill | +0.074 |
ting | +0.071 |
keeping | +0.071 |
painter | +0.070 |
Neg logit contributions | |
much | -0.075 |
drift | -0.073 |
dives | -0.069 |
nap | -0.069 |
swim | -0.067 |
Token | Looks |
Token ID | 41102 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
mill | +0.328 |
office | +0.302 |
ting | +0.289 |
painter | +0.283 |
cut | +0.279 |
Neg logit contributions | |
much | -0.406 |
drift | -0.386 |
ust | -0.385 |
nap | -0.381 |
irm | -0.378 |
Token | like |
Token ID | 588 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
drift | +0.307 |
ls | +0.305 |
dive | +0.291 |
ust | +0.286 |
nap | +0.286 |
Neg logit contributions | |
ting | -0.241 |
painter | -0.222 |
pavement | -0.216 |
floors | -0.207 |
mill | -0.203 |
Token | that |
Token ID | 326 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
mill | +0.078 |
ting | +0.078 |
ini | +0.075 |
painter | +0.075 |
paramed | +0.073 |
Neg logit contributions | |
much | -0.049 |
nap | -0.048 |
drift | -0.047 |
dives | -0.047 |
irm | -0.045 |
Token | apple |
Token ID | 17180 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
mill | +0.046 |
ting | +0.045 |
painter | +0.045 |
ini | +0.043 |
office | +0.042 |
Neg logit contributions | |
dives | -0.033 |
drift | -0.033 |
irm | -0.033 |
much | -0.032 |
nap | -0.032 |
Token | made |
Token ID | 925 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
mill | +0.034 |
ting | +0.034 |
painter | +0.033 |
ini | +0.032 |
office | +0.031 |
Neg logit contributions | |
drift | -0.023 |
irm | -0.023 |
dives | -0.023 |
much | -0.023 |
nap | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
ting | +0.066 |
mill | +0.064 |
painter | +0.062 |
ini | +0.061 |
office | +0.059 |
Neg logit contributions | |
dives | -0.056 |
drift | -0.056 |
irm | -0.055 |
nap | -0.054 |
much | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
mill | +0.058 |
ting | +0.056 |
cut | +0.055 |
ini | +0.053 |
painter | +0.051 |
Neg logit contributions | |
irm | -0.076 |
nap | -0.075 |
much | -0.074 |
ust | -0.073 |
dives | -0.072 |
Token | too |
Token ID | 1165 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
mill | +0.061 |
ting | +0.060 |
painter | +0.057 |
cut | +0.056 |
paramed | +0.055 |
Neg logit contributions | |
dives | -0.040 |
nap | -0.039 |
drift | -0.039 |
irm | -0.039 |
ls | -0.038 |
Token | strong |
Token ID | 1913 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
nap | +0.114 |
drift | +0.113 |
dives | +0.112 |
irm | +0.112 |
hops | +0.109 |
Neg logit contributions | |
mill | -0.170 |
painter | -0.152 |
ini | -0.151 |
ting | -0.145 |
cut | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | -4.03e-03 |
Pos logit contributions | |
ting | +0.027 |
mill | +0.024 |
painter | +0.023 |
office | +0.022 |
cut | +0.022 |
Neg logit contributions | |
dives | -0.021 |
drift | -0.020 |
irm | -0.020 |
ust | -0.020 |
nap | -0.020 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
drift | +0.005 |
much | +0.005 |
dives | +0.005 |
nap | +0.005 |
irm | +0.005 |
Neg logit contributions | |
ting | -0.007 |
mill | -0.007 |
painter | -0.007 |
ini | -0.006 |
office | -0.006 |
Token | ust |
Token ID | 436 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
drift | +0.014 |
nap | +0.013 |
dives | +0.012 |
hops | +0.011 |
irm | +0.011 |
Neg logit contributions | |
ini | -0.034 |
painter | -0.032 |
mill | -0.032 |
years | -0.031 |
rom | -0.031 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
nap | +0.288 |
irm | +0.270 |
much | +0.267 |
drift | +0.265 |
dives | +0.263 |
Neg logit contributions | |
cut | -0.283 |
mill | -0.271 |
ting | -0.267 |
ini | -0.263 |
ter | -0.256 |
Token | , |
Token ID | 11 |
Feature activation | +5.25e-02 |
Pos logit contributions | |
much | +0.011 |
drift | +0.011 |
dives | +0.011 |
nap | +0.011 |
irm | +0.011 |
Neg logit contributions | |
ting | -0.021 |
mill | -0.021 |
painter | -0.020 |
ini | -0.020 |
office | -0.019 |
Token | he |
Token ID | 339 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
ting | +0.115 |
mill | +0.115 |
painter | +0.110 |
office | +0.105 |
ini | +0.105 |
Neg logit contributions | |
irm | -0.047 |
drift | -0.045 |
ust | -0.045 |
nap | -0.044 |
dives | -0.044 |
Token | started |
Token ID | 2067 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
much | +0.092 |
nap | +0.091 |
drift | +0.089 |
irm | +0.088 |
dives | +0.087 |
Neg logit contributions | |
ting | -0.095 |
mill | -0.095 |
painter | -0.089 |
ini | -0.086 |
cut | -0.086 |
Token | to |
Token ID | 284 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
mill | +0.089 |
ting | +0.088 |
painter | +0.084 |
office | +0.081 |
paramed | +0.080 |
Neg logit contributions | |
much | -0.077 |
nap | -0.076 |
ust | -0.076 |
irm | -0.075 |
dives | -0.075 |
Token | back |
Token ID | 736 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
dives | +0.026 |
drift | +0.026 |
hops | +0.025 |
irm | +0.024 |
dive | +0.024 |
Neg logit contributions | |
ting | -0.029 |
mill | -0.028 |
office | -0.027 |
painter | -0.027 |
ini | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
ting | +0.062 |
mill | +0.062 |
painter | +0.059 |
ini | +0.059 |
paramed | +0.057 |
Neg logit contributions | |
much | -0.035 |
drift | -0.034 |
dives | -0.034 |
nap | -0.034 |
irm | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
much | +0.003 |
drift | +0.003 |
dives | +0.003 |
nap | +0.003 |
irm | +0.003 |
Neg logit contributions | |
ting | -0.007 |
mill | -0.007 |
ini | -0.006 |
painter | -0.006 |
paramed | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
much | +0.051 |
drift | +0.050 |
dives | +0.050 |
nap | +0.050 |
irm | +0.048 |
Neg logit contributions | |
mill | -0.109 |
ting | -0.109 |
painter | -0.106 |
ini | -0.104 |
paramed | -0.102 |
Token | Fr |
Token ID | 6732 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
much | +0.081 |
ust | +0.073 |
dives | +0.070 |
nap | +0.070 |
drift | +0.069 |
Neg logit contributions | |
ting | -0.089 |
mill | -0.086 |
ini | -0.082 |
painter | -0.080 |
office | -0.078 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.003 |
nap | +0.003 |
dives | +0.003 |
hops | +0.002 |
much | +0.002 |
Neg logit contributions | |
mill | -0.017 |
ini | -0.017 |
painter | -0.017 |
ting | -0.017 |
rom | -0.017 |
Token | rated |
Token ID | 4111 |
Feature activation | -9.89e-03 |
Pos logit contributions | |
nap | +0.261 |
drift | +0.250 |
much | +0.248 |
dives | +0.245 |
irm | +0.241 |
Neg logit contributions | |
mill | -0.301 |
ting | -0.298 |
painter | -0.293 |
cut | -0.291 |
ini | -0.289 |
Token | , |
Token ID | 11 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
much | +0.010 |
dives | +0.010 |
drift | +0.009 |
nap | +0.009 |
irm | +0.009 |
Neg logit contributions | |
mill | -0.020 |
ting | -0.020 |
painter | -0.020 |
ini | -0.020 |
paramed | -0.019 |
Token | Jane |
Token ID | 12091 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
mill | +0.087 |
ting | +0.087 |
painter | +0.084 |
ini | +0.081 |
paramed | +0.079 |
Neg logit contributions | |
dives | -0.068 |
drift | -0.068 |
much | -0.068 |
nap | -0.067 |
irm | -0.066 |
Token | went |
Token ID | 1816 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
much | +0.029 |
drift | +0.029 |
dives | +0.028 |
nap | +0.028 |
irm | +0.027 |
Neg logit contributions | |
mill | -0.043 |
ting | -0.042 |
ini | -0.041 |
painter | -0.041 |
paramed | -0.040 |
Token | back |
Token ID | 736 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
much | +0.050 |
dives | +0.049 |
drift | +0.049 |
nap | +0.048 |
irm | +0.047 |
Neg logit contributions | |
mill | -0.071 |
ting | -0.071 |
painter | -0.069 |
ini | -0.068 |
paramed | -0.066 |
Token | but |
Token ID | 475 |
Feature activation | +9.68e-03 |
Pos logit contributions | |
ting | +0.095 |
mill | +0.094 |
painter | +0.091 |
ini | +0.089 |
office | +0.087 |
Neg logit contributions | |
much | -0.051 |
dives | -0.050 |
drift | -0.050 |
nap | -0.050 |
irm | -0.049 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ting | +0.018 |
mill | +0.018 |
painter | +0.016 |
cut | +0.016 |
office | +0.016 |
Neg logit contributions | |
drift | -0.012 |
dives | -0.012 |
irm | -0.012 |
nap | -0.012 |
much | -0.011 |
Token | 't |
Token ID | 470 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
ting | +0.149 |
mill | +0.149 |
painter | +0.132 |
Why | +0.131 |
rom | +0.131 |
Neg logit contributions | |
irm | -0.188 |
ust | -0.179 |
dives | -0.179 |
drift | -0.173 |
nap | -0.173 |
Token | . |
Token ID | 13 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
irm | +0.077 |
dives | +0.077 |
much | +0.075 |
ls | +0.073 |
drift | +0.073 |
Neg logit contributions | |
ting | -0.100 |
mill | -0.099 |
painter | -0.098 |
office | -0.090 |
ini | -0.089 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
much | +0.007 |
dives | +0.007 |
drift | +0.007 |
nap | +0.007 |
irm | +0.007 |
Neg logit contributions | |
ting | -0.016 |
mill | -0.016 |
painter | -0.016 |
ini | -0.016 |
paramed | -0.015 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.011 |
dives | +0.010 |
nap | +0.010 |
much | +0.010 |
hops | +0.009 |
Neg logit contributions | |
ini | -0.030 |
mill | -0.029 |
painter | -0.028 |
ting | -0.028 |
cut | -0.028 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
nap | +0.281 |
drift | +0.261 |
dives | +0.260 |
much | +0.259 |
irm | +0.258 |
Neg logit contributions | |
cut | -0.281 |
mill | -0.274 |
ting | -0.273 |
ini | -0.267 |
painter | -0.258 |
Token | , |
Token ID | 11 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
drift | +0.013 |
nap | +0.013 |
dives | +0.013 |
irm | +0.013 |
much | +0.013 |
Neg logit contributions | |
ting | -0.019 |
mill | -0.019 |
painter | -0.018 |
ini | -0.017 |
office | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
ting | +0.110 |
mill | +0.110 |
painter | +0.105 |
office | +0.101 |
cut | +0.100 |
Neg logit contributions | |
irm | -0.037 |
ust | -0.036 |
dives | -0.035 |
drift | -0.035 |
nap | -0.035 |
Token | started |
Token ID | 2067 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
much | +0.094 |
drift | +0.092 |
nap | +0.091 |
dives | +0.091 |
irm | +0.090 |
Neg logit contributions | |
mill | -0.101 |
ting | -0.101 |
painter | -0.096 |
ini | -0.093 |
office | -0.091 |
Token | to |
Token ID | 284 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ting | +0.103 |
mill | +0.103 |
ini | +0.101 |
painter | +0.099 |
cut | +0.096 |
Neg logit contributions | |
much | -0.063 |
drift | -0.062 |
nap | -0.061 |
dives | -0.061 |
irm | -0.058 |
Token | or |
Token ID | 393 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.020 |
nap | +0.020 |
dives | +0.019 |
irm | +0.019 |
Neg logit contributions | |
mill | -0.034 |
ting | -0.033 |
painter | -0.033 |
ini | -0.033 |
paramed | -0.032 |
Token | too |
Token ID | 1165 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
dives | +0.020 |
much | +0.020 |
nap | +0.020 |
drift | +0.020 |
irm | +0.019 |
Neg logit contributions | |
ting | -0.034 |
mill | -0.033 |
painter | -0.031 |
cut | -0.031 |
ini | -0.031 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
dives | +0.112 |
irm | +0.112 |
drift | +0.107 |
ares | +0.105 |
nap | +0.104 |
Neg logit contributions | |
mill | -0.172 |
ting | -0.164 |
painter | -0.158 |
ini | -0.156 |
cut | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
dives | +0.022 |
irm | +0.022 |
drift | +0.021 |
nap | +0.021 |
much | +0.021 |
Neg logit contributions | |
ting | -0.031 |
mill | -0.030 |
painter | -0.028 |
office | -0.028 |
ini | -0.027 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
much | +0.008 |
nap | +0.008 |
drift | +0.008 |
dives | +0.007 |
irm | +0.007 |
Neg logit contributions | |
ting | -0.015 |
mill | -0.015 |
painter | -0.015 |
ini | -0.015 |
paramed | -0.014 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.021 |
dives | +0.020 |
nap | +0.020 |
much | +0.020 |
irm | +0.019 |
Neg logit contributions | |
mill | -0.032 |
ting | -0.032 |
ini | -0.032 |
painter | -0.031 |
rom | -0.030 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
nap | +0.285 |
dives | +0.278 |
drift | +0.277 |
much | +0.277 |
irm | +0.274 |
Neg logit contributions | |
mill | -0.273 |
ting | -0.272 |
ini | -0.261 |
cut | -0.260 |
painter | -0.258 |
Token | , |
Token ID | 11 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
much | +0.010 |
dives | +0.010 |
drift | +0.009 |
nap | +0.009 |
irm | +0.009 |
Neg logit contributions | |
mill | -0.023 |
painter | -0.022 |
ting | -0.022 |
ini | -0.022 |
paramed | -0.022 |
Token | she |
Token ID | 673 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
mill | +0.096 |
ting | +0.095 |
ini | +0.094 |
painter | +0.092 |
paramed | +0.090 |
Neg logit contributions | |
much | -0.050 |
drift | -0.047 |
nap | -0.047 |
dives | -0.046 |
hops | -0.043 |
Token | kept |
Token ID | 4030 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
much | +0.076 |
drift | +0.075 |
dives | +0.074 |
nap | +0.074 |
irm | +0.073 |
Neg logit contributions | |
ting | -0.083 |
mill | -0.083 |
painter | -0.079 |
ini | -0.078 |
office | -0.075 |
Token | searching |
Token ID | 10342 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
ting | +0.118 |
mill | +0.114 |
painter | +0.108 |
office | +0.105 |
ini | +0.103 |
Neg logit contributions | |
much | -0.101 |
dives | -0.098 |
