TOP ACTIVATIONS
MAX = 7.121

some shells and rocks and seaw eed . He picked them
added shells and stones and seaw eed to make it look
like fish and shells and seaw eed . But they did
like fish and shells and seaw eed . One
shore , collecting shells and seaw eed . Jimmy took time
of shells , rocks and seaw eed , but Jane was
sk ates and helmets and pads . They use a puck
decorated it with shells and seaw eed . They had a
ate it with shells and seaw eed . They find a
Like shells and rocks and seaw eed ." M
buckets and shovel s and seaw eed . Then we can
saw five fish and seven seaw eed . They were happy
out of difficult and sticky situations . <|endoftext|> The family had
They went past rocks and seaw eed . They saw other
be happy . Even though situations can be serious , it
cand ies and fruits and vegetables and letters and numbers and
see shells , rocks , seaw eed , crabs and fish
shovel s and shells and stones . They worked hard and
pulled out vegetable scraps and weeds . He planted beautiful flowers
her collection of rocks and shells . They thanked her and

MIN ACTIVATIONS
MIN = -5.885

had measured the z ig zag line and the spicy pepper
can make the z ig zag another day . I 'm
back down the z ig zag branch and lay in the
The flood was gone the next day and the man took
walked on the z ig zag path . It went left
I have the z ig zag ?" M ama
bought the blue z ig zag . Tig was so happy
. <|endoftext|> Today was fog gy and grey . The fog
the rain drops z ig zag down the window . She
settled back into the go oe y mud . He was
would have to take the next one , but it was
never refused the z ig zag again . <|endoftext|> John had
mom brought the fortune - te ller toy home . When
they took it out the next day , the jelly was
up . It was the next day and he was feeling
When they took their next bite , the toast was
" Let 's set the timer for 30 minutes ," dad
The doctor put the st eth oscope on Molly 's chest
fly like the z ig zag if he just opened his
ready to take on the next adventure . <|endoftext|> Once upon

INTERVAL 3.870 - 7.121
CONTAINS 0.058%

each other 's hair and clothes . They are very loud
you are kind and help others , you can make them
of toys and books and clothes . But sometimes they do
decorations of all shapes and sizes . He noticed many were
stickers , colors , and drawings to decor ate her journal

INTERVAL 0.618 - 3.870
CONTAINS 23.278%

measure and she asked her parents to help . Her parents
and sphere spun around and around as fast as they could
you , thank you ," L ila and Tom say .
there was a small boy called Tony . He was only
ran , and they had fun . Blue 's old friends

INTERVAL -2.633 - 0.618
CONTAINS 75.845%

them and asked , " Tom , are you sure you
. " Okay . I will be more careful
, the earth slowly got brighter and brighter . Everyone smiled
farmer 's dog then jumped into the hole and picked up
. <|endoftext|> Once upon a time , there was a fine

INTERVAL -5.885 - -2.633
CONTAINS 0.818%

and looked for shells . One day , they saw a
two tiny fair ies . One was sick , and the
and have fun together . One day , the onion and
named Anna . She was three years old and liked to
also a bit scared . One day , she wanted to
Token some
Token ID617
Feature activation-1.30e+00

Pos logit contributions
aw+0.065
 regretted+0.064
 gol+0.063
opter+0.061
ime+0.056
Neg logit contributions
 first-0.034
 next-0.031
balls-0.027
 Mia-0.022
 one-0.022
Token shells
Token ID19679
Feature activation+3.30e+00

Pos logit contributions
 first+0.050
 next+0.048
balls+0.040
 last+0.037
 one+0.036
Neg logit contributions
 gol-0.063
aw-0.061
opter-0.061
 regretted-0.060
arre-0.056
Token and
Token ID290
Feature activation+2.82e-01

Pos logit contributions
aw+0.184
 regretted+0.173
 gol+0.168
opter+0.158
ime+0.149
Neg logit contributions
 first-0.120
 next-0.110
balls-0.097
ider-0.086
 last-0.080
Token rocks
Token ID12586
Feature activation+4.47e+00

Pos logit contributions
aw+0.013
 regretted+0.012
 gol+0.011
opter+0.010
ime+0.010
Neg logit contributions
 first-0.012
 next-0.011
balls-0.011
ider-0.010
 front-0.009
Token and
Token ID290
Feature activation+8.38e-01

Pos logit contributions
aw+0.252
 regretted+0.237
 gol+0.229
opter+0.218
ime+0.204
Neg logit contributions
 first-0.157
 next-0.143
balls-0.127
ider-0.113
 last-0.102
Token seaw
Token ID32085
Feature activation+7.12e+00

Pos logit contributions
aw+0.040
 regretted+0.036
 gol+0.035
opter+0.033
ime+0.031
Neg logit contributions
 first-0.036
 next-0.033
balls-0.031
ider-0.028
 one-0.026
Tokeneed
Token ID2308
Feature activation+3.69e+00

Pos logit contributions
aw+0.245
 regretted+0.235
 gol+0.215
opter+0.190
ime+0.180
Neg logit contributions
 first-0.375
balls-0.358
 next-0.352
ider-0.341
 hips-0.301
Token.
Token ID13
Feature activation+9.94e-02

Pos logit contributions
aw+0.221
 regretted+0.209
 gol+0.205
opter+0.194
ime+0.185
Neg logit contributions
 first-0.114
 next-0.104
balls-0.095
ider-0.083
 last-0.068
Token He
Token ID679
Feature activation+4.81e-01

Pos logit contributions
aw+0.004
 regretted+0.004
 gol+0.004
opter+0.003
ime+0.003
Neg logit contributions
 first-0.005
 next-0.004
balls-0.004
ider-0.004
 front-0.004
Token picked
Token ID6497
Feature activation+9.36e-02

Pos logit contributions
aw+0.023
 regretted+0.020
 gol+0.020
opter+0.019
ime+0.018
Neg logit contributions
 first-0.020
 next-0.019
balls-0.017
ider-0.016
 last-0.014
Token them
Token ID606
Feature activation-2.06e-01

Pos logit contributions
aw+0.005
 regretted+0.005
 gol+0.005
opter+0.004
ime+0.004
Neg logit contributions
 first-0.003
 next-0.003
ider-0.003
balls-0.003
 hips-0.002
Token added
Token ID2087
Feature activation-1.23e+00

Pos logit contributions
 first+0.027
 next+0.025
balls+0.023
ider+0.023
 last+0.019
Neg logit contributions
aw-0.032
 regretted-0.029
 gol-0.027
opter-0.025
ime-0.024
Token shells
Token ID19679
Feature activation+3.01e+00

Pos logit contributions
 first+0.040
 next+0.036
balls+0.031
 last+0.025
 one+0.025
Neg logit contributions
aw-0.070
 regretted-0.070
 gol-0.068
opter-0.065
ime-0.060
Token and
Token ID290
Feature activation-7.07e-01

Pos logit contributions
aw+0.159
 regretted+0.149
 gol+0.141
opter+0.133
ime+0.127
Neg logit contributions
 first-0.114
 next-0.104
balls-0.096
ider-0.088
 last-0.078
Token stones
Token ID14966
Feature activation+4.70e+00

Pos logit contributions
 first+0.033
 next+0.031
balls+0.029
ider+0.029
 particular+0.024
Neg logit contributions
aw-0.031
 regretted-0.027
 gol-0.026
opter-0.023
ime-0.022
Token and
Token ID290
Feature activation+5.18e-01

Pos logit contributions
aw+0.248
 regretted+0.230
 gol+0.219
opter+0.206
ime+0.196
Neg logit contributions
 first-0.177
 next-0.161
balls-0.149
ider-0.141
 last-0.119
Token seaw
Token ID32085
Feature activation+7.10e+00

Pos logit contributions
aw+0.024
 regretted+0.022
 gol+0.021
opter+0.020
ime+0.019
Neg logit contributions
 first-0.022
 next-0.021
balls-0.019
ider-0.018
 last-0.016
Tokeneed
Token ID2308
Feature activation+3.65e+00