nap | -0.098 |
drift | -0.098 |
ust | -0.097 |
Token | he |
Token ID | 339 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
ting | +0.017 |
mill | +0.017 |
painter | +0.016 |
cut | +0.016 |
ini | +0.016 |
Neg logit contributions | |
drift | -0.012 |
dives | -0.012 |
nap | -0.012 |
much | -0.012 |
irm | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
drift | +0.095 |
dives | +0.093 |
nap | +0.091 |
much | +0.091 |
irm | +0.090 |
Neg logit contributions | |
mill | -0.097 |
ting | -0.095 |
painter | -0.093 |
ini | -0.090 |
cut | -0.088 |
Token | no |
Token ID | 645 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
much | +0.047 |
nap | +0.040 |
dives | +0.039 |
drift | +0.039 |
swim | +0.037 |
Neg logit contributions | |
ini | -0.105 |
mill | -0.105 |
ting | -0.104 |
painter | -0.101 |
laund | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | -9.08e-03 |
Pos logit contributions | |
mill | +0.010 |
ting | +0.010 |
painter | +0.010 |
ini | +0.010 |
paramed | +0.009 |
Neg logit contributions | |
much | -0.005 |
nap | -0.005 |
drift | -0.005 |
dives | -0.005 |
irm | -0.004 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
much | +0.011 |
dives | +0.011 |
drift | +0.011 |
nap | +0.011 |
irm | +0.011 |
Neg logit contributions | |
ting | -0.017 |
mill | -0.016 |
painter | -0.016 |
ini | -0.016 |
paramed | -0.015 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.014 |
nap | +0.013 |
dives | +0.012 |
much | +0.012 |
hops | +0.012 |
Neg logit contributions | |
ini | -0.035 |
mill | -0.033 |
painter | -0.033 |
ting | -0.033 |
rom | -0.032 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
nap | +0.281 |
drift | +0.265 |
much | +0.254 |
dives | +0.253 |
irm | +0.247 |
Neg logit contributions | |
cut | -0.287 |
mill | -0.280 |
ting | -0.280 |
ini | -0.274 |
painter | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
much | +0.012 |
drift | +0.012 |
dives | +0.012 |
nap | +0.012 |
irm | +0.011 |
Neg logit contributions | |
ting | -0.022 |
mill | -0.022 |
painter | -0.021 |
ini | -0.021 |
paramed | -0.020 |
Token | Bob |
Token ID | 5811 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
ting | +0.090 |
mill | +0.089 |
Why | +0.083 |
painter | +0.080 |
cut | +0.080 |
Neg logit contributions | |
irm | -0.065 |
ust | -0.062 |
nap | -0.061 |
drift | -0.060 |
dives | -0.060 |
Token | decided |
Token ID | 3066 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
drift | +0.029 |
much | +0.029 |
nap | +0.028 |
dives | +0.028 |
irm | +0.028 |
Neg logit contributions | |
mill | -0.033 |
ting | -0.033 |
painter | -0.032 |
paramed | -0.031 |
office | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
mill | +0.071 |
ini | +0.071 |
ting | +0.071 |
painter | +0.069 |
rom | +0.067 |
Neg logit contributions | |
much | -0.036 |
dives | -0.033 |
nap | -0.033 |
drift | -0.032 |
irm | -0.031 |
Token | smiled |
Token ID | 13541 |
Feature activation | +9.19e-03 |
Pos logit contributions | |
ting | +0.168 |
mill | +0.168 |
ini | +0.160 |
painter | +0.157 |
office | +0.155 |
Neg logit contributions | |
much | -0.107 |
nap | -0.104 |
drift | -0.103 |
dives | -0.103 |
irm | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ting | +0.014 |
painter | +0.013 |
mill | +0.013 |
ini | +0.012 |
Why | +0.012 |
Neg logit contributions | |
dives | -0.015 |
nap | -0.014 |
drift | -0.014 |
dive | -0.014 |
irm | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -4.62e-02 |
Pos logit contributions | |
dives | +0.039 |
irm | +0.039 |
much | +0.039 |
drift | +0.038 |
ust | +0.038 |
Neg logit contributions | |
mill | -0.052 |
ting | -0.052 |
painter | -0.050 |
paramed | -0.048 |
ini | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
much | +0.047 |
dives | +0.043 |
drift | +0.043 |
nap | +0.043 |
irm | +0.040 |
Neg logit contributions | |
mill | -0.098 |
ting | -0.097 |
ini | -0.094 |
painter | -0.094 |
office | -0.091 |
Token | " |
Token ID | 366 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
mill | +0.078 |
ini | +0.077 |
ting | +0.077 |
painter | +0.073 |
office | +0.071 |
Neg logit contributions | |
much | -0.083 |
drift | -0.081 |
nap | -0.077 |
dives | -0.077 |
swim | -0.074 |
Token | Looks |
Token ID | 41102 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
mill | +0.321 |
ting | +0.304 |
office | +0.299 |
painter | +0.286 |
paramed | +0.280 |
Neg logit contributions | |
much | -0.405 |
drift | -0.380 |
nap | -0.375 |
ust | -0.374 |
dives | -0.370 |
Token | like |
Token ID | 588 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
drift | +0.320 |
ls | +0.317 |
zag | +0.306 |
nap | +0.300 |
dive | +0.300 |
Neg logit contributions | |
ting | -0.209 |
painter | -0.198 |
pavement | -0.189 |
floors | -0.187 |
artist | -0.181 |
Token | you |
Token ID | 345 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
mill | +0.073 |
ting | +0.073 |
painter | +0.070 |
ini | +0.067 |
office | +0.067 |
Neg logit contributions | |
drift | -0.053 |
dives | -0.053 |
irm | -0.053 |
much | -0.051 |
nap | -0.051 |
Token | like |
Token ID | 588 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
much | +0.069 |
nap | +0.066 |
drift | +0.065 |
dives | +0.065 |
irm | +0.062 |
Neg logit contributions | |
ting | -0.122 |
mill | -0.122 |
ini | -0.118 |
painter | -0.117 |
paramed | -0.114 |
Token | the |
Token ID | 262 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
ting | +0.075 |
mill | +0.074 |
ini | +0.073 |
painter | +0.072 |
paramed | +0.069 |
Neg logit contributions | |
much | -0.055 |
nap | -0.053 |
dives | -0.053 |
drift | -0.053 |
irm | -0.050 |
Token | wardrobe |
Token ID | 35593 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
ting | +0.106 |
mill | +0.101 |
ini | +0.096 |
rom | +0.096 |
painter | +0.096 |
Neg logit contributions | |
nap | -0.080 |
much | -0.079 |
drift | -0.075 |
dives | -0.071 |
irm | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
mill | +0.051 |
ting | +0.050 |
painter | +0.049 |
ini | +0.047 |
office | +0.046 |
Neg logit contributions | |
dives | -0.035 |
drift | -0.035 |
irm | -0.034 |
ls | -0.033 |
hops | -0.033 |
Token | little |
Token ID | 1310 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
much | +0.093 |
nap | +0.090 |
dives | +0.088 |
drift | +0.088 |
swim | +0.083 |
Neg logit contributions | |
ting | -0.141 |
mill | -0.135 |
ini | -0.131 |
painter | -0.128 |
rom | -0.128 |
Token | crab |
Token ID | 32202 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ting | +0.028 |
mill | +0.026 |
ini | +0.025 |
rom | +0.025 |
painter | +0.024 |
Neg logit contributions | |
much | -0.041 |
nap | -0.041 |
dives | -0.040 |
drift | -0.040 |
swim | -0.039 |
Token | named |
Token ID | 3706 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ting | +0.031 |
mill | +0.031 |
painter | +0.029 |
ini | +0.029 |
paramed | +0.028 |
Neg logit contributions | |
much | -0.040 |
drift | -0.039 |
nap | -0.039 |
dives | -0.039 |
irm | -0.038 |
Token | Cr |
Token ID | 3864 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
ting | +0.056 |
mill | +0.055 |
painter | +0.053 |
ini | +0.048 |
pavement | +0.048 |
Neg logit contributions | |
irm | -0.067 |
drift | -0.066 |
dives | -0.066 |
ust | -0.065 |
much | -0.065 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.051 |
dives | +0.049 |
nap | +0.046 |
much | +0.045 |
hops | +0.044 |
Neg logit contributions | |
ini | -0.125 |
painter | -0.125 |
mill | -0.123 |
ting | -0.120 |
rom | -0.118 |
Token | y |
Token ID | 88 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
drift | +0.296 |
nap | +0.293 |
much | +0.292 |
dives | +0.291 |
irm | +0.287 |
Neg logit contributions | |
mill | -0.265 |
ting | -0.264 |
painter | -0.254 |
ini | -0.249 |
cut | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ting | +0.009 |
mill | +0.009 |
laund | +0.009 |
ini | +0.009 |
paramed | +0.009 |
Neg logit contributions | |
much | -0.003 |
swim | -0.003 |
nap | -0.003 |
dive | -0.003 |
ls | -0.003 |
Token | Cr |
Token ID | 3864 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
much | +0.021 |
dives | +0.020 |
drift | +0.020 |
nap | +0.020 |
irm | +0.019 |
Neg logit contributions | |
ting | -0.028 |
mill | -0.028 |
painter | -0.027 |
ini | -0.027 |
paramed | -0.026 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.039 |
dives | +0.035 |
nap | +0.034 |
much | +0.032 |
hops | +0.030 |
Neg logit contributions | |
ini | -0.134 |
painter | -0.131 |
mill | -0.129 |
ting | -0.127 |
rom | -0.126 |
Token | y |
Token ID | 88 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
drift | +0.321 |
nap | +0.319 |
dives | +0.312 |
much | +0.308 |
irm | +0.307 |
Neg logit contributions | |
mill | -0.230 |
ting | -0.229 |
ini | -0.224 |
painter | -0.222 |
cut | -0.215 |
Token | was |
Token ID | 373 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
much | +0.030 |
dives | +0.030 |
drift | +0.030 |
nap | +0.029 |
irm | +0.029 |
Neg logit contributions | |
mill | -0.031 |
ting | -0.031 |
painter | -0.029 |
ini | -0.029 |
paramed | -0.028 |
Token | too |
Token ID | 1165 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
mill | +0.058 |
ting | +0.056 |
office | +0.055 |
iron | +0.055 |
Why | +0.055 |
Neg logit contributions | |
dives | -0.039 |
ls | -0.036 |
drift | -0.034 |
irm | -0.034 |
hops | -0.034 |
Token | dangerous |
Token ID | 4923 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
dives | +0.130 |
drift | +0.127 |
nap | +0.126 |
irm | +0.125 |
hops | +0.123 |
Neg logit contributions | |
mill | -0.165 |
painter | -0.149 |
ini | -0.147 |
iron | -0.141 |
paramed | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
ting | +0.101 |
mill | +0.101 |
painter | +0.097 |
ini | +0.096 |
paramed | +0.093 |
Neg logit contributions | |
much | -0.057 |
drift | -0.056 |
dives | -0.055 |
nap | -0.055 |
irm | -0.053 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
much | +0.005 |
dives | +0.005 |
drift | +0.005 |
nap | +0.005 |
irm | +0.005 |
Neg logit contributions | |
ting | -0.011 |
mill | -0.011 |
painter | -0.011 |
ini | -0.011 |
paramed | -0.011 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.013 |
nap | +0.013 |
dives | +0.013 |
much | +0.012 |
hops | +0.012 |
Neg logit contributions | |
ini | -0.032 |
mill | -0.031 |
painter | -0.031 |
ting | -0.030 |
office | -0.030 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
nap | +0.296 |
drift | +0.281 |
dives | +0.279 |
much | +0.276 |
irm | +0.272 |
Neg logit contributions | |
cut | -0.269 |
mill | -0.261 |
ini | -0.256 |
ting | -0.252 |
painter | -0.249 |
Token | , |
Token ID | 11 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
drift | +0.011 |
much | +0.011 |
dives | +0.011 |
nap | +0.011 |
irm | +0.011 |
Neg logit contributions | |
ting | -0.020 |
mill | -0.020 |
painter | -0.019 |
ini | -0.019 |
office | -0.018 |
Token | Sam |
Token ID | 3409 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ting | +0.093 |
mill | +0.092 |
painter | +0.090 |
office | +0.085 |
ini | +0.085 |
Neg logit contributions | |
drift | -0.056 |
dives | -0.056 |
nap | -0.055 |
much | -0.055 |
irm | -0.055 |
Token | turned |
Token ID | 2900 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
mill | +0.022 |
ting | +0.022 |
painter | +0.022 |
ini | +0.021 |
office | +0.021 |
Neg logit contributions | |
much | -0.020 |
dives | -0.019 |
drift | -0.019 |
nap | -0.019 |
irm | -0.019 |
Token | away |
Token ID | 1497 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
much | +0.070 |
drift | +0.069 |
dives | +0.068 |
nap | +0.068 |
irm | +0.066 |
Neg logit contributions | |
mill | -0.110 |
ting | -0.109 |
painter | -0.106 |
ini | -0.105 |
office | -0.101 |
Token | around |
Token ID | 1088 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.033 |
dives | +0.032 |
nap | +0.032 |
irm | +0.031 |
Neg logit contributions | |
mill | -0.055 |
ting | -0.055 |
painter | -0.053 |
ini | -0.053 |
paramed | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
paramed | +0.088 |
mill | +0.085 |
ini | +0.083 |
laund | +0.081 |
painter | +0.080 |
Neg logit contributions | |
much | -0.041 |
nap | -0.035 |
drift | -0.034 |
time | -0.033 |
dives | -0.032 |
Token | door |
Token ID | 3420 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
ting | +0.102 |
paramed | +0.100 |
ican | +0.094 |
years | +0.093 |
rom | +0.092 |
Neg logit contributions | |
nap | -0.090 |
much | -0.086 |
time | -0.084 |
long | -0.077 |
close | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
mill | +0.005 |
ting | +0.005 |
painter | +0.005 |
ini | +0.005 |
paramed | +0.005 |
Neg logit contributions | |
much | -0.003 |
drift | -0.003 |
nap | -0.003 |
dives | -0.003 |
irm | -0.002 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
much | +0.003 |
drift | +0.003 |
dives | +0.003 |
nap | +0.003 |
irm | +0.003 |
Neg logit contributions | |
ting | -0.006 |
mill | -0.006 |
painter | -0.006 |
ini | -0.006 |
office | -0.006 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.009 |
nap | +0.009 |
dives | +0.008 |
hops | +0.008 |
much | +0.008 |
Neg logit contributions | |
ini | -0.038 |
painter | -0.037 |
mill | -0.037 |
rom | -0.036 |
office | -0.035 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
nap | +0.266 |
much | +0.251 |
drift | +0.250 |
dives | +0.247 |
irm | +0.243 |
Neg logit contributions | |
mill | -0.293 |
ting | -0.291 |
cut | -0.289 |
ini | -0.287 |
painter | -0.286 |
Token | , |
Token ID | 11 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
much | +0.013 |
dives | +0.012 |
drift | +0.012 |
nap | +0.012 |
irm | +0.012 |
Neg logit contributions | |
mill | -0.025 |
ting | -0.024 |
painter | -0.024 |
ini | -0.024 |
paramed | -0.023 |
Token | Jack |
Token ID | 3619 |
Feature activation | -6.31e-03 |
Pos logit contributions | |
ting | +0.090 |
mill | +0.089 |
painter | +0.087 |
Why | +0.081 |
office | +0.080 |
Neg logit contributions | |
drift | -0.059 |
nap | -0.058 |
irm | -0.058 |
dives | -0.057 |
ust | -0.056 |
Token | put |
Token ID | 1234 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
much | +0.009 |
dives | +0.009 |
drift | +0.009 |
nap | +0.008 |
irm | +0.008 |
Neg logit contributions | |
mill | -0.011 |
ting | -0.011 |
ini | -0.010 |
painter | -0.010 |
paramed | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
mill | +0.065 |
ting | +0.064 |
painter | +0.063 |
ini | +0.063 |
paramed | +0.061 |
Neg logit contributions | |
much | -0.044 |
drift | -0.042 |
nap | -0.042 |
dives | -0.042 |
irm | -0.041 |
Token | answer |
Token ID | 3280 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
much | +0.020 |
drift | +0.019 |
ls | +0.019 |
ust | +0.019 |
dives | +0.019 |
Neg logit contributions | |
mill | -0.034 |
painter | -0.033 |
office | -0.032 |
ting | -0.031 |
paramed | -0.031 |
Token | for |
Token ID | 329 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
much | +0.026 |
drift | +0.024 |
nap | +0.024 |
dives | +0.024 |
irm | +0.022 |
Neg logit contributions | |
mill | -0.055 |
ting | -0.054 |
ini | -0.054 |
painter | -0.053 |
paramed | -0.052 |
Token | him |
Token ID | 683 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
mill | +0.061 |
ting | +0.061 |
ini | +0.060 |
painter | +0.060 |
paramed | +0.058 |
Neg logit contributions | |
much | -0.057 |
drift | -0.055 |
nap | -0.055 |
dives | -0.054 |
irm | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
much | +0.022 |
drift | +0.021 |
dives | +0.021 |
nap | +0.021 |
irm | +0.020 |
Neg logit contributions | |
mill | -0.040 |
ting | -0.040 |
painter | -0.038 |
ini | -0.038 |
paramed | -0.037 |
Token | Fr |
Token ID | 1305 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
drift | +0.004 |
nap | +0.003 |
dives | +0.003 |
much | +0.003 |
irm | +0.003 |
Neg logit contributions | |
mill | -0.006 |
ting | -0.006 |
painter | -0.005 |
office | -0.005 |
paramed | -0.005 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.013 |
nap | +0.013 |
dives | +0.013 |
much | +0.012 |
hops | +0.012 |
Neg logit contributions | |
mill | -0.030 |
ini | -0.030 |
painter | -0.030 |
ting | -0.030 |
rom | -0.029 |
Token | rated |
Token ID | 4111 |
Feature activation | -8.49e-03 |
Pos logit contributions | |
nap | +0.287 |
drift | +0.266 |
much | +0.264 |
dives | +0.263 |
irm | +0.260 |
Neg logit contributions | |
cut | -0.279 |
mill | -0.278 |
ting | -0.273 |
ini | -0.269 |
painter | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
much | +0.009 |
drift | +0.009 |
dives | +0.009 |
nap | +0.009 |
irm | +0.008 |
Neg logit contributions | |
mill | -0.017 |
ting | -0.017 |
painter | -0.016 |
ini | -0.016 |
paramed | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | -6.17e-02 |
Pos logit contributions | |
ting | +0.108 |
mill | +0.107 |
painter | +0.104 |
office | +0.100 |
paramed | +0.099 |
Neg logit contributions | |
drift | -0.047 |
dives | -0.047 |
nap | -0.046 |
irm | -0.046 |
much | -0.044 |
Token | decided |
Token ID | 3066 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
much | +0.095 |
nap | +0.095 |
drift | +0.092 |
irm | +0.092 |
dives | +0.091 |
Neg logit contributions | |
mill | -0.093 |
ting | -0.092 |
painter | -0.088 |
cut | -0.083 |
office | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
mill | +0.070 |
ting | +0.070 |
ini | +0.068 |
painter | +0.068 |
paramed | +0.065 |
Neg logit contributions | |
much | -0.040 |
dives | -0.039 |
drift | -0.039 |
nap | -0.038 |
irm | -0.037 |
Token | ge |
Token ID | 469 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ting | +0.007 |
mill | +0.007 |
ini | +0.007 |
painter | +0.007 |
rom | +0.007 |
Neg logit contributions | |
dives | -0.004 |
drift | -0.004 |
much | -0.004 |
nap | -0.004 |
irm | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
dives | +0.049 |
drift | +0.048 |
much | +0.048 |
nap | +0.047 |
irm | +0.046 |
Neg logit contributions | |
ting | -0.079 |
mill | -0.078 |
painter | -0.075 |
ini | -0.074 |
office | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
much | +0.006 |
nap | +0.005 |
drift | +0.005 |
dives | +0.004 |
irm | +0.004 |
Neg logit contributions | |
ting | -0.017 |
mill | -0.017 |
ini | -0.017 |
painter | -0.016 |
cut | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.77e-02 |
Pos logit contributions | |
dives | +0.063 |
drift | +0.063 |
nap | +0.061 |
irm | +0.061 |
much | +0.060 |
Neg logit contributions | |
mill | -0.112 |
ting | -0.111 |
painter | -0.108 |
ini | -0.107 |
office | -0.104 |
Token | Fr |
Token ID | 6732 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
much | +0.083 |
ust | +0.070 |
nap | +0.068 |
drift | +0.065 |
irm | +0.064 |
Neg logit contributions | |
ting | -0.110 |
mill | -0.107 |
painter | -0.100 |
ini | -0.100 |
keeping | -0.099 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.004 |
dives | +0.003 |
nap | +0.003 |
much | +0.003 |
hops | +0.003 |
Neg logit contributions | |
mill | -0.016 |
ini | -0.016 |
painter | -0.016 |
ting | -0.015 |
rom | -0.015 |
Token | rated |
Token ID | 4111 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
nap | +0.262 |
drift | +0.248 |
much | +0.248 |
dives | +0.246 |
irm | +0.241 |
Neg logit contributions | |
mill | -0.295 |
ting | -0.292 |
cut | -0.288 |
ini | -0.284 |
painter | -0.282 |
Token | , |
Token ID | 11 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
much | +0.011 |
drift | +0.011 |
dives | +0.010 |
nap | +0.010 |
irm | +0.010 |
Neg logit contributions | |
mill | -0.021 |
ting | -0.021 |
painter | -0.020 |
ini | -0.020 |
paramed | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
ting | +0.093 |
mill | +0.093 |
ini | +0.090 |
painter | +0.089 |
paramed | +0.086 |
Neg logit contributions | |
much | -0.058 |
drift | -0.056 |
nap | -0.056 |
dives | -0.055 |
irm | -0.053 |
Token | little |
Token ID | 1310 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ting | +0.076 |
rom | +0.074 |
keeping | +0.073 |
stick | +0.072 |
paramed | +0.071 |
Neg logit contributions | |
nap | -0.107 |
much | -0.106 |
dives | -0.101 |
dive | -0.100 |
swim | -0.100 |
Token | ant |
Token ID | 1885 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
rom | +0.027 |
ting | +0.027 |
paramed | +0.026 |
keeping | +0.026 |
cut | +0.026 |
Neg logit contributions | |
nap | -0.040 |
dives | -0.038 |
hops | -0.038 |
dive | -0.037 |
much | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ting | +0.028 |
mill | +0.028 |
painter | +0.027 |
ini | +0.026 |
cut | +0.026 |
Neg logit contributions | |
drift | -0.018 |
much | -0.018 |
nap | -0.018 |
irm | -0.018 |
dives | -0.018 |
Token | One |
Token ID | 1881 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
much | +0.012 |
drift | +0.012 |
dives | +0.012 |
nap | +0.012 |
irm | +0.012 |
Neg logit contributions | |
mill | -0.032 |
ting | -0.032 |
painter | -0.031 |
ini | -0.031 |
paramed | -0.030 |
Token | day |
Token ID | 1110 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
irm | +0.080 |
drift | +0.079 |
ares | +0.079 |
ls | +0.078 |
ust | +0.077 |
Neg logit contributions | |
mill | -0.062 |
painter | -0.057 |
ini | -0.056 |
ting | -0.050 |
office | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
drift | +0.042 |
irm | +0.041 |
ust | +0.041 |
nap | +0.039 |
dives | +0.039 |
Neg logit contributions | |
ting | -0.049 |
mill | -0.048 |
painter | -0.046 |
paramed | -0.043 |
years | -0.042 |
Token | Cr |
Token ID | 3864 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
ting | +0.088 |
mill | +0.088 |
painter | +0.085 |
ini | +0.083 |
paramed | +0.081 |
Neg logit contributions | |
much | -0.051 |
drift | -0.051 |
dives | -0.051 |
nap | -0.050 |
irm | -0.049 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.042 |
dives | +0.037 |
nap | +0.035 |
much | +0.033 |
dive | +0.033 |
Neg logit contributions | |
ini | -0.130 |
painter | -0.127 |
mill | -0.124 |
ting | -0.122 |
rom | -0.122 |
Token | y |
Token ID | 88 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
nap | +0.344 |
drift | +0.339 |
much | +0.333 |
irm | +0.328 |
dives | +0.323 |
Neg logit contributions | |
ting | -0.205 |
mill | -0.204 |
ini | -0.195 |
painter | -0.192 |
cut | -0.184 |
Token | found |
Token ID | 1043 |
Feature activation | +7.62e-02 |
Pos logit contributions | |
ting | +0.007 |
mill | +0.007 |
painter | +0.007 |
ini | +0.006 |
paramed | +0.006 |
Neg logit contributions | |
much | -0.007 |
dives | -0.007 |
nap | -0.007 |
drift | -0.007 |
irm | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
mill | +0.178 |
ting | +0.176 |
ini | +0.176 |
painter | +0.174 |
rom | +0.170 |
Neg logit contributions | |
much | -0.065 |
dives | -0.052 |
nap | -0.052 |
irm | -0.047 |
swim | -0.047 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.63e-03 |
Pos logit contributions | |
much | +0.085 |
drift | +0.084 |
dives | +0.084 |
nap | +0.082 |
irm | +0.082 |
Neg logit contributions | |
mill | -0.140 |
ting | -0.138 |
painter | -0.135 |
ini | -0.132 |
office | -0.128 |
Token | shell |
Token ID | 7582 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
ting | +0.003 |
paramed | +0.003 |
years | +0.003 |
mill | +0.003 |
ini | +0.003 |
Neg logit contributions | |
nap | -0.002 |
dives | -0.002 |
much | -0.002 |
dive | -0.002 |
swim | -0.002 |
Token | Cr |
Token ID | 3864 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
ting | +0.056 |
mill | +0.055 |
painter | +0.053 |
ini | +0.048 |
pavement | +0.048 |
Neg logit contributions | |
irm | -0.067 |
drift | -0.066 |
dives | -0.066 |
ust | -0.065 |
much | -0.065 |
Token | ust |
Token ID | 436 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
drift | +0.051 |
dives | +0.049 |
nap | +0.046 |
much | +0.045 |
hops | +0.044 |
Neg logit contributions | |
ini | -0.125 |
painter | -0.125 |
mill | -0.123 |
ting | -0.120 |
rom | -0.118 |
Token | y |
Token ID | 88 |
Feature activation | +4.09e-03 |
Pos logit contributions | |
drift | +0.296 |
nap | +0.293 |
much | +0.292 |
dives | +0.291 |
irm | +0.287 |
Neg logit contributions | |
mill | -0.265 |
ting | -0.264 |
painter | -0.254 |
ini | -0.249 |
cut | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ting | +0.009 |
mill | +0.009 |
laund | +0.009 |
ini | +0.009 |
paramed | +0.009 |
Neg logit contributions | |
much | -0.003 |
swim | -0.003 |
nap | -0.003 |
dive | -0.003 |
ls | -0.003 |
Token | Cr |
Token ID | 3864 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
much | +0.021 |
dives | +0.020 |
drift | +0.020 |
nap | +0.020 |
irm | +0.019 |
Neg logit contributions | |
ting | -0.028 |
mill | -0.028 |
painter | -0.027 |
ini | -0.027 |
paramed | -0.026 |
Token | ust |
Token ID | 436 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
drift | +0.039 |
dives | +0.035 |
nap | +0.034 |
much | +0.032 |
hops | +0.030 |
Neg logit contributions | |
ini | -0.134 |
painter | -0.131 |
mill | -0.129 |
ting | -0.127 |
rom | -0.126 |
Token | y |
Token ID | 88 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
drift | +0.321 |
nap | +0.319 |
dives | +0.312 |
much | +0.308 |
irm | +0.307 |
Neg logit contributions | |
mill | -0.230 |
ting | -0.229 |
ini | -0.224 |
painter | -0.222 |
cut | -0.215 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ting | +0.008 |
mill | +0.007 |
painter | +0.007 |
ini | +0.007 |
paramed | +0.007 |
Neg logit contributions | |
much | -0.007 |
nap | -0.007 |
dives | -0.007 |
drift | -0.007 |
hops | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
ting | +0.103 |
mill | +0.101 |
painter | +0.100 |
ini | +0.095 |
years | +0.094 |
Neg logit contributions | |
drift | -0.090 |
dives | -0.086 |
nap | -0.085 |
irm | -0.083 |
much | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
drift | +0.057 |
dives | +0.057 |
irm | +0.056 |
ust | +0.055 |
much | +0.055 |
Neg logit contributions | |
mill | -0.090 |
ting | -0.089 |
painter | -0.086 |
ini | -0.083 |
office | -0.083 |
Token | big |
Token ID | 1263 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
much | +0.073 |
nap | +0.070 |
dives | +0.067 |
dive | +0.063 |
swim | +0.062 |
Neg logit contributions | |
ting | -0.171 |
cles | -0.158 |
rom | -0.157 |
ini | -0.157 |
paramed | -0.157 |
Token | stick |
Token ID | 4859 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
irm | +0.100 |
ls | +0.096 |
dives | +0.093 |
hops | +0.093 |
oll | +0.089 |
Neg logit contributions | |
iron | -0.078 |
painter | -0.076 |
mill | -0.073 |
cut | -0.072 |
ting | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
ting | +0.028 |
mill | +0.026 |
painter | +0.025 |
cut | +0.024 |
ini | +0.024 |
Neg logit contributions | |
dives | -0.019 |
drift | -0.019 |
nap | -0.019 |
irm | -0.019 |
hops | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
drift | +0.005 |
dives | +0.005 |
much | +0.005 |