Pos logit contributions
aw+0.247
 regretted+0.239
 gol+0.215
opter+0.193
ime+0.183
Neg logit contributions
 first-0.372
balls-0.352
 next-0.350
ider-0.335
 hips-0.294
Token to
Token ID284
Feature activation+1.46e+00

Pos logit contributions
aw+0.205
 regretted+0.193
 gol+0.185
opter+0.174
ime+0.167
Neg logit contributions
 first-0.125
 next-0.114
balls-0.105
ider-0.096
 last-0.080
Token make
Token ID787
Feature activation-1.11e+00

Pos logit contributions
aw+0.080
 regretted+0.073
 gol+0.070
opter+0.065
ime+0.063
Neg logit contributions
 first-0.052
 next-0.047
balls-0.044
ider-0.043
 front-0.034
Token it
Token ID340
Feature activation-7.37e-01

Pos logit contributions
 first+0.042
 next+0.038
balls+0.036
 Mia+0.029
 one+0.029
Neg logit contributions
 regretted-0.056
aw-0.056
 gol-0.053
opter-0.050
ime-0.046
Token look
Token ID804
Feature activation-1.90e+00

Pos logit contributions
 first+0.029
 next+0.027
ider+0.026
balls+0.025
 hips+0.022
Neg logit contributions
aw-0.036
 regretted-0.032
 gol-0.030
opter-0.028
ime-0.027
Token like
Token ID588
Feature activation+9.79e-01

Pos logit contributions
aw+0.001
 regretted+0.001
 gol+0.001
ime+0.001
 mustache+0.001
Neg logit contributions
 first-0.001
ider-0.001
balls-0.001
 next-0.001
 front-0.001
Token fish
Token ID5916
Feature activation+1.96e+00

Pos logit contributions
aw+0.046
 regretted+0.044
 gol+0.042
opter+0.039
ime+0.037
Neg logit contributions
 first-0.043
 next-0.039
balls-0.036
ider-0.032
 one-0.030
Token and
Token ID290
Feature activation+7.24e-01

Pos logit contributions
aw+0.105
 regretted+0.098
 gol+0.094
opter+0.088
ime+0.083
Neg logit contributions
 first-0.074
 next-0.067
balls-0.062
ider-0.057
 last-0.048
Token shells
Token ID19679
Feature activation+5.11e+00

Pos logit contributions
aw+0.032
 regretted+0.029
 gol+0.028
opter+0.026
ime+0.024
Neg logit contributions
 first-0.033
 next-0.031
balls-0.029
ider-0.028
 front-0.024
Token and
Token ID290
Feature activation+8.70e-01

Pos logit contributions
aw+0.303
 regretted+0.284
 gol+0.275
opter+0.259
ime+0.248
Neg logit contributions
 first-0.159
 next-0.142
balls-0.129
ider-0.119
 last-0.095
Token seaw
Token ID32085
Feature activation+7.08e+00

Pos logit contributions
aw+0.039
 regretted+0.035
 gol+0.034
opter+0.032
ime+0.030
Neg logit contributions
 first-0.040
 next-0.037
balls-0.034
ider-0.032
 last-0.029
Tokeneed
Token ID2308
Feature activation+3.51e+00

Pos logit contributions
aw+0.236
 regretted+0.213
 gol+0.196
opter+0.173
ime+0.160
Neg logit contributions
 first-0.396
 next-0.372
balls-0.363
ider-0.351
 hips-0.310
Token.
Token ID13
Feature activation+4.62e-01

Pos logit contributions
aw+0.204
 regretted+0.189
 gol+0.182
opter+0.171
ime+0.164
Neg logit contributions
 first-0.112
 next-0.100
balls-0.092
ider-0.087
 front-0.069
Token But
Token ID887
Feature activation-8.29e-01

Pos logit contributions
aw+0.024
 regretted+0.021
 gol+0.021
opter+0.018
ime+0.018
Neg logit contributions
 first-0.018
 next-0.016
balls-0.015
ider-0.015
 last-0.012
Token they
Token ID484
Feature activation-6.55e-02

Pos logit contributions
ider+0.025
balls+0.024
 first+0.023
 next+0.021
 hips+0.019
Neg logit contributions
aw-0.042
 regretted-0.041
 gol-0.038
opter-0.032
 mustache-0.032
Token did
Token ID750
Feature activation-3.37e-01

Pos logit contributions
 first+0.003
 next+0.002
balls+0.002
ider+0.002
 Mia+0.002
Neg logit contributions
aw-0.004
 gol-0.003
opter-0.003
 regretted-0.003
ime-0.003
Token like
Token ID588
Feature activation+9.24e-01

Pos logit contributions
aw+0.001
 regretted+0.001
 gol+0.001
opter+0.001
ime+0.001
Neg logit contributions
 first-0.001
 next-0.001
balls-0.001
ider-0.001
 front-0.001
Token fish
Token ID5916
Feature activation+1.95e+00

Pos logit contributions
aw+0.045
 regretted+0.044
 gol+0.041
opter+0.039
arre+0.037
Neg logit contributions
 first-0.039
 next-0.036
balls-0.033
 one-0.028
ider-0.028
Token and
Token ID290
Feature activation+7.06e-01

Pos logit contributions
aw+0.106
 regretted+0.100
 gol+0.097
opter+0.090
ime+0.085
Neg logit contributions
 first-0.072
 next-0.065
balls-0.060
ider-0.054
 last-0.046
Token shells
Token ID19679
Feature activation+5.04e+00

Pos logit contributions
aw+0.034
 regretted+0.030
 gol+0.029
opter+0.028
ime+0.026
Neg logit contributions
 first-0.031
 next-0.028
balls-0.026
ider-0.024
 last-0.022
Token and
Token ID290
Feature activation+8.24e-01

Pos logit contributions
aw+0.302
 regretted+0.285
 gol+0.276
opter+0.261
ime+0.249
Neg logit contributions
 first-0.155
 next-0.139
balls-0.125
ider-0.113
 last-0.092
Token seaw
Token ID32085
Feature activation+6.85e+00

Pos logit contributions
aw+0.039
 regretted+0.035
 gol+0.034
opter+0.032
ime+0.030
Neg logit contributions
 first-0.036
 next-0.033
balls-0.031
ider-0.028
 last-0.026
Tokeneed
Token ID2308
Feature activation+3.44e+00

Pos logit contributions
aw+0.232
 regretted+0.217
 gol+0.199
opter+0.176
ime+0.164
Neg logit contributions
 first-0.372
 next-0.349
balls-0.348
ider-0.333
 hips-0.293
Token.
Token ID13
Feature activation+4.33e-01

Pos logit contributions
aw+0.201
 regretted+0.186
 gol+0.179
opter+0.168
ime+0.161
Neg logit contributions
 first-0.110
 next-0.098
balls-0.090
ider-0.085
 last-0.067
Token
Token ID198
Feature activation-7.99e-02

Pos logit contributions
aw+0.022
 regretted+0.019
 gol+0.019
opter+0.016
ime+0.016
Neg logit contributions
 first-0.017
 next-0.016
ider-0.015
balls-0.015
 last-0.013
Token
Token ID198
Feature activation-5.77e-01

Pos logit contributions
 first+0.003
balls+0.003
ider+0.003
 next+0.003
 hips+0.003
Neg logit contributions
aw-0.004
 regretted-0.003
 gol-0.003
opter-0.003
ime-0.003
TokenOne
Token ID3198
Feature activation-4.01e+00

Pos logit contributions
 first+0.019
balls+0.018
 next+0.016
ider+0.016
 hips+0.015
Neg logit contributions
aw-0.032
 gol-0.028
 regretted-0.027
opter-0.026
ime-0.024
Token shore
Token ID15191
Feature activation+5.23e-01

Pos logit contributions
aw+0.052
 regretted+0.046
 gol+0.044
opter+0.041
ime+0.039
Neg logit contributions
 first-0.054
 next-0.050
balls-0.044
ider-0.040
 last-0.039
Token,
Token ID11
Feature activation+1.56e+00