nap | +0.005 |
irm | +0.005 |
Neg logit contributions | |
mill | -0.010 |
ting | -0.010 |
painter | -0.010 |
ini | -0.009 |
office | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
drift | +0.064 |
dives | +0.063 |
nap | +0.062 |
irm | +0.061 |
much | +0.060 |
Neg logit contributions | |
mill | -0.109 |
ting | -0.108 |
painter | -0.105 |
ini | -0.104 |
office | -0.102 |
Token | Fr |
Token ID | 6732 |
Feature activation | -5.96e-03 |
Pos logit contributions | |
much | +0.082 |
nap | +0.075 |
dives | +0.075 |
drift | +0.074 |
ust | +0.073 |
Neg logit contributions | |
ting | -0.098 |
mill | -0.097 |
painter | -0.093 |
ini | -0.091 |
paramed | -0.088 |
Token | ust |
Token ID | 436 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
drift | +0.004 |
nap | +0.004 |
dives | +0.004 |
hops | +0.003 |
much | +0.003 |
Neg logit contributions | |
mill | -0.015 |
ini | -0.015 |
painter | -0.014 |
cut | -0.014 |
ting | -0.014 |
Token | rated |
Token ID | 4111 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
nap | +0.269 |
drift | +0.258 |
much | +0.253 |
dives | +0.252 |
irm | +0.250 |
Neg logit contributions | |
mill | -0.288 |
ting | -0.285 |
cut | -0.282 |
painter | -0.280 |
ini | -0.278 |
Token | , |
Token ID | 11 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
much | +0.009 |
drift | +0.008 |
dives | +0.008 |
nap | +0.008 |
irm | +0.008 |
Neg logit contributions | |
ting | -0.016 |
mill | -0.016 |
painter | -0.015 |
ini | -0.015 |
paramed | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
ting | +0.087 |
mill | +0.087 |
painter | +0.083 |
office | +0.078 |
cut | +0.078 |
Neg logit contributions | |
irm | -0.062 |
drift | -0.061 |
dives | -0.061 |
ust | -0.059 |
nap | -0.059 |
Token | lion |
Token ID | 18744 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
ting | +0.088 |
rom | +0.086 |
mill | +0.085 |
ini | +0.085 |
laund | +0.084 |
Neg logit contributions | |
much | -0.092 |
nap | -0.092 |
dives | -0.089 |
swim | -0.086 |
drift | -0.086 |
Token | went |
Token ID | 1816 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
ting | +0.036 |
mill | +0.036 |
painter | +0.035 |
ini | +0.033 |
cut | +0.033 |
Neg logit contributions | |
much | -0.034 |
drift | -0.033 |
dives | -0.033 |
nap | -0.033 |
irm | -0.033 |
Token | table |
Token ID | 3084 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
years | +0.083 |
ting | +0.078 |
ini | +0.077 |
paramed | +0.076 |
mill | +0.074 |
Neg logit contributions | |
nap | -0.103 |
drift | -0.096 |
much | -0.095 |
swim | -0.091 |
time | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
ting | +0.043 |
mill | +0.042 |
ini | +0.041 |
painter | +0.041 |
paramed | +0.040 |
Neg logit contributions | |
much | -0.019 |
nap | -0.018 |
drift | -0.018 |
dives | -0.017 |
irm | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
much | +0.002 |
dives | +0.002 |
nap | +0.002 |
drift | +0.002 |
irm | +0.002 |
Neg logit contributions | |
ting | -0.005 |
mill | -0.005 |
painter | -0.005 |
ini | -0.005 |
cut | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
much | +0.044 |
nap | +0.038 |
dives | +0.037 |
drift | +0.036 |
irm | +0.034 |
Neg logit contributions | |
ting | -0.122 |
mill | -0.119 |
painter | -0.116 |
ini | -0.115 |
paramed | -0.111 |
Token | " |
Token ID | 1 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
much | +0.073 |
nap | +0.064 |
dives | +0.063 |
ls | +0.061 |
drift | +0.060 |
Neg logit contributions | |
ting | -0.096 |
mill | -0.093 |
ini | -0.089 |
painter | -0.088 |
stick | -0.086 |
Token | Looks |
Token ID | 41102 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
mill | +0.261 |
ting | +0.251 |
ini | +0.249 |
office | +0.236 |
rom | +0.229 |
Neg logit contributions | |
nap | -0.433 |
much | -0.420 |
dives | -0.415 |
drift | -0.414 |
irm | -0.399 |
Token | like |
Token ID | 588 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
drift | +0.267 |
nap | +0.255 |
ust | +0.250 |
dive | +0.250 |
dives | +0.249 |
Neg logit contributions | |
ting | -0.278 |
painter | -0.266 |
mill | -0.264 |
floors | -0.252 |
pavement | -0.248 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
ting | +0.080 |
ini | +0.078 |
mill | +0.078 |
painter | +0.075 |
cut | +0.075 |
Neg logit contributions | |
much | -0.056 |
nap | -0.054 |
dives | -0.052 |
drift | -0.051 |
dive | -0.049 |
Token | has |
Token ID | 468 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ting | +0.194 |
mill | +0.190 |
ini | +0.183 |
laund | +0.180 |
painter | +0.179 |
Neg logit contributions | |
much | -0.121 |
nap | -0.112 |
dives | -0.108 |
drift | -0.108 |
ls | -0.104 |
Token | some |
Token ID | 617 |
Feature activation | -6.47e-02 |
Pos logit contributions | |
ting | +0.077 |
ini | +0.075 |
mill | +0.074 |
painter | +0.072 |
cut | +0.072 |
Neg logit contributions | |
much | -0.051 |
nap | -0.048 |
dives | -0.046 |
drift | -0.045 |
irm | -0.042 |
Token | mail |
Token ID | 6920 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
much | +0.085 |
nap | +0.083 |
dives | +0.079 |
drift | +0.079 |
ls | +0.074 |
Neg logit contributions | |
ting | -0.120 |
mill | -0.115 |
ini | -0.113 |
painter | -0.112 |
rom | -0.110 |
Token | something |
Token ID | 1223 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ting | +0.109 |
mill | +0.108 |
painter | +0.103 |
office | +0.100 |
ini | +0.099 |
Neg logit contributions | |
drift | -0.089 |
dives | -0.088 |
nap | -0.087 |
irm | -0.087 |
much | -0.086 |
Token | just |
Token ID | 655 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
drift | +0.082 |
irm | +0.081 |
dives | +0.078 |
nap | +0.077 |
hops | +0.076 |
Neg logit contributions | |
mill | -0.107 |
ting | -0.105 |
painter | -0.102 |
office | -0.100 |
ini | -0.097 |
Token | because |
Token ID | 780 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
much | +0.139 |
drift | +0.138 |
dives | +0.138 |
nap | +0.137 |
irm | +0.135 |
Neg logit contributions | |
ting | -0.211 |
mill | -0.207 |
painter | -0.199 |
office | -0.192 |
ini | -0.192 |
Token | someone |
Token ID | 2130 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
much | +0.040 |
drift | +0.039 |
dives | +0.039 |
nap | +0.039 |
irm | +0.038 |
Neg logit contributions | |
mill | -0.067 |
ting | -0.067 |
painter | -0.064 |
ini | -0.063 |
office | -0.062 |
Token | d |
Token ID | 288 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
drift | +0.050 |
irm | +0.049 |
much | +0.048 |
nap | +0.048 |
dives | +0.048 |
Neg logit contributions | |
ting | -0.064 |
mill | -0.064 |
painter | -0.062 |
office | -0.059 |
ini | -0.059 |
Token | ares |
Token ID | 3565 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
much | +0.063 |
drift | +0.062 |
dives | +0.062 |
nap | +0.062 |
irm | +0.060 |
Neg logit contributions | |
ting | -0.085 |
mill | -0.085 |
painter | -0.081 |
ini | -0.080 |
paramed | -0.078 |
Token | you |
Token ID | 345 |
Feature activation | -6.37e-02 |
Pos logit contributions | |
much | +0.212 |
drift | +0.212 |
dives | +0.210 |
nap | +0.209 |
irm | +0.204 |
Neg logit contributions | |
ting | -0.340 |
mill | -0.337 |
painter | -0.325 |
ini | -0.319 |
office | -0.311 |
Token | . |
Token ID | 13 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
much | +0.073 |
dives | +0.071 |
nap | +0.071 |
drift | +0.070 |
irm | +0.067 |
Neg logit contributions | |
mill | -0.123 |
ting | -0.122 |
painter | -0.119 |
ini | -0.118 |
paramed | -0.115 |
Token | Always |
Token ID | 16622 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
much | +0.006 |
drift | +0.006 |
dives | +0.006 |
nap | +0.006 |
irm | +0.006 |
Neg logit contributions | |
mill | -0.008 |
ting | -0.008 |
painter | -0.007 |
ini | -0.007 |
paramed | -0.007 |
Token | remember |
Token ID | 3505 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
ls | +0.008 |
much | +0.008 |
dives | +0.008 |
drift | +0.008 |
irm | +0.008 |
Neg logit contributions | |
mill | -0.014 |
ting | -0.014 |
painter | -0.013 |
office | -0.013 |
ini | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
much | +0.011 |
nap | +0.010 |
dives | +0.010 |
drift | +0.010 |
dive | +0.009 |
Neg logit contributions | |
ini | -0.017 |
ting | -0.017 |
mill | -0.017 |
painter | -0.017 |
paramed | -0.017 |
Token | smiled |
Token ID | 13541 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
much | +0.012 |
drift | +0.012 |
dives | +0.012 |
nap | +0.012 |
irm | +0.012 |
Neg logit contributions | |
ting | -0.016 |
mill | -0.016 |
painter | -0.015 |
ini | -0.015 |
paramed | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
ting | +0.014 |
mill | +0.013 |
painter | +0.013 |
ini | +0.012 |
rom | +0.012 |
Neg logit contributions | |
dives | -0.013 |
nap | -0.013 |
drift | -0.013 |
much | -0.012 |
irm | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
mill | +0.080 |
ting | +0.080 |
painter | +0.077 |
ini | +0.076 |
paramed | +0.073 |
Neg logit contributions | |
much | -0.073 |
drift | -0.071 |
dives | -0.071 |
nap | -0.071 |
irm | -0.069 |
Token | replied |
Token ID | 8712 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
nap | +0.037 |
much | +0.036 |
drift | +0.036 |
dives | +0.036 |
irm | +0.036 |
Neg logit contributions | |
ting | -0.056 |
mill | -0.055 |
painter | -0.053 |
paramed | -0.050 |
cut | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +4.99e-02 |
Pos logit contributions | |
much | +0.033 |
drift | +0.033 |
dives | +0.033 |
nap | +0.033 |
irm | +0.032 |
Neg logit contributions | |
ting | -0.061 |
mill | -0.061 |
painter | -0.059 |
ini | -0.057 |
paramed | -0.056 |
Token | " |
Token ID | 366 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
mill | +0.069 |
ting | +0.068 |
ini | +0.068 |
painter | +0.065 |
office | +0.062 |
Neg logit contributions | |
much | -0.085 |
drift | -0.083 |
dives | -0.081 |
nap | -0.080 |
irm | -0.077 |
Token | I |
Token ID | 40 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
mill | +0.280 |
office | +0.260 |
ting | +0.255 |
painter | +0.247 |
floors | +0.243 |
Neg logit contributions | |
much | -0.425 |
drift | -0.417 |
ust | -0.411 |
dives | -0.405 |
irm | -0.402 |
Token | will |
Token ID | 481 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
mill | +0.026 |
painter | +0.024 |
ini | +0.023 |
paramed | +0.023 |
cut | +0.023 |
Neg logit contributions | |
ls | -0.025 |
irm | -0.025 |
much | -0.024 |
drift | -0.024 |
dives | -0.024 |
Token | ! |
Token ID | 0 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
mill | +0.154 |
ting | +0.154 |
painter | +0.148 |
ini | +0.144 |
office | +0.142 |
Neg logit contributions | |
much | -0.095 |
dives | -0.095 |
irm | -0.094 |
drift | -0.091 |
nap | -0.091 |
Token | I |
Token ID | 314 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
ting | +0.019 |
mill | +0.019 |
painter | +0.018 |
ini | +0.018 |
paramed | +0.017 |
Neg logit contributions | |
much | -0.016 |
drift | -0.015 |
dives | -0.015 |
nap | -0.015 |
irm | -0.015 |
Token | 'll |
Token ID | 1183 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
mill | +0.067 |
ting | +0.063 |
painter | +0.063 |
ini | +0.063 |
cut | +0.062 |
Neg logit contributions | |
ls | -0.053 |
much | -0.053 |
irm | -0.053 |
dives | -0.052 |
drift | -0.051 |
Token | His |
Token ID | 2399 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
drift | +0.008 |
nap | +0.008 |
much | +0.008 |
dives | +0.008 |
irm | +0.008 |
Neg logit contributions | |
mill | -0.009 |
ting | -0.009 |
painter | -0.009 |
ini | -0.008 |
paramed | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
much | +0.020 |
nap | +0.019 |
drift | +0.019 |
dives | +0.019 |
irm | +0.019 |
Neg logit contributions | |
ting | -0.024 |
mill | -0.024 |
painter | -0.023 |
ini | -0.023 |
paramed | -0.022 |
Token | my |
Token ID | 1820 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
mill | +0.156 |
ting | +0.148 |
pavement | +0.143 |
laund | +0.141 |
ini | +0.141 |
Neg logit contributions | |
much | -0.158 |
drift | -0.158 |
nap | -0.154 |
swim | -0.147 |
dives | -0.147 |
Token | said |
Token ID | 531 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
mill | +0.053 |
ting | +0.053 |
ini | +0.051 |
painter | +0.051 |
office | +0.049 |
Neg logit contributions | |
drift | -0.034 |
much | -0.034 |
nap | -0.033 |
dives | -0.033 |
irm | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
much | +0.049 |
drift | +0.047 |
dives | +0.047 |
nap | +0.046 |
irm | +0.044 |
Neg logit contributions | |
mill | -0.096 |
ting | -0.096 |
painter | -0.093 |
ini | -0.093 |
office | -0.089 |
Token | " |
Token ID | 366 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ini | +0.080 |
mill | +0.078 |
painter | +0.075 |
ting | +0.075 |
office | +0.071 |
Neg logit contributions | |
much | -0.080 |
drift | -0.076 |
dives | -0.072 |
nap | -0.072 |
swim | -0.071 |
Token | It |
Token ID | 1026 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
mill | +0.286 |
ting | +0.272 |
office | +0.268 |
painter | +0.264 |
ini | +0.253 |
Neg logit contributions | |
much | -0.419 |
drift | -0.409 |
dives | -0.408 |
irm | -0.403 |
nap | -0.401 |
Token | 's |
Token ID | 338 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
nap | +0.023 |
irm | +0.023 |
much | +0.022 |
drift | +0.022 |
inn | +0.021 |
Neg logit contributions | |
ting | -0.026 |
mill | -0.026 |
ini | -0.025 |
painter | -0.025 |
cut | -0.025 |