Pos logit contributions
aw+0.029
 regretted+0.027
 gol+0.026
opter+0.025
ime+0.023
Neg logit contributions
 first-0.018
 next-0.017
balls-0.015
ider-0.014
 last-0.012
Token collecting
Token ID13157
Feature activation+9.25e-01

Pos logit contributions
aw+0.085
 regretted+0.078
 gol+0.074
opter+0.070
ime+0.067
Neg logit contributions
 first-0.055
 next-0.050
balls-0.046
ider-0.045
 front-0.037
Token shells
Token ID19679
Feature activation+3.67e+00

Pos logit contributions
 regretted+0.044
aw+0.043
 gol+0.042
opter+0.041
arre+0.038
Neg logit contributions
 first-0.037
 next-0.035
balls-0.029
 one-0.028
 some-0.027
Token and
Token ID290
Feature activation+4.16e-01

Pos logit contributions
aw+0.200
 regretted+0.189
 gol+0.181
opter+0.171
ime+0.161
Neg logit contributions
 first-0.134
 next-0.122
balls-0.110
ider-0.099
 last-0.089
Token seaw
Token ID32085
Feature activation+6.85e+00

Pos logit contributions
aw+0.021
 regretted+0.019
 gol+0.018
opter+0.017
ime+0.016
Neg logit contributions
 first-0.017
 next-0.016
balls-0.015
ider-0.013
 last-0.012
Tokeneed
Token ID2308
Feature activation+3.40e+00

Pos logit contributions
aw+0.237
 regretted+0.234
 gol+0.212
opter+0.189
ime+0.175
Neg logit contributions
 first-0.353
balls-0.337
 next-0.333
ider-0.321
 hips-0.281
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
aw+0.198
 regretted+0.187
 gol+0.180
opter+0.170
ime+0.162
Neg logit contributions
 first-0.111
 next-0.099
balls-0.092
ider-0.083
 last-0.068
Token Jimmy
Token ID12963
Feature activation+9.19e-01

Pos logit contributions
aw+0.014
 regretted+0.013
 gol+0.012
opter+0.012
ime+0.011
Neg logit contributions
 first-0.009
 next-0.008
balls-0.008
ider-0.007
 Mia-0.006
Token took
Token ID1718
Feature activation-2.75e-01

Pos logit contributions
aw+0.049
 gol+0.046
 regretted+0.044
opter+0.042
anes+0.040
Neg logit contributions
 first-0.034
 next-0.031
balls-0.026
ider-0.023
 one-0.022
Token time
Token ID640
Feature activation-4.10e-01

Pos logit contributions
 first+0.009
 next+0.008
balls+0.006
 one+0.006
 some+0.005
Neg logit contributions
aw-0.016
 regretted-0.016
 gol-0.015
opter-0.015
 perspective-0.014
Token of
Token ID286
Feature activation-7.44e-01

Pos logit contributions
aw+0.055
 regretted+0.049
 gol+0.046
opter+0.042
ime+0.040
Neg logit contributions
 first-0.060
 next-0.055
balls-0.052
ider-0.051
 front-0.044
Token shells
Token ID19679
Feature activation+3.13e+00

Pos logit contributions
 first+0.027
 next+0.025
 one+0.018
 some+0.017
 particular+0.017
Neg logit contributions
aw-0.038
 gol-0.038
 regretted-0.037
opter-0.036
ane-0.036
Token,
Token ID11
Feature activation+6.50e-01

Pos logit contributions
aw+0.169
 regretted+0.158
 gol+0.152
opter+0.142
ime+0.134
Neg logit contributions
 first-0.117
 next-0.106
balls-0.096
ider-0.088
 last-0.078
Token rocks
Token ID12586
Feature activation+3.90e+00

Pos logit contributions
aw+0.030
 regretted+0.028
 gol+0.026
opter+0.024
ime+0.023
Neg logit contributions
 first-0.029
 next-0.026
balls-0.025
ider-0.023
 front-0.021
Token and
Token ID290
Feature activation+4.61e-01

Pos logit contributions
aw+0.214
 regretted+0.201
 gol+0.193
opter+0.179
ime+0.169
Neg logit contributions
 first-0.145
 next-0.130
balls-0.117
ider-0.106
 last-0.096
Token seaw
Token ID32085
Feature activation+6.75e+00

Pos logit contributions
aw+0.022
 regretted+0.020
 gol+0.019
opter+0.018
ime+0.017
Neg logit contributions
 first-0.020
 next-0.018
balls-0.017
ider-0.016
 front-0.014
Tokeneed
Token ID2308
Feature activation+3.29e+00

Pos logit contributions
 regretted+0.236
aw+0.236
 gol+0.211
opter+0.188
ime+0.178
Neg logit contributions
 first-0.347
balls-0.332
 next-0.324
ider-0.314
 hips-0.276
Token,
Token ID11
Feature activation+1.64e+00

Pos logit contributions
aw+0.188
 regretted+0.176
 gol+0.170
opter+0.159
ime+0.152
Neg logit contributions
 first-0.112
 next-0.100
balls-0.093
ider-0.084
 last-0.070
Token but
Token ID475
Feature activation+7.90e-01

Pos logit contributions
aw+0.089
 regretted+0.083
 gol+0.079
opter+0.076
ime+0.071
Neg logit contributions
 first-0.061
 next-0.056
balls-0.050
ider-0.046
 front-0.040
Token Jane
Token ID12091
Feature activation+5.20e-01

Pos logit contributions
aw+0.042
 regretted+0.039
 gol+0.036
opter+0.034
ime+0.033
Neg logit contributions
 first-0.027
 next-0.025
balls-0.025
ider-0.024
 front-0.019
Token was
Token ID373
Feature activation+1.23e+00

Pos logit contributions
aw+0.026
 gol+0.025
 regretted+0.022
opter+0.022
ime+0.020
Neg logit contributions
 first-0.022
 next-0.019
balls-0.017
ider-0.016
 one-0.015
Token sk
Token ID1341
Feature activation+5.56e-02

Pos logit contributions
aw+0.019
 regretted+0.018
 gol+0.017
opter+0.016
ime+0.016
Neg logit contributions
 first-0.014
 next-0.012
balls-0.012
ider-0.010
 front-0.009
Tokenates
Token ID689
Feature activation+1.17e+00

Pos logit contributions
aw+0.003
 regretted+0.003
 gol+0.002
opter+0.002
 perspective+0.002
Neg logit contributions
 first-0.002
balls-0.002
 next-0.002
ider-0.002
 hips-0.002
Token and
Token ID290
Feature activation+6.33e-01

Pos logit contributions
aw+0.060
 regretted+0.054
 gol+0.051
opter+0.048
ime+0.046
Neg logit contributions
 first-0.046
 next-0.042
balls-0.039
ider-0.038
 front-0.032
Token helmets
Token ID28359
Feature activation+2.96e+00

Pos logit contributions
aw+0.032
 regretted+0.030
 gol+0.028
opter+0.027
ime+0.026
Neg logit contributions
 first-0.025
 next-0.023
balls-0.021
ider-0.020
 last-0.017
Token and
Token ID290
Feature activation+9.26e-01

Pos logit contributions
aw+0.188
 regretted+0.177
 gol+0.174
ime+0.160
opter+0.160
Neg logit contributions
 first-0.095
 next-0.080
balls-0.069
 last-0.057
ider-0.056
Token pads
Token ID21226
Feature activation+6.75e+00

Pos logit contributions
aw+0.048
 regretted+0.043
 gol+0.042
opter+0.041
ime+0.039
Neg logit contributions
 first-0.037
 next-0.034
balls-0.031
ider-0.028
 last-0.026
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
aw+0.406
 regretted+0.387
 gol+0.376
opter+0.355
ime+0.346
Neg logit contributions
 first-0.218
 next-0.194
balls-0.169
ider-0.151
 last-0.132
Token They
Token ID1119
Feature activation-5.00e-01