Token | time |
Token ID | 640 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
dives | +0.025 |
ls | +0.024 |
drift | +0.023 |
hops | +0.022 |
nap | +0.022 |
Neg logit contributions | |
mill | -0.061 |
ting | -0.060 |
office | -0.058 |
painter | -0.057 |
Why | -0.057 |
Token | for |
Token ID | 329 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
much | +0.118 |
drift | +0.118 |
dives | +0.117 |
nap | +0.115 |
irm | +0.115 |
Neg logit contributions | |
mill | -0.186 |
ting | -0.185 |
painter | -0.178 |
ini | -0.173 |
office | -0.172 |
Token | a |
Token ID | 257 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
ting | +0.062 |
mill | +0.062 |
painter | +0.058 |
office | +0.057 |
paramed | +0.055 |
Neg logit contributions | |
ust | -0.051 |
irm | -0.051 |
dives | -0.050 |
drift | -0.050 |
much | -0.050 |
Token | |
Token ID | 220 |
Feature activation | -9.47e-03 |
Pos logit contributions | |
ting | +0.129 |
mill | +0.121 |
painter | +0.115 |
paramed | +0.111 |
rom | +0.110 |
Neg logit contributions | |
ust | -0.095 |
dives | -0.094 |
nap | -0.093 |
irm | -0.091 |
drift | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
nap | +0.012 |
drift | +0.012 |
dives | +0.012 |
irm | +0.012 |
much | +0.012 |
Neg logit contributions | |
mill | -0.016 |
ting | -0.015 |
rom | -0.015 |
painter | -0.015 |
office | -0.015 |
Token | Dad |
Token ID | 46270 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
much | +0.082 |
drift | +0.080 |
dives | +0.080 |
nap | +0.080 |
irm | +0.078 |
Neg logit contributions | |
ting | -0.074 |
mill | -0.073 |
painter | -0.070 |
ini | -0.068 |
office | -0.066 |
Token | said |
Token ID | 531 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
mill | +0.121 |
ting | +0.121 |
painter | +0.117 |
ini | +0.115 |
paramed | +0.112 |
Neg logit contributions | |
much | -0.088 |
drift | -0.086 |
dives | -0.086 |
nap | -0.085 |
irm | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
much | +0.049 |
drift | +0.049 |
dives | +0.049 |
nap | +0.049 |
irm | +0.048 |
Neg logit contributions | |
ting | -0.090 |
mill | -0.090 |
painter | -0.087 |
ini | -0.085 |
paramed | -0.083 |
Token | " |
Token ID | 366 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
mill | +0.076 |
ini | +0.075 |
ting | +0.075 |
painter | +0.071 |
office | +0.070 |
Neg logit contributions | |
much | -0.084 |
drift | -0.082 |
dives | -0.080 |
nap | -0.079 |
swim | -0.077 |
Token | Yes |
Token ID | 5297 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
mill | +0.300 |
ting | +0.279 |
office | +0.278 |
paramed | +0.267 |
painter | +0.261 |
Neg logit contributions | |
much | -0.424 |
drift | -0.401 |
ust | -0.399 |
dives | -0.396 |
nap | -0.391 |
Token | , |
Token ID | 11 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
drift | +0.106 |
much | +0.106 |
dives | +0.106 |
nap | +0.104 |
irm | +0.103 |
Neg logit contributions | |
ting | -0.177 |
mill | -0.176 |
painter | -0.170 |
ini | -0.166 |
paramed | -0.162 |
Token | we |
Token ID | 356 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
ting | +0.103 |
mill | +0.103 |
painter | +0.099 |
ini | +0.098 |
paramed | +0.095 |
Neg logit contributions | |
much | -0.058 |
drift | -0.057 |
dives | -0.057 |
nap | -0.056 |
irm | -0.054 |
Token | did |
Token ID | 750 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
much | +0.023 |
nap | +0.022 |
drift | +0.022 |
dives | +0.021 |
dive | +0.020 |
Neg logit contributions | |
ting | -0.046 |
mill | -0.045 |
ini | -0.044 |
paramed | -0.043 |
painter | -0.043 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.16e-02 |
Pos logit contributions | |
mill | +0.055 |
ting | +0.055 |
painter | +0.053 |
ini | +0.051 |
office | +0.051 |
Neg logit contributions | |
drift | -0.042 |
dives | -0.042 |
irm | -0.042 |
nap | -0.041 |
much | -0.041 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
ting | +0.031 |
mill | +0.030 |
painter | +0.029 |
ini | +0.029 |
paramed | +0.028 |
Neg logit contributions | |
much | -0.024 |
nap | -0.024 |
dives | -0.023 |
drift | -0.023 |
irm | -0.023 |
Token | Her |
Token ID | 2332 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
ting | +0.123 |
mill | +0.123 |
painter | +0.118 |
ini | +0.117 |
paramed | +0.113 |
Neg logit contributions | |
much | -0.081 |
drift | -0.080 |
dives | -0.079 |
nap | -0.079 |
irm | -0.077 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
much | +0.007 |
nap | +0.007 |
drift | +0.006 |
dives | +0.006 |
irm | +0.006 |
Neg logit contributions | |
ting | -0.010 |
mill | -0.010 |
ini | -0.009 |
painter | -0.009 |
cut | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
mill | +0.189 |
ting | +0.189 |
painter | +0.183 |
ini | +0.180 |
paramed | +0.175 |
Neg logit contributions | |
much | -0.121 |
dives | -0.119 |
drift | -0.118 |
nap | -0.117 |
irm | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
much | +0.051 |
drift | +0.048 |
nap | +0.048 |
dives | +0.048 |
irm | +0.046 |
Neg logit contributions | |
mill | -0.104 |
ting | -0.104 |
painter | -0.100 |
ini | -0.100 |
office | -0.096 |
Token | " |
Token ID | 366 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ini | +0.079 |
mill | +0.077 |
keeping | +0.073 |
ting | +0.072 |
painter | +0.072 |
Neg logit contributions | |
much | -0.071 |
drift | -0.067 |
nap | -0.063 |
they | -0.062 |
dives | -0.062 |
Token | Yes |
Token ID | 5297 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
mill | +0.374 |
ting | +0.371 |
painter | +0.354 |
ini | +0.349 |
office | +0.347 |
Neg logit contributions | |
much | -0.341 |
nap | -0.320 |
drift | -0.318 |
dives | -0.314 |
irm | -0.314 |
Token | , |
Token ID | 11 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
dives | +0.104 |
much | +0.103 |
drift | +0.103 |
nap | +0.101 |
irm | +0.100 |
Neg logit contributions | |
mill | -0.182 |
ting | -0.182 |
painter | -0.175 |
ini | -0.171 |
paramed | -0.168 |
Token | you |
Token ID | 345 |
Feature activation | -6.34e-02 |
Pos logit contributions | |
mill | +0.093 |
ting | +0.092 |
painter | +0.090 |
ini | +0.087 |
paramed | +0.085 |
Neg logit contributions | |
dives | -0.056 |
drift | -0.056 |
irm | -0.055 |
much | -0.054 |
nap | -0.053 |
Token | can |
Token ID | 460 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
dives | +0.092 |
drift | +0.091 |
irm | +0.091 |
ls | +0.088 |
nap | +0.087 |
Neg logit contributions | |
mill | -0.101 |
painter | -0.098 |
ting | -0.097 |
ini | -0.092 |
office | -0.091 |
Token | organize |
Token ID | 16481 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
mill | +0.207 |
ting | +0.206 |
painter | +0.199 |
ini | +0.196 |
office | +0.190 |
Neg logit contributions | |
much | -0.146 |
dives | -0.144 |
drift | -0.143 |
nap | -0.141 |
irm | -0.140 |
Token | a |
Token ID | 257 |
Feature activation | -7.04e-02 |
Pos logit contributions | |
dives | +0.038 |
drift | +0.038 |
much | +0.037 |
irm | +0.036 |
nap | +0.036 |
Neg logit contributions | |
mill | -0.065 |
ting | -0.065 |
painter | -0.062 |
ini | -0.061 |
office | -0.061 |
Token | hug |
Token ID | 16225 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
irm | +0.095 |
ust | +0.094 |
dives | +0.090 |
drift | +0.090 |
ls | +0.088 |
Neg logit contributions | |
mill | -0.118 |
painter | -0.117 |
paramed | -0.114 |
iron | -0.106 |
laund | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -3.35e-03 |
Pos logit contributions | |
mill | +0.025 |
ini | +0.024 |
painter | +0.024 |
years | +0.023 |
ting | +0.023 |
Neg logit contributions | |
much | -0.009 |
nap | -0.008 |
drift | -0.008 |
irm | -0.007 |
dives | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
much | +0.004 |
nap | +0.004 |
drift | +0.004 |
dives | +0.004 |
irm | +0.004 |
Neg logit contributions | |
ting | -0.006 |
mill | -0.006 |
painter | -0.006 |
ini | -0.006 |
cut | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
much | +0.050 |
drift | +0.048 |
nap | +0.048 |
dives | +0.048 |
irm | +0.045 |
Neg logit contributions | |
ting | -0.113 |
mill | -0.113 |
painter | -0.109 |
ini | -0.108 |
paramed | -0.105 |
Token | " |
Token ID | 1 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
much | +0.071 |
nap | +0.061 |
drift | +0.059 |
dives | +0.057 |
irm | +0.057 |
Neg logit contributions | |
mill | -0.101 |
ting | -0.101 |
smith | -0.097 |
painter | -0.093 |
office | -0.093 |
Token | Are |
Token ID | 8491 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
mill | +0.276 |
ting | +0.259 |
office | +0.254 |
painter | +0.242 |
ini | +0.240 |
Neg logit contributions | |
much | -0.433 |
nap | -0.429 |
drift | -0.422 |
irm | -0.410 |
dives | -0.404 |
Token | you |
Token ID | 345 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
ting | +0.101 |
Why | +0.089 |
years | +0.088 |
mill | +0.086 |
ter | +0.085 |
Neg logit contributions | |
drift | -0.112 |
dives | -0.108 |
irm | -0.106 |
nap | -0.101 |
hops | -0.101 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
ls | +0.054 |
dives | +0.048 |
common | +0.046 |
drift | +0.046 |
Zac | +0.044 |
Neg logit contributions | |
ting | -0.138 |
ter | -0.131 |
ini | -0.130 |
painter | -0.130 |
mill | -0.129 |
Token | ?" |
Token ID | 1701 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
drift | +0.037 |
dives | +0.037 |
much | +0.036 |
irm | +0.036 |
nap | +0.035 |
Neg logit contributions | |
mill | -0.052 |
ting | -0.052 |
painter | -0.052 |
ini | -0.049 |
office | -0.049 |
Token | her |
Token ID | 607 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
mill | +0.110 |
ting | +0.110 |
painter | +0.107 |
ini | +0.104 |
paramed | +0.102 |
Neg logit contributions | |
much | -0.070 |
dives | -0.069 |
drift | -0.069 |
nap | -0.068 |
irm | -0.067 |
Token | day |
Token ID | 1110 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
dives | +0.110 |
drift | +0.108 |
irm | +0.107 |
ls | +0.107 |
ares | +0.104 |
Neg logit contributions | |
painter | -0.083 |
mill | -0.082 |
ini | -0.076 |
office | -0.070 |
ting | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
ust | +0.043 |
irm | +0.043 |
drift | +0.043 |
dives | +0.041 |
hops | +0.040 |
Neg logit contributions | |
ting | -0.044 |
mill | -0.044 |
painter | -0.041 |
paramed | -0.040 |
laund | -0.038 |
Token | Tim |
Token ID | 5045 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
mill | +0.073 |
ting | +0.073 |
painter | +0.069 |
ini | +0.066 |
paramed | +0.065 |
Neg logit contributions | |
drift | -0.069 |
dives | -0.069 |
irm | -0.068 |
nap | -0.067 |
much | -0.067 |
Token | my |
Token ID | 1820 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ting | +0.050 |
mill | +0.049 |
painter | +0.045 |
paramed | +0.045 |
cut | +0.044 |
Neg logit contributions | |
much | -0.067 |
nap | -0.067 |
dives | -0.066 |
drift | -0.066 |
irm | -0.065 |
Token | 's |
Token ID | 338 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
ting | +0.046 |
mill | +0.046 |
painter | +0.044 |
ini | +0.044 |
paramed | +0.043 |
Neg logit contributions | |
much | -0.034 |
dives | -0.034 |
drift | -0.033 |
nap | -0.033 |
irm | -0.032 |
Token | friend |
Token ID | 1545 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
nap | +0.030 |
much | +0.028 |
dives | +0.026 |
drift | +0.026 |
swim | +0.026 |
Neg logit contributions | |
ting | -0.056 |
cut | -0.052 |
mill | -0.051 |
years | -0.051 |
ini | -0.051 |
Token | came |
Token ID | 1625 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
ting | +0.084 |
mill | +0.083 |
painter | +0.082 |
paramed | +0.078 |
ini | +0.077 |
Neg logit contributions | |
drift | -0.069 |
irm | -0.068 |
dives | -0.068 |
much | -0.067 |
nap | -0.066 |
Token | over |
Token ID | 625 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ting | +0.010 |
painter | +0.010 |
mill | +0.009 |
office | +0.009 |
ini | +0.009 |
Neg logit contributions | |
drift | -0.013 |
nap | -0.012 |
ls | -0.012 |
dives | -0.012 |
irm | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
much | +0.039 |
nap | +0.038 |
dives | +0.038 |
drift | +0.036 |
irm | +0.035 |
Neg logit contributions | |
mill | -0.068 |
ting | -0.067 |
ini | -0.066 |
painter | -0.065 |
cut | -0.064 |
Token | play |
Token ID | 711 |
Feature activation | +2.59e-03 |
Pos logit contributions | |
mill | +0.084 |
ini | +0.084 |
ting | +0.083 |
floors | +0.081 |
rom | +0.080 |
Neg logit contributions | |
swim | -0.045 |
nap | -0.045 |
drift | -0.043 |
dive | -0.042 |
dives | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
ting | +0.005 |
mill | +0.005 |
painter | +0.005 |
ini | +0.005 |
office | +0.005 |
Neg logit contributions | |
much | -0.003 |
drift | -0.003 |
dives | -0.003 |
nap | -0.003 |
irm | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
much | +0.160 |
drift | +0.154 |
nap | +0.152 |
dives | +0.151 |
irm | +0.144 |
Neg logit contributions | |
ting | -0.301 |
mill | -0.299 |
ini | -0.290 |
painter | -0.289 |
paramed | -0.281 |
Token | they |
Token ID | 484 |
Feature activation | -7.71e-02 |
Pos logit contributions | |
ting | +0.117 |
mill | +0.117 |
painter | +0.113 |
ini | +0.112 |
paramed | +0.109 |
Neg logit contributions | |
much | -0.041 |
drift | -0.040 |
dives | -0.040 |
nap | -0.040 |
irm | -0.038 |
Token | were |
Token ID | 547 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
much | +0.095 |
drift | +0.092 |
nap | +0.088 |
dives | +0.087 |
dive | +0.084 |