Pos logit contributions
aw+0.010
 regretted+0.009
 gol+0.009
opter+0.008
ime+0.007
Neg logit contributions
 first-0.008
 next-0.007
balls-0.007
ider-0.007
 last-0.006
Token use
Token ID779
Feature activation-7.44e-01

Pos logit contributions
 first+0.020
 next+0.017
balls+0.015
 last+0.014
ider+0.014
Neg logit contributions
aw-0.027
 gol-0.024
 regretted-0.024
opter-0.022
ime-0.022
Token a
Token ID257
Feature activation-4.64e-01

Pos logit contributions
 first+0.025
 next+0.022
balls+0.020
ider+0.017
 last+0.016
Neg logit contributions
aw-0.043
 regretted-0.041
 gol-0.039
opter-0.037
ime-0.035
Token puck
Token ID20695
Feature activation+9.95e-01

Pos logit contributions
 first+0.017
 next+0.014
balls+0.014
 last+0.012
 hips+0.012
Neg logit contributions
aw-0.028
 regretted-0.024
 gol-0.022
ateful-0.022
aden-0.022
Token decorated
Token ID24789
Feature activation-1.37e-01

Pos logit contributions
aw+0.010
 regretted+0.009
 gol+0.009
opter+0.008
ime+0.008
Neg logit contributions
 first-0.007
 next-0.006
balls-0.006
ider-0.005
 last-0.005
Token it
Token ID340
Feature activation+3.38e-01

Pos logit contributions
 first+0.006
 next+0.006
ider+0.006
balls+0.005
 hips+0.005
Neg logit contributions
aw-0.006
 regretted-0.005
 gol-0.005
opter-0.005
ime-0.004
Token with
Token ID351
Feature activation-8.98e-01

Pos logit contributions
aw+0.015
 regretted+0.012
 gol+0.012
opter+0.011
 goals+0.011
Neg logit contributions
 first-0.012
ider-0.011
 particular-0.010
balls-0.010
 hips-0.010
Token shells
Token ID19679
Feature activation+4.08e+00

Pos logit contributions
 first+0.033
 next+0.030
balls+0.026
 front+0.024
 one+0.024
Neg logit contributions
aw-0.049
 regretted-0.047
 gol-0.045
opter-0.043
arre-0.040
Token and
Token ID290
Feature activation+6.19e-01

Pos logit contributions
aw+0.241
 regretted+0.228
 gol+0.220
opter+0.208
ime+0.200
Neg logit contributions
 first-0.130
 next-0.118
balls-0.105
ider-0.095
 last-0.079
Token seaw
Token ID32085
Feature activation+6.66e+00

Pos logit contributions
aw+0.029
 regretted+0.026
 gol+0.025
opter+0.024
ime+0.022
Neg logit contributions
 first-0.027
 next-0.025
balls-0.024
ider-0.022
 front-0.020
Tokeneed
Token ID2308
Feature activation+3.75e+00

Pos logit contributions
aw+0.230
 regretted+0.222
 gol+0.203
opter+0.178
ime+0.168
Neg logit contributions
 first-0.349
balls-0.332
 next-0.329
ider-0.317
 hips-0.279
Token.
Token ID13
Feature activation+5.32e-01

Pos logit contributions
aw+0.226
 regretted+0.213
 gol+0.205
opter+0.193
ime+0.187
Neg logit contributions
 first-0.114
 next-0.103
balls-0.095
ider-0.086
 last-0.067
Token They
Token ID1119
Feature activation-5.31e-01

Pos logit contributions
aw+0.029
 regretted+0.027
 gol+0.025
opter+0.024
ime+0.023
Neg logit contributions
 first-0.019
 next-0.017
balls-0.016
ider-0.016
 last-0.013
Token had
Token ID550
Feature activation+4.96e-01

Pos logit contributions
 first+0.021
 next+0.019
balls+0.017
ider+0.016
 last+0.015
Neg logit contributions
aw-0.027
 regretted-0.024
 gol-0.024
opter-0.022
ime-0.022
Token a
Token ID257
Feature activation-2.75e-01

Pos logit contributions
aw+0.025
 regretted+0.023
 gol+0.022
opter+0.021
ime+0.020
Neg logit contributions
 first-0.020
 next-0.018
balls-0.017
ider-0.016
 front-0.014
Tokenate
Token ID378
Feature activation-8.05e-02

Pos logit contributions
 first+0.015
 next+0.013
ider+0.013
balls+0.013
 hips+0.012
Neg logit contributions
aw-0.010
 regretted-0.008
 gol-0.007
opter-0.007
ime-0.006
Token it
Token ID340
Feature activation+8.45e-02

Pos logit contributions
 first+0.003
ider+0.003
 next+0.003
balls+0.003
 seek+0.002
Neg logit contributions
aw-0.004
 regretted-0.004
 gol-0.003
opter-0.003
ime-0.003
Token with
Token ID351
Feature activation-1.22e+00

Pos logit contributions
aw+0.004
 regretted+0.003
 gol+0.003
opter+0.003
ong+0.003
Neg logit contributions
 first-0.003
ider-0.003
balls-0.003
 Luna-0.003
 hips-0.003
Token shells
Token ID19679
Feature activation+3.91e+00

Pos logit contributions
 first+0.041
 next+0.037
balls+0.032
 front+0.029
 one+0.029
Neg logit contributions
aw-0.071
 regretted-0.069
 gol-0.065
opter-0.064
arre-0.059
Token and
Token ID290
Feature activation+5.56e-01

Pos logit contributions
aw+0.231
 regretted+0.218
 gol+0.209
opter+0.198
ime+0.190
Neg logit contributions
 first-0.124
 next-0.111
balls-0.100
ider-0.091
 last-0.075
Token seaw
Token ID32085
Feature activation+6.65e+00

Pos logit contributions
aw+0.026
 regretted+0.023
 gol+0.022
opter+0.021
ime+0.020
Neg logit contributions
 first-0.025
 next-0.023
balls-0.021
ider-0.020
 last-0.018
Tokeneed
Token ID2308
Feature activation+3.56e+00

Pos logit contributions
aw+0.228
 regretted+0.219
 gol+0.198
opter+0.174
ime+0.165
Neg logit contributions
 first-0.352
balls-0.334
 next-0.333
ider-0.317
 hips-0.281
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
aw+0.214
 regretted+0.202
 gol+0.194
opter+0.183
ime+0.176
Neg logit contributions
 first-0.108
 next-0.098
balls-0.090
ider-0.080
 last-0.064
Token They
Token ID1119
Feature activation-6.27e-01

Pos logit contributions
aw+0.017
 regretted+0.016
 gol+0.015
opter+0.014
ime+0.013
Neg logit contributions
 first-0.011
 next-0.010
balls-0.009
ider-0.009
 front-0.007
Token find
Token ID1064
Feature activation+4.99e-01

Pos logit contributions
 first+0.024
 next+0.021
balls+0.019
ider+0.017
 last+0.016
Neg logit contributions
aw-0.035
 regretted-0.031
 gol-0.030
opter-0.028
ime-0.028
Token a
Token ID257
Feature activation-9.10e-01

Pos logit contributions
aw+0.030
 regretted+0.029
 gol+0.029
opter+0.027
ime+0.026
Neg logit contributions
 first-0.014
 next-0.012
balls-0.011
 last-0.009
 one-0.009
Token Like
Token ID4525
Feature activation-9.05e-01

Pos logit contributions
aw+0.002
 regretted+0.002
 gol+0.002
opter+0.001
ime+0.001
Neg logit contributions
 first-0.002
 next-0.002
balls-0.001
ider-0.001
 last-0.001
Token shells
Token ID19679
Feature activation+3.19e+00

Pos logit contributions
 first+0.033
 next+0.030
balls+0.026
ider+0.023
 one+0.021
Neg logit contributions
aw-0.051
 regretted-0.049
 gol-0.045
opter-0.044
ime-0.041
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
aw+0.178
 regretted+0.175
 gol+0.167
opter+0.157
ime+0.149
Neg logit contributions
 first-0.116
 next-0.104
balls-0.088
ider-0.078
 last-0.074
Token rocks
Token ID12586
Feature activation+4.12e+00

Pos logit contributions
 first+0.009
 next+0.008
balls+0.008
ider+0.007
 one+0.007
Neg logit contributions
aw-0.010
 regretted-0.009
 gol-0.008
opter-0.008
ime-0.007
Token and
Token ID290
Feature activation+4.15e-01

Pos logit contributions
aw+0.239
 regretted+0.234
 gol+0.221
opter+0.210
ime+0.199
Neg logit contributions
 first-0.140
 next-0.126
balls-0.107
ider-0.095
 last-0.086
Token seaw
Token ID32085
Feature activation+6.49e+00

Pos logit contributions
aw+0.020
 regretted+0.018
 gol+0.017
opter+0.017
ime+0.015
Neg logit contributions
 first-0.018
 next-0.017
balls-0.015
ider-0.014
 one-0.013
Tokeneed
Token ID2308
Feature activation+3.26e+00

Pos logit contributions
 regretted+0.240
aw+0.233
 gol+0.216
opter+0.193
ime+0.181
Neg logit contributions
 first-0.322
balls-0.313
 next-0.301
ider-0.292
 hips-0.253
Token."
Token ID526
Feature activation+2.46e-01

Pos logit contributions
aw+0.195
 regretted+0.188
 gol+0.182
opter+0.171
ime+0.164
Neg logit contributions
 first-0.103
 next-0.093
balls-0.082
ider-0.073
 last-0.060
Token
Token ID198
Feature activation+4.44e-01

Pos logit contributions
aw+0.013
 regretted+0.012
 gol+0.012
opter+0.011
ime+0.010
Neg logit contributions
 first-0.009
 next-0.008
balls-0.008
ider-0.007
 front-0.006
Token
Token ID198
Feature activation-1.55e-01

Pos logit contributions
aw+0.024
 regretted+0.023
 gol+0.022
opter+0.020
ime+0.019
Neg logit contributions
 first-0.016
 next-0.014
balls-0.013
ider-0.012
 front-0.010
TokenM
Token ID44
Feature activation-1.02e+00

Pos logit contributions
 first+0.006
 next+0.006
balls+0.005
ider+0.005
 last+0.004
Neg logit contributions
aw-0.008
 regretted-0.007
 gol-0.007
opter-0.006
ime-0.006
Token buckets
Token ID38674
Feature activation+1.06e+00

Pos logit contributions
 first+0.037
 next+0.034
balls+0.030
ider+0.027
 front+0.025
Neg logit contributions
aw-0.056
 regretted-0.053
 gol-0.050
opter-0.047
ime-0.044
Token and
Token ID290
Feature activation-9.87e-01

Pos logit contributions
aw+0.057
 regretted+0.055
 gol+0.052
opter+0.049
ime+0.046
Neg logit contributions
 first-0.039
 next-0.036
balls-0.032
ider-0.029
 last-0.026
Token shovel
Token ID33677
Feature activation+4.13e+00

Pos logit contributions
 first+0.041
 next+0.037
balls+0.035
ider+0.035
 particular+0.029
Neg logit contributions
aw-0.047
 regretted-0.043
 gol-0.041
opter-0.038
ime-0.036
Tokens
Token ID82
Feature activation-1.06e-03

Pos logit contributions
aw+0.236
 regretted+0.230
 gol+0.224
opter+0.204
ime+0.194
Neg logit contributions
 first-0.144
 next-0.126
balls-0.111
ider-0.094
 last-0.088
Token and
Token ID290
Feature activation+3.29e-01

Pos logit contributions
 first+0.000
 next+0.000
balls+0.000
ider+0.000
 last+0.000
Neg logit contributions
aw-0.000
 regretted-0.000
 gol-0.000
opter-0.000
aden-0.000
Token seaw
Token ID32085
Feature activation+6.48e+00

Pos logit contributions
aw+0.018
 regretted+0.016
 gol+0.015
opter+0.015
ime+0.014
Neg logit contributions
 first-0.013
 next-0.011
balls-0.010
ider-0.009
 last-0.009
Tokeneed
Token ID2308
Feature activation+3.51e+00

Pos logit contributions
aw+0.224
 regretted+0.216
 gol+0.197
opter+0.174
ime+0.163
Neg logit contributions
 first-0.343
balls-0.322
 next-0.321
ider-0.309
 hips-0.273
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
aw+0.205
 regretted+0.194
 gol+0.187
opter+0.175
ime+0.169
Neg logit contributions
 first-0.117
 next-0.105
balls-0.094
ider-0.086
 last-0.072
Token Then
Token ID3244
Feature activation-7.33e-01

Pos logit contributions
 first+0.004
 next+0.004
balls+0.004
ider+0.004
 last+0.003
Neg logit contributions
aw-0.006
 gol-0.005
 regretted-0.005
opter-0.004
ime-0.004
Token we
Token ID356
Feature activation+2.44e-01

Pos logit contributions
 first+0.020
 next+0.018
balls+0.017
ider+0.017
 front+0.012
Neg logit contributions
aw-0.045
 regretted-0.041
 gol-0.039
opter-0.037
ime-0.035
Token can
Token ID460
Feature activation+4.48e-01

Pos logit contributions
aw+0.012
 regretted+0.010
 gol+0.010
opter+0.009
ime+0.008
Neg logit contributions
 first-0.012
 next-0.010
balls-0.009
ider-0.009
 last-0.009
Token saw
Token ID2497
Feature activation-1.22e-01

Pos logit contributions
 first+0.063
 next+0.056
balls+0.051
ider+0.047
 last+0.046
Neg logit contributions
aw-0.067
 gol-0.062
 regretted-0.059
opter-0.057
ime-0.055
Token five
Token ID1936
Feature activation-2.45e+00

Pos logit contributions
 first+0.003
 next+0.003
balls+0.002
 one+0.002
 some+0.002
Neg logit contributions
 regretted-0.008
 gol-0.007
opter-0.007
aw-0.007
arre-0.007
Token fish
Token ID5916
Feature activation+1.36e+00

Pos logit contributions
 first+0.109
 next+0.101
balls+0.094
ider+0.092
 front+0.079
Neg logit contributions
aw-0.112
 regretted-0.102
 gol-0.096
opter-0.089
ime-0.084
Token and
Token ID290
Feature activation+2.65e-01

Pos logit contributions
aw+0.073
 regretted+0.070
 gol+0.066
opter+0.064
ime+0.059
Neg logit contributions
 first-0.050
 next-0.046
balls-0.042
ider-0.038
 last-0.033
Token seven
Token ID3598
Feature activation-6.57e-01

Pos logit contributions
aw+0.013
 regretted+0.012
 gol+0.012
opter+0.011
ime+0.010
Neg logit contributions
 first-0.011
 next-0.010
balls-0.009
ider-0.008
 last-0.008
Token seaw
Token ID32085
Feature activation+6.41e+00

Pos logit contributions
 first+0.030
 next+0.028
balls+0.026
ider+0.025
 last+0.022
Neg logit contributions
aw-0.029
 regretted-0.027
 gol-0.026
opter-0.024
ime-0.022
Tokeneed
Token ID2308
Feature activation+3.31e+00

Pos logit contributions
aw+0.221
 regretted+0.217
 gol+0.193
opter+0.172
ime+0.164
Neg logit contributions
 first-0.334
balls-0.317
 next-0.312
ider-0.304
 hips-0.267
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
aw+0.195
 regretted+0.185
 gol+0.177
opter+0.168
ime+0.161
Neg logit contributions
 first-0.104
 next-0.093
balls-0.086
ider-0.077
 last-0.062
Token They
Token ID1119
Feature activation-5.71e-01