Neg logit contributions | |
ting | -0.149 |
mill | -0.144 |
ini | -0.141 |
paramed | -0.137 |
painter | -0.136 |
Token | able |
Token ID | 1498 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ting | +0.050 |
mill | +0.049 |
ini | +0.048 |
painter | +0.047 |
paramed | +0.046 |
Neg logit contributions | |
much | -0.025 |
drift | -0.023 |
dives | -0.023 |
nap | -0.022 |
irm | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
drift | +0.051 |
dives | +0.050 |
irm | +0.050 |
nap | +0.049 |
hops | +0.048 |
Neg logit contributions | |
mill | -0.053 |
ting | -0.051 |
painter | -0.051 |
office | -0.048 |
ini | -0.048 |
Token | build |
Token ID | 1382 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
ting | +0.088 |
mill | +0.079 |
years | +0.078 |
ini | +0.078 |
paramed | +0.077 |
Neg logit contributions | |
nap | -0.059 |
much | -0.059 |
drift | -0.058 |
dive | -0.058 |
swim | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
mill | +0.121 |
ting | +0.121 |
painter | +0.116 |
ini | +0.114 |
office | +0.112 |
Neg logit contributions | |
drift | -0.088 |
much | -0.088 |
dives | -0.088 |
nap | -0.087 |
irm | -0.086 |
Token | house |
Token ID | 2156 |
Feature activation | +6.85e-02 |
Pos logit contributions | |
ting | +0.085 |
years | +0.071 |
stick | +0.071 |
cut | +0.067 |
paramed | +0.067 |
Neg logit contributions | |
much | -0.111 |
nap | -0.107 |
drift | -0.100 |
dives | -0.098 |
time | -0.097 |
Token | in |
Token ID | 287 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ting | +0.133 |
mill | +0.133 |
painter | +0.128 |
ini | +0.126 |
paramed | +0.123 |
Neg logit contributions | |
much | -0.076 |
drift | -0.074 |
dives | -0.074 |
nap | -0.074 |
irm | -0.072 |
Token | no |
Token ID | 645 |
Feature activation | +5.64e-03 |
Pos logit contributions | |
much | +0.062 |
nap | +0.056 |
drift | +0.054 |
dives | +0.051 |
dive | +0.050 |
Neg logit contributions | |
ting | -0.086 |
ini | -0.080 |
mill | -0.079 |
paramed | -0.078 |
painter | -0.077 |
Token | time |
Token ID | 640 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
mill | +0.013 |
painter | +0.013 |
ting | +0.013 |
office | +0.012 |
floors | +0.012 |
Neg logit contributions | |
ls | -0.004 |
ust | -0.004 |
dives | -0.004 |
drift | -0.004 |
irm | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
much | +0.049 |
nap | +0.046 |
drift | +0.045 |
dives | +0.044 |
irm | +0.043 |
Neg logit contributions | |
ting | -0.119 |
mill | -0.119 |
painter | -0.115 |
ini | -0.114 |
cut | -0.110 |
Token | Her |
Token ID | 9360 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
much | +0.084 |
nap | +0.080 |
irm | +0.077 |
ust | +0.076 |
drift | +0.076 |
Neg logit contributions | |
ting | -0.086 |
mill | -0.084 |
ini | -0.078 |
painter | -0.077 |
cut | -0.075 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
much | +0.016 |
nap | +0.016 |
dives | +0.016 |
drift | +0.016 |
irm | +0.015 |
Neg logit contributions | |
ting | -0.021 |
mill | -0.020 |
ini | -0.019 |
painter | -0.019 |
cut | -0.018 |
Token | came |
Token ID | 1625 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
mill | +0.197 |
ini | +0.190 |
painter | +0.185 |
keeping | +0.184 |
ting | +0.183 |
Neg logit contributions | |
much | -0.124 |
drift | -0.121 |
nap | -0.118 |
dives | -0.114 |
irm | -0.109 |
Token | to |
Token ID | 284 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
mill | +0.020 |
ini | +0.020 |
ting | +0.019 |
cut | +0.019 |
painter | +0.019 |
Neg logit contributions | |
much | -0.012 |
nap | -0.012 |
dives | -0.012 |
drift | -0.012 |
irm | -0.011 |
Token | help |
Token ID | 1037 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ini | +0.089 |
mill | +0.088 |
ting | +0.085 |
cles | +0.085 |
cut | +0.085 |
Neg logit contributions | |
nap | -0.050 |
drift | -0.046 |
swim | -0.046 |
much | -0.042 |
dive | -0.041 |
Token | her |
Token ID | 607 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
mill | +0.068 |
ting | +0.066 |
ini | +0.065 |
painter | +0.064 |
cut | +0.062 |
Neg logit contributions | |
much | -0.052 |
nap | -0.051 |
drift | -0.050 |
dives | -0.048 |
irm | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
much | +0.041 |
dives | +0.040 |
drift | +0.040 |
nap | +0.040 |
irm | +0.039 |
Neg logit contributions | |
mill | -0.060 |
ting | -0.060 |
painter | -0.058 |
ini | -0.057 |
office | -0.056 |
Token | said |
Token ID | 531 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
much | +0.030 |
drift | +0.028 |
nap | +0.027 |
dives | +0.027 |
irm | +0.026 |
Neg logit contributions | |
ting | -0.062 |
mill | -0.062 |
ini | -0.060 |
painter | -0.060 |
pavement | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
much | +0.046 |
nap | +0.043 |
drift | +0.043 |
dives | +0.042 |
irm | +0.040 |
Neg logit contributions | |
ting | -0.096 |
mill | -0.096 |
ini | -0.094 |
painter | -0.093 |
office | -0.089 |
Token | " |
Token ID | 366 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ini | +0.082 |
mill | +0.079 |
painter | +0.076 |
ting | +0.076 |
keeping | +0.074 |
Neg logit contributions | |
much | -0.076 |
drift | -0.071 |
nap | -0.067 |
they | -0.067 |
okay | -0.067 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ting | +0.020 |
mill | +0.020 |
painter | +0.020 |
ini | +0.020 |
paramed | +0.019 |
Neg logit contributions | |
much | -0.011 |
nap | -0.011 |
dives | -0.010 |
drift | -0.010 |
dive | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
mill | +0.042 |
ting | +0.041 |
painter | +0.040 |
ini | +0.040 |
paramed | +0.039 |
Neg logit contributions | |
much | -0.026 |
drift | -0.025 |
nap | -0.025 |
dives | -0.025 |
irm | -0.023 |
Token | Would |
Token ID | 10928 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
much | +0.008 |
drift | +0.008 |
dives | +0.008 |
nap | +0.008 |
irm | +0.008 |
Neg logit contributions | |
mill | -0.011 |
ting | -0.011 |
painter | -0.010 |
ini | -0.010 |
paramed | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
ting | +0.059 |
mill | +0.058 |
painter | +0.056 |
ini | +0.055 |
office | +0.053 |
Neg logit contributions | |
drift | -0.036 |
much | -0.036 |
dives | -0.036 |
nap | -0.036 |
irm | -0.036 |
Token | like |
Token ID | 588 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ls | +0.090 |
irm | +0.088 |
dives | +0.088 |
drift | +0.087 |
much | +0.084 |
Neg logit contributions | |
painter | -0.095 |
ting | -0.094 |
mill | -0.092 |
ini | -0.088 |
office | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
ini | +0.079 |
ting | +0.078 |
mill | +0.078 |
paramed | +0.075 |
painter | +0.075 |
Neg logit contributions | |
much | -0.041 |
nap | -0.041 |
dives | -0.038 |
drift | -0.037 |
dive | -0.037 |
Token | play |
Token ID | 711 |
Feature activation | +4.56e-03 |
Pos logit contributions | |
mill | +0.082 |
ting | +0.082 |
painter | +0.079 |
ini | +0.077 |
office | +0.075 |
Neg logit contributions | |
much | -0.047 |
dives | -0.047 |
drift | -0.046 |
irm | -0.045 |
nap | -0.045 |
Token | too |
Token ID | 1165 |
Feature activation | -9.55e-02 |
Pos logit contributions | |
mill | +0.009 |
ting | +0.009 |
ini | +0.009 |
painter | +0.009 |
paramed | +0.009 |
Neg logit contributions | |
much | -0.005 |
nap | -0.005 |
dives | -0.005 |
drift | -0.005 |
irm | -0.004 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.87e-02 |
Pos logit contributions | |
drift | +0.146 |
dives | +0.145 |
much | +0.145 |
nap | +0.143 |
irm | +0.142 |
Neg logit contributions | |
mill | -0.145 |
ting | -0.144 |
painter | -0.138 |
ini | -0.135 |
office | -0.131 |
Token |
|
Token ID | 198 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
ting | +0.140 |
mill | +0.140 |
painter | +0.136 |
ini | +0.134 |
paramed | +0.130 |
Neg logit contributions | |
much | -0.070 |
drift | -0.068 |
dives | -0.068 |
nap | -0.068 |
irm | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
much | +0.048 |
drift | +0.045 |
nap | +0.045 |
dives | +0.045 |
irm | +0.043 |
Neg logit contributions | |
ting | -0.115 |
mill | -0.114 |
painter | -0.110 |
ini | -0.109 |
office | -0.106 |
Token | ily |
Token ID | 813 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
drift | +0.004 |
much | +0.004 |
dives | +0.004 |
nap | +0.004 |
irm | +0.004 |
Neg logit contributions | |
ting | -0.003 |
mill | -0.003 |
painter | -0.003 |
ini | -0.003 |
office | -0.003 |
Token | didn |
Token ID | 1422 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ting | +0.062 |
mill | +0.060 |
ini | +0.058 |
painter | +0.058 |
paramed | +0.056 |
Neg logit contributions | |
much | -0.049 |
dives | -0.048 |
drift | -0.047 |
nap | -0.047 |
irm | -0.046 |
Token | 't |
Token ID | 470 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
mill | +0.088 |
ting | +0.087 |
painter | +0.083 |
rom | +0.082 |
paramed | +0.081 |
Neg logit contributions | |
irm | -0.100 |
dives | -0.099 |
drift | -0.096 |
hops | -0.096 |
nap | -0.093 |
Token | like |
Token ID | 588 |
Feature activation | +4.11e-02 |
Pos logit contributions | |
ls | +0.074 |
dives | +0.071 |
irm | +0.069 |
drift | +0.069 |
hops | +0.064 |
Neg logit contributions | |
painter | -0.111 |
ting | -0.105 |
mill | -0.101 |
owl | -0.101 |
paramed | -0.098 |
Token | bugs |
Token ID | 11316 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
ini | +0.084 |
rom | +0.081 |
cut | +0.080 |
paramed | +0.079 |
cles | +0.078 |
Neg logit contributions | |
much | -0.052 |
nap | -0.048 |
dives | -0.046 |
dive | -0.044 |
time | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
ting | +0.056 |
mill | +0.054 |
painter | +0.052 |
ini | +0.050 |
cut | +0.049 |
Neg logit contributions | |
dives | -0.035 |
much | -0.035 |
drift | -0.035 |
irm | -0.034 |
nap | -0.033 |
Token | so |
Token ID | 523 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
ini | +0.106 |
mill | +0.105 |
ting | +0.104 |
painter | +0.104 |
paramed | +0.100 |
Neg logit contributions | |
much | -0.046 |
nap | -0.043 |
drift | -0.043 |
dives | -0.042 |
irm | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
much | +0.051 |
dives | +0.050 |
drift | +0.050 |
nap | +0.050 |
irm | +0.049 |
Neg logit contributions | |
ting | -0.085 |
mill | -0.085 |
painter | -0.082 |
ini | -0.080 |
paramed | -0.078 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
much | +0.080 |
drift | +0.079 |
nap | +0.078 |
dives | +0.077 |
irm | +0.076 |
Neg logit contributions | |
mill | -0.076 |
ting | -0.076 |
painter | -0.073 |
ini | -0.070 |
paramed | -0.069 |
Token | her |
Token ID | 607 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ini | +0.047 |
mill | +0.044 |
laund | +0.041 |
ting | +0.041 |
rom | +0.041 |
Neg logit contributions | |
much | -0.026 |
nap | -0.023 |
drift | -0.022 |
okay | -0.021 |
OK | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
much | +0.046 |
nap | +0.045 |
dives | +0.043 |
drift | +0.043 |
swim | +0.041 |
Neg logit contributions | |
ting | -0.070 |
mill | -0.067 |
ini | -0.066 |
rom | -0.063 |
pavement | -0.063 |
Token | made |
Token ID | 925 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
ting | +0.023 |
painter | +0.023 |
mill | +0.023 |
ini | +0.021 |
office | +0.021 |
Neg logit contributions | |
much | -0.021 |
drift | -0.021 |
dives | -0.021 |
irm | -0.020 |
ust | -0.020 |
Token | her |
Token ID | 607 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
ting | +0.065 |
mill | +0.064 |
painter | +0.064 |
office | +0.061 |
ini | +0.060 |
Neg logit contributions | |
drift | -0.049 |
dives | -0.048 |
irm | -0.047 |
ust | -0.047 |
nap | -0.046 |
Token | flower |
Token ID | 15061 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
dives | +0.049 |
irm | +0.049 |
drift | +0.049 |
ust | +0.049 |
much | +0.046 |
Neg logit contributions | |
painter | -0.061 |
office | -0.057 |
mill | -0.055 |
ting | -0.052 |
ini | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-05 |
Pos logit contributions | |
dives | +0.002 |
irm | +0.002 |
ust | +0.002 |
drift | +0.002 |
much | +0.002 |
Neg logit contributions | |
painter | -0.002 |
mill | -0.002 |
office | -0.002 |
ting | -0.002 |
ini | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
painter | +0.000 |
mill | +0.000 |
ting | +0.000 |
Why | +0.000 |
paramed | +0.000 |
Neg logit contributions | |
drift | -0.000 |
dives | -0.000 |
nap | -0.000 |
dive | -0.000 |
irm | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
much | +0.056 |
drift | +0.055 |
dives | +0.055 |
nap | +0.054 |
irm | +0.053 |
Neg logit contributions | |
mill | -0.115 |
ting | -0.115 |
painter | -0.111 |
ini | -0.110 |
office | -0.107 |
Token | The |
Token ID | 464 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
much | +0.088 |
nap | +0.084 |
drift | +0.084 |
dives | +0.084 |
irm | +0.082 |
Neg logit contributions | |
mill | -0.089 |
ting | -0.088 |
painter | -0.084 |
ini | -0.082 |
office | -0.080 |
Token | teacher |
Token ID | 4701 |
Feature activation | +9.82e-02 |
Pos logit contributions | |
ting | +0.104 |
mill | +0.100 |
ini | +0.097 |
rom | +0.094 |
cut | +0.093 |
Neg logit contributions | |
nap | -0.131 |
much | -0.129 |
dives | -0.123 |
drift | -0.120 |
hops | -0.117 |
Token | says |
Token ID | 1139 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
mill | +0.181 |
ting | +0.181 |
painter | +0.180 |
office | +0.172 |
paramed | +0.164 |
Neg logit contributions | |
much | -0.119 |
irm | -0.116 |
drift | -0.116 |