Pos logit contributions
 first+0.006
 next+0.005
balls+0.005
ider+0.004
 Mia+0.004
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.009
opter-0.009
ime-0.009
Token were
Token ID547
Feature activation+1.85e-01

Pos logit contributions
 first+0.024
 next+0.021
balls+0.019
ider+0.017
 last+0.017
Neg logit contributions
aw-0.028
 regretted-0.025
 gol-0.025
opter-0.024
ime-0.023
Token happy
Token ID3772
Feature activation-4.78e-01

Pos logit contributions
aw+0.009
 regretted+0.009
 gol+0.008
opter+0.008
ime+0.007
Neg logit contributions
 first-0.007
 next-0.007
balls-0.006
ider-0.006
 front-0.005
Token out
Token ID503
Feature activation+1.23e+00

Pos logit contributions
aw+0.050
 regretted+0.045
 gol+0.044
opter+0.041
aden+0.039
Neg logit contributions
 first-0.030
 next-0.027
balls-0.021
ider-0.020
 last-0.019
Token of
Token ID286
Feature activation+1.09e+00

Pos logit contributions
aw+0.068
 regretted+0.063
 gol+0.062
opter+0.058
aden+0.054
Neg logit contributions
 first-0.046
 next-0.043
balls-0.035
ider-0.033
 last-0.030
Token difficult
Token ID2408
Feature activation+1.10e+00

Pos logit contributions
aw+0.059
 regretted+0.053
 gol+0.051
opter+0.049
aden+0.045
Neg logit contributions
 first-0.044
 next-0.040
balls-0.033
 one-0.030
 last-0.030
Token and
Token ID290
Feature activation-6.49e-01

Pos logit contributions
aw+0.047
 regretted+0.040
 gol+0.039
opter+0.037
aden+0.033
Neg logit contributions
 first-0.056
 next-0.053
balls-0.045
 one-0.043
ider-0.043
Token sticky
Token ID23408
Feature activation+2.18e+00

Pos logit contributions
 first+0.023
 next+0.021
balls+0.018
ider+0.017
 last+0.015
Neg logit contributions
aw-0.038
 regretted-0.033
 gol-0.032
opter-0.031
ime-0.029
Token situations
Token ID7445
Feature activation+6.41e+00

Pos logit contributions
aw+0.110
 regretted+0.101
 gol+0.099
opter+0.094
aden+0.088
Neg logit contributions
 first-0.087
 next-0.083
balls-0.075
 one-0.064
ider-0.063
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
aw+0.400
 regretted+0.366
 gol+0.354
opter+0.336
ime+0.318
Neg logit contributions
 first-0.198
 next-0.176
balls-0.144
ider-0.139
 last-0.119
Token<|endoftext|>
Token ID50256
Feature activation+8.19e-01

Pos logit contributions
aw+0.013
 regretted+0.012
 gol+0.012
opter+0.011
ime+0.010
Neg logit contributions
 first-0.011
 next-0.010
balls-0.010
ider-0.010
 seek-0.008
TokenThe
Token ID464
Feature activation-3.48e-01

Pos logit contributions
aw+0.044
 regretted+0.041
 gol+0.039
opter+0.037
ime+0.034
Neg logit contributions
 first-0.031
 next-0.028
balls-0.025
ider-0.023
 front-0.021
Token family
Token ID1641
Feature activation+1.62e+00

Pos logit contributions
 first+0.015
 next+0.015
balls+0.012
 one+0.011
ider+0.011
Neg logit contributions
aw-0.017
 regretted-0.016
opter-0.015
 gol-0.014
und-0.013
Token had
Token ID550
Feature activation+5.17e-01

Pos logit contributions
aw+0.085
 gol+0.081
opter+0.076
 regretted+0.074
 tant+0.073
Neg logit contributions
 first-0.060
 next-0.058
 one-0.044
 last-0.040
 some-0.038
Token They
Token ID1119
Feature activation-8.30e-01

Pos logit contributions
 first+0.022
 next+0.020
balls+0.018
ider+0.018
 front+0.015
Neg logit contributions
aw-0.030
 regretted-0.027
 gol-0.026
opter-0.024
ime-0.023
Token went
Token ID1816
Feature activation+2.81e-01

Pos logit contributions
 first+0.037
 next+0.034
balls+0.032
ider+0.030
 last+0.027
Neg logit contributions
aw-0.038
 regretted-0.034
 gol-0.033
opter-0.031
ime-0.029
Token past
Token ID1613
Feature activation-5.24e-01

Pos logit contributions
aw+0.011
 gol+0.009
 regretted+0.009
act+0.007
opter+0.007
Neg logit contributions
ider-0.012
 first-0.012
 next-0.011
 particular-0.011
 eyel-0.010
Token rocks
Token ID12586
Feature activation+2.12e+00

Pos logit contributions
 first+0.018
 next+0.016
balls+0.014
ider+0.013
 last+0.012
Neg logit contributions
aw-0.029
 regretted-0.028
 gol-0.027
opter-0.025
ime-0.024
Token and
Token ID290
Feature activation-4.37e-01

Pos logit contributions
aw+0.101
 regretted+0.090
 gol+0.086
opter+0.079
ime+0.075
Neg logit contributions
 first-0.087
 next-0.080
ider-0.077
balls-0.077
 particular-0.064
Token seaw
Token ID32085
Feature activation+6.37e+00

Pos logit contributions
 first+0.019
 next+0.018
ider+0.018
balls+0.017
 front+0.015
Neg logit contributions
aw-0.019
 regretted-0.018
 gol-0.017
opter-0.015
ime-0.014
Tokeneed
Token ID2308
Feature activation+2.77e+00

Pos logit contributions
aw+0.216
 regretted+0.200
 gol+0.185
opter+0.164
ime+0.152
Neg logit contributions
 first-0.346
 next-0.325
balls-0.323
ider-0.311
 hips-0.273
Token.
Token ID13
Feature activation-3.31e-01

Pos logit contributions
aw+0.143
 regretted+0.130
 gol+0.123
opter+0.115
ime+0.109
Neg logit contributions
 first-0.104
 next-0.095
ider-0.088
balls-0.088
 particular-0.074
Token They
Token ID1119
Feature activation-7.47e-01

Pos logit contributions
 first+0.013
 next+0.012
balls+0.011
ider+0.011
 seek+0.009
Neg logit contributions
aw-0.017
 regretted-0.015
 gol-0.015
opter-0.013
ime-0.013
Token saw
Token ID2497
Feature activation+4.47e-01

Pos logit contributions
 first+0.033
 next+0.030
balls+0.028
ider+0.026
 last+0.024
Neg logit contributions
aw-0.035
 regretted-0.031
 gol-0.030
opter-0.028
ime-0.027
Token other
Token ID584
Feature activation+1.66e+00

Pos logit contributions
aw+0.025
 gol+0.024
 regretted+0.024
opter+0.024
ime+0.022
Neg logit contributions
 first-0.015
 next-0.014
balls-0.011
 some-0.010
 one-0.010
Token be
Token ID307
Feature activation+3.75e-01

Pos logit contributions
aw+0.018
 gol+0.016
 regretted+0.016
opter+0.015
ime+0.014
Neg logit contributions
 first-0.011
 next-0.010
balls-0.008
 last-0.007
ider-0.007
Token happy
Token ID3772
Feature activation-1.22e-01

Pos logit contributions
aw+0.018
 regretted+0.016
 gol+0.016
opter+0.015
ime+0.014
Neg logit contributions
 first-0.016
 next-0.015
balls-0.013
ider-0.013
 front-0.011
Token.
Token ID13
Feature activation-2.81e-01

Pos logit contributions
 first+0.004
 next+0.004
balls+0.003
ider+0.003
 one+0.002
Neg logit contributions
aw-0.007
 regretted-0.007
 gol-0.007
opter-0.006
ime-0.006
Token Even
Token ID3412
Feature activation-7.98e-02