nap | -0.112 |
ust | -0.112 |
Token | , |
Token ID | 11 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
drift | +0.059 |
much | +0.059 |
dives | +0.058 |
irm | +0.058 |
nap | +0.058 |
Neg logit contributions | |
mill | -0.103 |
ting | -0.103 |
painter | -0.100 |
ini | -0.096 |
paramed | -0.096 |
Token | " |
Token ID | 366 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
ini | +0.102 |
keeping | +0.093 |
mill | +0.092 |
floors | +0.090 |
pavement | +0.088 |
Neg logit contributions | |
much | -0.064 |
they | -0.060 |
nap | -0.058 |
swim | -0.057 |
dives | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
much | +0.034 |
dives | +0.033 |
nap | +0.033 |
drift | +0.032 |
swim | +0.032 |
Neg logit contributions | |
ini | -0.071 |
ting | -0.068 |
mill | -0.067 |
painter | -0.066 |
rom | -0.065 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ting | +0.110 |
years | +0.108 |
paramed | +0.107 |
mill | +0.106 |
ini | +0.106 |
Neg logit contributions | |
nap | -0.080 |
much | -0.076 |
dives | -0.074 |
drift | -0.072 |
swim | -0.072 |
Token | rolled |
Token ID | 11686 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
mill | +0.016 |
ting | +0.016 |
painter | +0.015 |
cut | +0.014 |
office | +0.014 |
Neg logit contributions | |
drift | -0.015 |
irm | -0.015 |
dives | -0.015 |
much | -0.015 |
nap | -0.014 |
Token | away |
Token ID | 1497 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
much | +0.033 |
dives | +0.031 |
nap | +0.030 |
irm | +0.030 |
drift | +0.030 |
Neg logit contributions | |
mill | -0.063 |
ini | -0.063 |
painter | -0.062 |
ting | -0.061 |
paramed | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
dives | +0.010 |
drift | +0.010 |
irm | +0.010 |
nap | +0.010 |
hops | +0.009 |
Neg logit contributions | |
ting | -0.013 |
mill | -0.013 |
painter | -0.012 |
cut | -0.012 |
office | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
drift | +0.003 |
dives | +0.003 |
nap | +0.003 |
much | +0.003 |
irm | +0.003 |
Neg logit contributions | |
mill | -0.005 |
ting | -0.005 |
painter | -0.005 |
paramed | -0.004 |
ini | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
dives | +0.077 |
drift | +0.077 |
irm | +0.075 |
hops | +0.073 |
nap | +0.072 |
Neg logit contributions | |
mill | -0.096 |
painter | -0.092 |
ting | -0.091 |
ini | -0.090 |
rom | -0.090 |
Token | " |
Token ID | 1 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
drift | +0.077 |
dives | +0.077 |
nap | +0.076 |
much | +0.075 |
irm | +0.075 |
Neg logit contributions | |
mill | -0.096 |
ting | -0.094 |
painter | -0.091 |
ini | -0.089 |
paramed | -0.088 |
Token | Tom |
Token ID | 13787 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
mill | +0.211 |
ting | +0.200 |
ini | +0.195 |
office | +0.192 |
painter | +0.182 |
Neg logit contributions | |
much | -0.480 |
nap | -0.476 |
dives | -0.468 |
drift | -0.467 |
irm | -0.458 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
ting | +0.112 |
mill | +0.111 |
ini | +0.107 |
laund | +0.107 |
floors | +0.106 |
Neg logit contributions | |
much | -0.037 |
nap | -0.035 |
dives | -0.035 |
drift | -0.032 |
hops | -0.032 |
Token | you |
Token ID | 345 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
mill | +0.093 |
ting | +0.093 |
painter | +0.090 |
ini | +0.087 |
paramed | +0.086 |
Neg logit contributions | |
much | -0.060 |
drift | -0.059 |
dives | -0.059 |
irm | -0.058 |
nap | -0.057 |
Token | them |
Token ID | 606 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
much | +0.051 |
dives | +0.050 |
drift | +0.050 |
nap | +0.050 |
irm | +0.049 |
Neg logit contributions | |
mill | -0.049 |
ting | -0.049 |
painter | -0.047 |
ini | -0.046 |
paramed | -0.044 |
Token | hot |
Token ID | 3024 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
drift | +0.028 |
dives | +0.028 |
irm | +0.028 |
much | +0.027 |
hops | +0.027 |
Neg logit contributions | |
ting | -0.033 |
mill | -0.033 |
painter | -0.032 |
paramed | -0.030 |
office | -0.030 |
Token | chocolate |
Token ID | 11311 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
nap | +0.006 |
much | +0.006 |
dives | +0.006 |
drift | +0.006 |
irm | +0.006 |
Neg logit contributions | |
ting | -0.007 |
mill | -0.007 |
painter | -0.007 |
ini | -0.007 |
years | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
dives | +0.024 |
much | +0.023 |
drift | +0.023 |
irm | +0.023 |
nap | +0.023 |
Neg logit contributions | |
mill | -0.029 |
ting | -0.029 |
painter | -0.027 |
ini | -0.027 |
paramed | -0.027 |
Token | cookies |
Token ID | 14746 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
dives | +0.047 |
much | +0.046 |
drift | +0.046 |
irm | +0.046 |
ust | +0.045 |
Neg logit contributions | |
mill | -0.057 |
ting | -0.056 |
painter | -0.055 |
ini | -0.052 |
paramed | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
dives | +0.038 |
irm | +0.037 |
much | +0.037 |
drift | +0.037 |
ust | +0.036 |
Neg logit contributions | |
ting | -0.050 |
mill | -0.050 |
painter | -0.047 |
cut | -0.046 |
paramed | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
drift | +0.002 |
dives | +0.002 |
much | +0.002 |
nap | +0.002 |
irm | +0.002 |
Neg logit contributions | |
mill | -0.003 |
ting | -0.003 |
painter | -0.003 |
ini | -0.003 |
paramed | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
mill | +0.002 |
painter | +0.002 |
ting | +0.002 |
office | +0.002 |
ini | +0.002 |
Neg logit contributions | |
dives | -0.002 |
irm | -0.002 |
drift | -0.002 |
much | -0.002 |
ust | -0.002 |
Token | kind |
Token ID | 1611 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
painter | +0.060 |
ting | +0.060 |
mill | +0.060 |
paramed | +0.058 |
office | +0.058 |
Neg logit contributions | |
dives | -0.043 |
drift | -0.042 |
hops | -0.041 |
nap | -0.041 |
irm | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ting | +0.110 |
mill | +0.109 |
painter | +0.105 |
ini | +0.104 |
paramed | +0.100 |
Neg logit contributions | |
much | -0.076 |
drift | -0.075 |
dives | -0.075 |
nap | -0.074 |
irm | -0.072 |
Token | loving |
Token ID | 14442 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
dives | +0.041 |
drift | +0.041 |
nap | +0.040 |
much | +0.040 |
irm | +0.040 |
Neg logit contributions | |
mill | -0.064 |
ting | -0.064 |
painter | -0.062 |
ini | -0.061 |
paramed | -0.059 |
Token | when |
Token ID | 618 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
mill | +0.089 |
ting | +0.089 |
ini | +0.087 |
cut | +0.085 |
painter | +0.083 |
Neg logit contributions | |
much | -0.065 |
nap | -0.060 |
drift | -0.058 |
dives | -0.056 |
irm | -0.054 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
much | +0.059 |
drift | +0.058 |
dives | +0.058 |
nap | +0.057 |
irm | +0.056 |
Neg logit contributions | |
ting | -0.072 |
mill | -0.072 |
painter | -0.069 |
ini | -0.068 |
paramed | -0.066 |
Token | was |
Token ID | 373 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
ting | +0.027 |
mill | +0.027 |
cut | +0.026 |
ini | +0.026 |
paramed | +0.026 |
Neg logit contributions | |
nap | -0.017 |
drift | -0.016 |
dives | -0.015 |
much | -0.015 |
irm | -0.015 |
Token | using |
Token ID | 1262 |
Feature activation | +7.66e-03 |
Pos logit contributions | |
ting | +0.047 |
mill | +0.047 |
painter | +0.045 |
ini | +0.044 |
paramed | +0.042 |
Neg logit contributions | |
much | -0.048 |
dives | -0.047 |
drift | -0.047 |
nap | -0.047 |
irm | -0.046 |
Token | her |
Token ID | 607 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
ting | +0.013 |
mill | +0.013 |
ini | +0.013 |
painter | +0.012 |
paramed | +0.012 |
Neg logit contributions | |
much | -0.011 |
nap | -0.011 |
drift | -0.011 |
dives | -0.010 |
irm | -0.010 |
Token | brush |
Token ID | 14093 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
nap | +0.053 |
much | +0.051 |
drift | +0.051 |
dives | +0.050 |
irm | +0.048 |
Neg logit contributions | |
ting | -0.050 |
mill | -0.047 |
ini | -0.046 |
cut | -0.045 |
paramed | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
ting | +0.063 |
mill | +0.063 |
ini | +0.062 |
painter | +0.061 |
paramed | +0.060 |
Neg logit contributions | |
much | -0.031 |
nap | -0.030 |
drift | -0.029 |
dives | -0.026 |
irm | -0.026 |
Token | she |
Token ID | 673 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
ting | +0.107 |
mill | +0.106 |
ini | +0.105 |
cut | +0.100 |
paramed | +0.100 |
Neg logit contributions | |
much | -0.051 |
nap | -0.044 |
drift | -0.042 |
dives | -0.038 |
they | -0.037 |
Token | heard |
Token ID | 2982 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
much | +0.061 |
nap | +0.058 |
dives | +0.057 |
drift | +0.055 |
hops | +0.053 |
Neg logit contributions | |
ting | -0.088 |
mill | -0.083 |
cut | -0.081 |
ican | -0.080 |
paramed | -0.080 |
Token | a |
Token ID | 257 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
mill | +0.151 |
ini | +0.150 |
ting | +0.146 |
cut | +0.144 |
painter | +0.141 |
Neg logit contributions | |
much | -0.065 |
nap | -0.052 |
drift | -0.049 |
dives | -0.045 |
time | -0.042 |
Token | loud |
Token ID | 7812 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
much | +0.087 |
drift | +0.083 |
nap | +0.082 |
dives | +0.080 |
swim | +0.077 |
Neg logit contributions | |
ting | -0.144 |
mill | -0.137 |
ini | -0.137 |
keeping | -0.133 |
painter | -0.132 |
Token | away |
Token ID | 1497 |
Feature activation | -9.50e-03 |
Pos logit contributions | |
ting | +0.027 |
office | +0.024 |
stick | +0.024 |
mill | +0.024 |
rom | +0.023 |
Neg logit contributions | |
dives | -0.023 |
drift | -0.022 |
hops | -0.022 |
much | -0.021 |
irm | -0.021 |
Token | from |
Token ID | 422 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
dives | +0.014 |
irm | +0.013 |
nap | +0.013 |
drift | +0.013 |
hops | +0.012 |
Neg logit contributions | |
ting | -0.017 |
mill | -0.016 |
painter | -0.015 |
cut | -0.015 |
office | -0.015 |
Token | him |
Token ID | 683 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
nap | +0.078 |
much | +0.076 |
drift | +0.071 |
swim | +0.070 |
dives | +0.068 |
Neg logit contributions | |
ini | -0.162 |
paramed | -0.152 |
mill | -0.147 |
painter | -0.143 |
laund | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
dives | +0.021 |
much | +0.020 |
drift | +0.020 |
irm | +0.020 |
nap | +0.019 |
Neg logit contributions | |
ting | -0.032 |
mill | -0.031 |
painter | -0.030 |
office | -0.029 |
ini | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
much | +0.002 |
nap | +0.002 |
dives | +0.002 |
drift | +0.002 |
irm | +0.002 |
Neg logit contributions | |
ini | -0.005 |
ting | -0.005 |
mill | -0.005 |
painter | -0.004 |
cut | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
much | +0.050 |
drift | +0.047 |
nap | +0.047 |
dives | +0.047 |
irm | +0.044 |
Neg logit contributions | |
ting | -0.119 |
mill | -0.118 |
painter | -0.115 |
ini | -0.114 |
paramed | -0.110 |
Token | But |
Token ID | 1537 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
much | +0.077 |
nap | +0.070 |
dives | +0.068 |
drift | +0.067 |
irm | +0.067 |
Neg logit contributions | |
ting | -0.094 |
mill | -0.092 |
ini | -0.092 |
painter | -0.089 |
smith | -0.087 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
mill | +0.078 |
ting | +0.077 |
painter | +0.075 |
ini | +0.074 |
paramed | +0.071 |
Neg logit contributions | |
much | -0.051 |
drift | -0.050 |
dives | -0.049 |
nap | -0.049 |
irm | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
mill | +0.024 |
ting | +0.024 |
ini | +0.023 |
painter | +0.023 |
paramed | +0.022 |
Neg logit contributions | |
much | -0.015 |
nap | -0.015 |
dives | -0.015 |
drift | -0.015 |
irm | -0.014 |
Token | stronger |
Token ID | 7387 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
ting | +0.057 |
painter | +0.055 |
years | +0.055 |
mill | +0.054 |
Why | +0.054 |
Neg logit contributions | |
drift | -0.037 |
dives | -0.035 |
irm | -0.032 |
hops | -0.032 |
nap | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
much | +0.054 |
dives | +0.052 |
nap | +0.052 |
drift | +0.052 |
irm | +0.050 |
Neg logit contributions | |
mill | -0.088 |
ting | -0.088 |
painter | -0.085 |
ini | -0.085 |
paramed | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
drift | +0.007 |
dives | +0.007 |
much | +0.007 |
nap | +0.007 |
irm | +0.007 |
Neg logit contributions | |
mill | -0.011 |
ting | -0.011 |
painter | -0.011 |
ini | -0.011 |
rom | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
dives | +0.069 |
drift | +0.069 |
irm | +0.067 |
nap | +0.066 |
much | +0.064 |
Neg logit contributions | |
mill | -0.113 |
ting | -0.110 |
painter | -0.109 |
ini | -0.108 |
rom | -0.105 |
Token | One |
Token ID | 3198 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
much | +0.068 |
drift | +0.065 |
nap | +0.065 |
dives | +0.065 |
irm | +0.062 |
Neg logit contributions | |
ting | -0.117 |
mill | -0.116 |
painter | -0.112 |
ini | -0.110 |
office | -0.108 |
Token | day |
Token ID | 1110 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
irm | +0.118 |
ls | +0.117 |
ares | +0.115 |
drift | +0.113 |
dives | +0.112 |
Neg logit contributions | |
mill | -0.073 |
painter | -0.071 |
office | -0.069 |
ini | -0.060 |
paramed | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +4.78e-02 |
Pos logit contributions | |
ust | +0.050 |
irm | +0.049 |
drift | +0.048 |
dives | +0.045 |
nap | +0.044 |