Pos logit contributions
 first+0.010
 next+0.009
balls+0.008
ider+0.008
 Mia+0.007
Neg logit contributions
aw-0.015
 regretted-0.014
 gol-0.013
opter-0.013
ime-0.012
Token though
Token ID996
Feature activation-1.70e-01

Pos logit contributions
 first+0.003
 next+0.003
balls+0.002
 one+0.002
 last+0.002
Neg logit contributions
aw-0.004
 regretted-0.004
opter-0.004
 gol-0.004
ime-0.004
Token situations
Token ID7445
Feature activation+6.19e+00

Pos logit contributions
 first+0.006
 next+0.005
balls+0.004
ider+0.004
 one+0.004
Neg logit contributions
aw-0.010
 regretted-0.009
 gol-0.009
opter-0.008
aden-0.008
Token can
Token ID460
Feature activation+1.20e+00

Pos logit contributions
aw+0.303
 regretted+0.267
 gol+0.263
opter+0.239
ime+0.223
Neg logit contributions
 first-0.276
 next-0.250
balls-0.215
ider-0.205
 last-0.204
Token be
Token ID307
Feature activation-4.07e-01

Pos logit contributions
aw+0.065
 regretted+0.060
 gol+0.056
opter+0.055
ime+0.053
Neg logit contributions
 first-0.039
balls-0.036
ider-0.035
 next-0.035
 hips-0.027
Token serious
Token ID2726
Feature activation-6.59e-02

Pos logit contributions
 first+0.016
 next+0.015
 one+0.012
 last+0.012
 some+0.011
Neg logit contributions
aw-0.021
 gol-0.019
opter-0.019
 regretted-0.018
aden-0.017
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.002
 one+0.001
Neg logit contributions
aw-0.004
 gol-0.004
 regretted-0.004
opter-0.003
aden-0.003
Token it
Token ID340
Feature activation+8.42e-01

Pos logit contributions
aw+0.059
 regretted+0.054
 gol+0.053
opter+0.050
ime+0.047
Neg logit contributions
 first-0.035
 next-0.032
balls-0.027
ider-0.025
 last-0.023
Token cand
Token ID2658
Feature activation+3.46e+00

Pos logit contributions
aw+0.001
 regretted+0.001
 gol+0.001
opter+0.001
ime+0.001
Neg logit contributions
 first-0.001
 next-0.001
balls-0.001
ider-0.001
 last-0.001
Tokenies
Token ID444
Feature activation+4.61e+00

Pos logit contributions
aw+0.168
 gol+0.163
 regretted+0.162
opter+0.141
ime+0.133
Neg logit contributions
 first-0.138
 next-0.131
balls-0.125
ider-0.112
 last-0.093
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
aw+0.290
 regretted+0.278
 gol+0.271
opter+0.258
ime+0.246
Neg logit contributions
 first-0.126
 next-0.118
balls-0.096
ider-0.087
 front-0.071
Token fruits
Token ID15921
Feature activation+5.64e+00

Pos logit contributions
aw+0.069
 regretted+0.061
 gol+0.060
opter+0.059
ime+0.056
Neg logit contributions
 first-0.055
 next-0.052
balls-0.047
ider-0.041
 one-0.040
Token and
Token ID290
Feature activation+1.05e+00

Pos logit contributions
aw+0.354
 regretted+0.343
 gol+0.332
opter+0.319
ime+0.304
Neg logit contributions
 first-0.154
 next-0.144
balls-0.115
ider-0.102
 last-0.087
Token vegetables
Token ID13701
Feature activation+6.08e+00

Pos logit contributions
aw+0.052
 regretted+0.046
 gol+0.046
opter+0.044
ime+0.041
Neg logit contributions
 first-0.044
 next-0.041
balls-0.037
ider-0.033
 last-0.031
Token and
Token ID290
Feature activation+1.16e+00

Pos logit contributions
aw+0.381
 regretted+0.358
 gol+0.347
opter+0.331
ime+0.318
Neg logit contributions
 first-0.175
 next-0.160
balls-0.134
ider-0.123
 last-0.099
Token letters
Token ID7475
Feature activation+3.74e+00

Pos logit contributions
aw+0.058
 regretted+0.052
 gol+0.051
opter+0.049
ime+0.046
Neg logit contributions
 first-0.048
 next-0.045
balls-0.040
ider-0.037
 last-0.035
Token and
Token ID290
Feature activation+6.38e-01

Pos logit contributions
aw+0.239
 regretted+0.236
 gol+0.226
opter+0.218
ime+0.208
Neg logit contributions
 first-0.099
 next-0.093
balls-0.073
ider-0.062
 one-0.055
Token numbers
Token ID3146
Feature activation+3.43e+00

Pos logit contributions
aw+0.031
 regretted+0.028
 gol+0.027
opter+0.026
ime+0.025
Neg logit contributions
 first-0.026
 next-0.025
balls-0.023
ider-0.020
 last-0.019
Token and
Token ID290
Feature activation+6.74e-01

Pos logit contributions
aw+0.221
 regretted+0.220
 gol+0.210
opter+0.202
ime+0.190
Neg logit contributions
 first-0.089
 next-0.084
balls-0.064
ider-0.054
 one-0.048
Token see
Token ID766
Feature activation-4.26e-01

Pos logit contributions
 first+0.034
 next+0.030
balls+0.024
 last+0.023
 front+0.022
Neg logit contributions
aw-0.053
 regretted-0.047
 gol-0.045
opter-0.044
ime-0.042
Token shells
Token ID19679
Feature activation+3.14e+00

Pos logit contributions
 first+0.015
 next+0.014
balls+0.011
 one+0.010
 some+0.010
Neg logit contributions
aw-0.023
 regretted-0.023
 gol-0.023
opter-0.022
ime-0.020
Token,
Token ID11
Feature activation+6.65e-02

Pos logit contributions
aw+0.170
 regretted+0.161
 gol+0.154
opter+0.143
ime+0.136
Neg logit contributions
 first-0.118
 next-0.107
balls-0.097
ider-0.087
 last-0.079
Token rocks
Token ID12586
Feature activation+3.79e+00

Pos logit contributions
aw+0.003
 regretted+0.003
 gol+0.002
opter+0.002
ime+0.002
Neg logit contributions
 first-0.003
 next-0.003
balls-0.003
ider-0.003
 front-0.002
Token,
Token ID11
Feature activation+4.64e-01

Pos logit contributions
aw+0.203
 regretted+0.189
 gol+0.180
opter+0.168
ime+0.159
Neg logit contributions
 first-0.145
 next-0.131
balls-0.120
ider-0.111
 last-0.097
Token seaw
Token ID32085
Feature activation+6.01e+00

Pos logit contributions
aw+0.021
 regretted+0.019
 gol+0.018
opter+0.017
ime+0.016
Neg logit contributions
 first-0.021
 next-0.019
balls-0.018
ider-0.018
 front-0.015
Tokeneed
Token ID2308
Feature activation+2.74e+00

Pos logit contributions
aw+0.209
 regretted+0.209
 gol+0.187
opter+0.165
ime+0.155
Neg logit contributions
 first-0.315
balls-0.296
 next-0.296
ider-0.280
 hips-0.249
Token,
Token ID11
Feature activation+9.28e-01

Pos logit contributions
aw+0.148
 regretted+0.140
 gol+0.133
opter+0.123
ime+0.118
Neg logit contributions
 first-0.103
 next-0.093
balls-0.087
ider-0.079
 last-0.067
Token crabs
Token ID49172
Feature activation+4.30e+00

Pos logit contributions
aw+0.045
 regretted+0.040
 gol+0.038
opter+0.035
ime+0.034
Neg logit contributions
 first-0.039
 next-0.035
balls-0.033
ider-0.033
 front-0.027
Token and
Token ID290
Feature activation+1.04e+00

Pos logit contributions
aw+0.239
 regretted+0.228
 gol+0.220
opter+0.206
ime+0.194
Neg logit contributions
 first-0.154
 next-0.140
balls-0.127
ider-0.113
 last-0.097
Token fish
Token ID5916
Feature activation+3.65e+00