Neg logit contributions | |
ting | -0.043 |
mill | -0.042 |
painter | -0.040 |
laund | -0.037 |
ter | -0.036 |
Token | they |
Token ID | 484 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
ting | +0.097 |
mill | +0.097 |
painter | +0.094 |
laund | +0.089 |
Why | +0.089 |
Neg logit contributions | |
drift | -0.050 |
dives | -0.049 |
irm | -0.048 |
hops | -0.047 |
ust | -0.046 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
much | +0.130 |
nap | +0.127 |
drift | +0.127 |
dives | +0.127 |
irm | +0.123 |
Neg logit contributions | |
ting | -0.121 |
mill | -0.120 |
ini | -0.114 |
painter | -0.114 |
paramed | -0.109 |
Token | a |
Token ID | 257 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
ini | +0.305 |
ting | +0.301 |
cut | +0.285 |
painter | +0.283 |
mill | +0.282 |
Neg logit contributions | |
much | -0.091 |
dives | -0.063 |
nap | -0.061 |
they | -0.059 |
swim | -0.059 |
Token | new |
Token ID | 649 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
much | +0.075 |
nap | +0.072 |
dives | +0.067 |
swim | +0.066 |
dive | +0.065 |
Neg logit contributions | |
ting | -0.162 |
keeping | -0.150 |
years | -0.150 |
ini | -0.148 |
cles | -0.146 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
ting | +0.017 |
mill | +0.016 |
ini | +0.015 |
years | +0.015 |
painter | +0.015 |
Neg logit contributions | |
much | -0.019 |
nap | -0.018 |
dives | -0.018 |
drift | -0.018 |
dive | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
ting | +0.041 |
mill | +0.040 |
painter | +0.039 |
ini | +0.037 |
office | +0.037 |
Neg logit contributions | |
drift | -0.042 |
much | -0.042 |
dives | -0.041 |
nap | -0.041 |
irm | -0.041 |
Token | wet |
Token ID | 9583 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
dives | +0.032 |
drift | +0.032 |
irm | +0.032 |
nap | +0.032 |
ust | +0.032 |
Neg logit contributions | |
mill | -0.031 |
ting | -0.031 |
painter | -0.030 |
ini | -0.030 |
paramed | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -7.77e-03 |
Pos logit contributions | |
mill | +0.058 |
painter | +0.058 |
paramed | +0.056 |
ini | +0.056 |
office | +0.056 |
Neg logit contributions | |
much | -0.022 |
nap | -0.021 |
dives | -0.020 |
drift | -0.020 |
irm | -0.019 |
Token | When |
Token ID | 1649 |
Feature activation | -5.52e-02 |
Pos logit contributions | |
much | +0.011 |
nap | +0.011 |
drift | +0.011 |
dives | +0.011 |
irm | +0.011 |
Neg logit contributions | |
mill | -0.013 |
ting | -0.013 |
ini | -0.012 |
painter | -0.012 |
cut | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
dives | +0.063 |
much | +0.063 |
drift | +0.063 |
irm | +0.062 |
nap | +0.061 |
Neg logit contributions | |
mill | -0.106 |
ting | -0.105 |
painter | -0.101 |
ini | -0.098 |
office | -0.097 |
Token | got |
Token ID | 1392 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
ust | +0.093 |
much | +0.091 |
irm | +0.090 |
possible | +0.086 |
drift | +0.086 |
Neg logit contributions | |
mill | -0.059 |
ting | -0.054 |
laund | -0.050 |
Why | -0.049 |
painter | -0.048 |
Token | out |
Token ID | 503 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
mill | +0.006 |
ting | +0.006 |
painter | +0.005 |
office | +0.005 |
laund | +0.005 |
Neg logit contributions | |
drift | -0.006 |
ust | -0.006 |
dives | -0.006 |
irm | -0.005 |
hops | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
ust | +0.164 |
irm | +0.154 |
dives | +0.153 |
drift | +0.149 |
much | +0.144 |
Neg logit contributions | |
mill | -0.211 |
ting | -0.209 |
painter | -0.198 |
office | -0.196 |
ini | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | +5.90e-02 |
Pos logit contributions | |
nap | +0.021 |
much | +0.020 |
drift | +0.020 |
dives | +0.019 |
irm | +0.019 |
Neg logit contributions | |
ting | -0.025 |
ini | -0.024 |
mill | -0.024 |
painter | -0.024 |
rom | -0.023 |
Token | pool |
Token ID | 5933 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
mill | +0.079 |
ting | +0.073 |
ini | +0.070 |
floors | +0.068 |
laund | +0.068 |
Neg logit contributions | |
ust | -0.105 |
drift | -0.104 |
irm | -0.104 |
much | -0.102 |
hops | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
drift | +0.064 |
much | +0.064 |
dives | +0.063 |
irm | +0.063 |
nap | +0.061 |
Neg logit contributions | |
mill | -0.107 |
ting | -0.106 |
painter | -0.102 |
ini | -0.099 |
office | -0.098 |
Token | she |
Token ID | 673 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
mill | +0.103 |
ini | +0.103 |
ting | +0.102 |
painter | +0.099 |
cles | +0.099 |
Neg logit contributions | |
much | -0.045 |
nap | -0.044 |
drift | -0.041 |
dives | -0.039 |
irm | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
ares | +0.001 |
ust | +0.001 |
ls | +0.001 |
ver | +0.001 |
irm | +0.001 |
Neg logit contributions | |
mill | -0.001 |
office | -0.001 |
painter | -0.001 |
porch | -0.001 |
paramed | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
mill | +0.096 |
ting | +0.095 |
painter | +0.093 |
ini | +0.091 |
paramed | +0.089 |
Neg logit contributions | |
dives | -0.054 |
much | -0.053 |
irm | -0.052 |
ust | -0.052 |
ls | -0.052 |
Token | sleep |
Token ID | 3993 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
much | +0.027 |
dives | +0.026 |
ust | +0.026 |
irm | +0.025 |
drift | +0.025 |
Neg logit contributions | |
mill | -0.082 |
ting | -0.079 |
painter | -0.078 |
ini | -0.077 |
paramed | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | -4.30e-03 |
Pos logit contributions | |
much | +0.074 |
drift | +0.072 |
nap | +0.071 |
dives | +0.069 |
irm | +0.067 |
Neg logit contributions | |
mill | -0.129 |
ting | -0.128 |
painter | -0.126 |
ini | -0.124 |
paramed | -0.120 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ls | +0.007 |
dives | +0.006 |
irm | +0.006 |
hops | +0.006 |
nap | +0.006 |
Neg logit contributions | |
ting | -0.007 |
mill | -0.007 |
office | -0.007 |
painter | -0.006 |
Why | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
mill | +0.099 |
ting | +0.099 |
painter | +0.095 |
ini | +0.093 |
paramed | +0.090 |
Neg logit contributions | |
much | -0.091 |
drift | -0.089 |
dives | -0.089 |
nap | -0.089 |
irm | -0.086 |
Token | there |
Token ID | 612 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
dives | +0.160 |
irm | +0.159 |
drift | +0.156 |
fins | +0.146 |
hops | +0.146 |
Neg logit contributions | |
mill | -0.215 |
painter | -0.206 |
office | -0.198 |
ini | -0.196 |
rom | -0.194 |
Token | was |
Token ID | 373 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
much | +0.059 |
nap | +0.057 |
drift | +0.057 |
dives | +0.057 |
irm | +0.055 |
Neg logit contributions | |
ting | -0.068 |
mill | -0.068 |
painter | -0.065 |
ini | -0.064 |
paramed | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | -7.69e-02 |
Pos logit contributions | |
mill | +0.053 |
ting | +0.052 |
painter | +0.051 |
ini | +0.050 |
paramed | +0.049 |
Neg logit contributions | |
dives | -0.031 |
drift | -0.031 |
irm | -0.030 |
nap | -0.029 |
much | -0.029 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
much | +0.099 |
nap | +0.097 |
drift | +0.093 |
dives | +0.093 |
swim | +0.089 |
Neg logit contributions | |
ting | -0.142 |
mill | -0.135 |
ini | -0.130 |
rom | -0.128 |
keeping | -0.128 |
Token | named |
Token ID | 3706 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
ting | +0.044 |
mill | +0.042 |
pavement | +0.041 |
ini | +0.041 |
floors | +0.041 |
Neg logit contributions | |
much | -0.041 |
nap | -0.038 |
swim | -0.037 |
dive | -0.036 |
drift | -0.035 |
Token | ! |
Token ID | 0 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
much | +0.003 |
dives | +0.003 |
drift | +0.003 |
nap | +0.003 |
irm | +0.003 |
Neg logit contributions | |
ting | -0.005 |
mill | -0.005 |
painter | -0.005 |
ini | -0.005 |
office | -0.005 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ting | +0.037 |
mill | +0.036 |
painter | +0.035 |
rom | +0.034 |
ini | +0.034 |
Neg logit contributions | |
dives | -0.030 |
drift | -0.028 |
irm | -0.028 |
dive | -0.028 |
nap | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
mill | +0.107 |
ting | +0.106 |
painter | +0.102 |
ini | +0.101 |
paramed | +0.098 |
Neg logit contributions | |
much | -0.082 |
drift | -0.080 |
dives | -0.080 |
nap | -0.080 |
irm | -0.078 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
dives | +0.163 |
drift | +0.161 |
irm | +0.161 |
hops | +0.148 |
fins | +0.147 |
Neg logit contributions | |
mill | -0.213 |
painter | -0.208 |
ini | -0.196 |
office | -0.194 |
rom | -0.192 |
Token | a |
Token ID | 257 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
Why | +0.052 |
ting | +0.052 |
painter | +0.051 |
mill | +0.050 |
office | +0.049 |
Neg logit contributions | |
dives | -0.056 |
ls | -0.056 |
irm | -0.055 |
drift | -0.054 |
hops | -0.053 |
Token | time |
Token ID | 640 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ls | +0.092 |
ares | +0.085 |
dives | +0.084 |
drift | +0.079 |
disappears | +0.077 |
Neg logit contributions | |
mill | -0.124 |
painter | -0.121 |
Why | -0.119 |
porch | -0.116 |
neighborhood | -0.116 |
Token | there |
Token ID | 612 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
irm | +0.176 |
drift | +0.172 |
dives | +0.161 |
fy | +0.158 |
ust | +0.157 |
Neg logit contributions | |
mill | -0.135 |
painter | -0.125 |
ting | -0.122 |
office | -0.117 |
Why | -0.113 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
much | +0.054 |
nap | +0.053 |
drift | +0.053 |
dives | +0.052 |
irm | +0.050 |
Neg logit contributions | |
ting | -0.065 |
mill | -0.064 |
painter | -0.062 |
ini | -0.061 |
paramed | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -7.35e-02 |
Pos logit contributions | |
ting | +0.126 |
mill | +0.125 |
painter | +0.122 |
ini | +0.118 |
office | +0.116 |
Neg logit contributions | |
drift | -0.073 |
dives | -0.072 |
much | -0.070 |
irm | -0.069 |
nap | -0.068 |
Token | baby |
Token ID | 5156 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
much | +0.095 |
drift | +0.094 |
dives | +0.093 |
nap | +0.092 |
irm | +0.091 |
Neg logit contributions | |
mill | -0.129 |
ting | -0.129 |
painter | -0.125 |
ini | -0.122 |
paramed | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
pavement | +0.033 |
years | +0.033 |
laund | +0.033 |
Fighting | +0.033 |
cles | +0.033 |
Neg logit contributions | |
much | -0.025 |
nap | -0.024 |
swim | -0.023 |
they | -0.022 |
ls | -0.022 |
Token | When |
Token ID | 2215 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
much | +0.071 |
drift | +0.065 |
nap | +0.064 |
dives | +0.063 |
ust | +0.062 |
Neg logit contributions | |
ting | -0.097 |
mill | -0.094 |
painter | -0.091 |
ini | -0.089 |
pavement | -0.086 |
Token | they |
Token ID | 484 |
Feature activation | -7.84e-02 |
Pos logit contributions | |
irm | +0.097 |
dives | +0.093 |
ust | +0.093 |
hops | +0.090 |
nap | +0.086 |
Neg logit contributions | |
mill | -0.127 |
ting | -0.123 |
laund | -0.115 |
painter | -0.115 |
office | -0.115 |
Token | got |
Token ID | 1392 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
irm | +0.129 |
ls | +0.123 |
much | +0.122 |
ust | +0.119 |
dives | +0.117 |
Neg logit contributions | |
ting | -0.109 |
mill | -0.109 |
painter | -0.101 |
years | -0.099 |
laund | -0.097 |
Token | on |
Token ID | 319 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
mill | +0.007 |
ting | +0.006 |
painter | +0.006 |
office | +0.006 |
years | +0.006 |
Neg logit contributions | |
drift | -0.007 |
ust | -0.006 |
irm | -0.006 |
hops | -0.006 |
nap | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
much | +0.107 |
drift | +0.104 |
nap | +0.104 |
dives | +0.104 |
irm | +0.098 |
Neg logit contributions | |
ting | -0.127 |
ini | -0.124 |
mill | -0.123 |
painter | -0.123 |
cut | -0.117 |
Token | they |
Token ID | 484 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
mill | +0.080 |
ting | +0.079 |
painter | +0.075 |
rom | +0.074 |
laund | +0.073 |
Neg logit contributions | |
dives | -0.066 |
irm | -0.065 |
nap | -0.063 |
hops | -0.063 |
drift | -0.063 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
much | +0.119 |
drift | +0.117 |
dives | +0.117 |
nap | +0.116 |
irm | +0.114 |
Neg logit contributions | |
ting | -0.122 |
mill | -0.122 |
painter | -0.116 |
ini | -0.115 |
paramed | -0.110 |
Token | a |
Token ID | 257 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
ini | +0.270 |
painter | +0.257 |
ting | +0.253 |
paramed | +0.245 |
mill | +0.244 |
Neg logit contributions | |
much | -0.125 |
nap | -0.098 |
dives | -0.097 |
they | -0.095 |
drift | -0.090 |
Token | big |
Token ID | 1263 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
much | +0.085 |
nap | +0.083 |
dives | +0.075 |
swim | +0.074 |
drift | +0.074 |
Neg logit contributions | |
ting | -0.153 |
keeping | -0.141 |
ini | -0.138 |
years | -0.137 |
organized | -0.137 |
Token | box |
Token ID | 3091 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
ting | +0.026 |
ini | +0.025 |
years | +0.024 |
keeping | +0.024 |
rom | +0.024 |
Neg logit contributions | |
nap | -0.019 |
dives | -0.018 |
much | -0.018 |
dive | -0.018 |
swim | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
mill | +0.003 |
ting | +0.003 |
painter | +0.003 |
ini | +0.003 |
office | +0.003 |
Neg logit contributions | |
much | -0.002 |
dives | -0.002 |
drift | -0.002 |
nap | -0.002 |
irm | -0.002 |