Pos logit contributions
aw+0.047
 regretted+0.043
 gol+0.041
opter+0.038
ime+0.036
Neg logit contributions
 first-0.047
 next-0.043
balls-0.040
ider-0.038
 last-0.034
Token shovel
Token ID33677
Feature activation+4.27e+00

Pos logit contributions
 first+0.049
 next+0.046
ider+0.044
balls+0.044
 particular+0.037
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.038
opter-0.035
ime-0.033
Tokens
Token ID82
Feature activation-4.50e-02

Pos logit contributions
aw+0.239
 regretted+0.225
 gol+0.219
opter+0.203
ime+0.192
Neg logit contributions
 first-0.151
 next-0.135
balls-0.123
ider-0.108
 last-0.097
Token and
Token ID290
Feature activation+2.17e-01

Pos logit contributions
 first+0.002
 next+0.001
balls+0.001
ider+0.001
 last+0.001
Neg logit contributions
aw-0.002
 regretted-0.002
 gol-0.002
opter-0.002
aden-0.002
Token shells
Token ID19679
Feature activation+5.45e+00

Pos logit contributions
aw+0.011
 regretted+0.010
 gol+0.009
opter+0.009
ime+0.008
Neg logit contributions
 first-0.009
 next-0.008
balls-0.008
ider-0.007
 last-0.006
Token and
Token ID290
Feature activation+9.43e-01

Pos logit contributions
aw+0.302
 regretted+0.283
 gol+0.273
opter+0.257
ime+0.243
Neg logit contributions
 first-0.194
 next-0.177
balls-0.160
ider-0.146
 last-0.127
Token stones
Token ID14966
Feature activation+5.98e+00

Pos logit contributions
aw+0.045
 regretted+0.040
 gol+0.039
opter+0.037
ime+0.034
Neg logit contributions
 first-0.041
 next-0.038
balls-0.035
ider-0.033
 last-0.030
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
aw+0.329
 regretted+0.304
 gol+0.291
opter+0.274
ime+0.261
Neg logit contributions
 first-0.211
 next-0.192
balls-0.176
ider-0.167
 last-0.138
Token They
Token ID1119
Feature activation-5.04e-01

Pos logit contributions
 first+0.010
 next+0.009
balls+0.008
ider+0.008
 front+0.007
Neg logit contributions
aw-0.015
 regretted-0.014
 gol-0.013
opter-0.013
ime-0.012
Token worked
Token ID3111
Feature activation-1.21e+00

Pos logit contributions
 first+0.020
 next+0.018
balls+0.017
ider+0.016
 last+0.014
Neg logit contributions
aw-0.026
 regretted-0.023
 gol-0.022
opter-0.021
ime-0.020
Token hard
Token ID1327
Feature activation-6.69e-01

Pos logit contributions
 first+0.041
ider+0.038
 next+0.037
balls+0.037
 Luna+0.030
Neg logit contributions
aw-0.064
 regretted-0.058
 gol-0.054
opter-0.049
ime-0.048
Token and
Token ID290
Feature activation-1.50e+00

Pos logit contributions
 first+0.024
 next+0.022
balls+0.020
ider+0.018
 last+0.016
Neg logit contributions
aw-0.037
 regretted-0.035
 gol-0.033
opter-0.031
ime-0.030
Token pulled
Token ID5954
Feature activation+5.22e-02

Pos logit contributions
 first+0.007
 next+0.006
balls+0.006
ider+0.006
 front+0.005
Neg logit contributions
aw-0.008
 regretted-0.007
 gol-0.007
opter-0.006
ime-0.006
Token out
Token ID503
Feature activation+6.95e-01

Pos logit contributions
aw+0.003
 regretted+0.003
 gol+0.003
opter+0.003
ane+0.002
Neg logit contributions
 first-0.002
 next-0.002
balls-0.001
 one-0.001
 last-0.001
Token vegetable
Token ID20236
Feature activation+9.78e-01

Pos logit contributions
aw+0.040
 regretted+0.037
 gol+0.036
opter+0.034
ime+0.031
Neg logit contributions
 first-0.024
 next-0.021
balls-0.019
ider-0.017
 front-0.016
Token scraps
Token ID44496
Feature activation+2.53e+00

Pos logit contributions
aw+0.057
 regretted+0.053
 gol+0.051
opter+0.048
ime+0.046
Neg logit contributions
 first-0.033
 next-0.029
balls-0.027
ider-0.024
 last-0.020
Token and
Token ID290
Feature activation+4.87e-01

Pos logit contributions
aw+0.149
 regretted+0.144
 gol+0.138
opter+0.131
arre+0.121
Neg logit contributions
 first-0.084
 next-0.076
balls-0.062
 last-0.055
 one-0.052
Token weeds
Token ID36708
Feature activation+5.93e+00

Pos logit contributions
aw+0.025
 regretted+0.022
 gol+0.021
opter+0.020
ime+0.019
Neg logit contributions
 first-0.019
 next-0.018
balls-0.017
ider-0.016
 front-0.013
Token.
Token ID13
Feature activation+5.19e-01

Pos logit contributions
aw+0.365
 regretted+0.336
 gol+0.331
opter+0.312
ime+0.289
Neg logit contributions
 first-0.182
 next-0.163
balls-0.147
ider-0.126
 last-0.110
Token He
Token ID679
Feature activation+5.76e-01

Pos logit contributions
aw+0.026
 regretted+0.024
 gol+0.022
opter+0.021
ime+0.020
Neg logit contributions
 first-0.021
 next-0.020
balls-0.018
ider-0.017
 front-0.015
Token planted
Token ID18969
Feature activation-4.10e-01

Pos logit contributions
aw+0.029
 regretted+0.027
 gol+0.026
opter+0.024
ime+0.023
Neg logit contributions
 first-0.023
 next-0.021
balls-0.019
ider-0.019
 last-0.016
Token beautiful
Token ID4950
Feature activation+6.07e-01

Pos logit contributions
 first+0.013
 next+0.011
balls+0.010
ider+0.008
 last+0.008
Neg logit contributions
aw-0.024
 regretted-0.023
 gol-0.023
opter-0.021
ime-0.020
Token flowers
Token ID12734
Feature activation+2.39e+00

Pos logit contributions
aw+0.031
 regretted+0.029
 gol+0.029
opter+0.027
aden+0.025
Neg logit contributions
 first-0.023
 next-0.022
balls-0.020
ider-0.017
 one-0.017
Token her
Token ID607
Feature activation+1.60e-01

Pos logit contributions
aw+0.035
 regretted+0.032
 gol+0.031
opter+0.029
ime+0.028
Neg logit contributions
 first-0.022
 next-0.020
balls-0.018
ider-0.017
 last-0.014
Token collection
Token ID4947
Feature activation+1.89e+00

Pos logit contributions
aw+0.010
 gol+0.009
 regretted+0.008
opter+0.008
ime+0.008
Neg logit contributions
 first-0.006
 next-0.005
balls-0.004
 last-0.004
 one-0.004
Token of
Token ID286
Feature activation+9.05e-01

Pos logit contributions
aw+0.107
 regretted+0.099
 gol+0.094
opter+0.089
ime+0.085
Neg logit contributions
 first-0.063
 next-0.057
balls-0.053
ider-0.051
 front-0.040
Token rocks
Token ID12586
Feature activation+3.42e+00

Pos logit contributions
aw+0.049
opter+0.045
 regretted+0.043
ane+0.042
ime+0.041
Neg logit contributions
 first-0.036
 next-0.031
 one-0.026
balls-0.024
 some-0.024
Token and
Token ID290
Feature activation+1.31e+00

Pos logit contributions
aw+0.196
 regretted+0.180
 gol+0.173
opter+0.163
ime+0.156
Neg logit contributions
 first-0.112
 next-0.101
balls-0.093
ider-0.089
 front-0.071
Token shells
Token ID19679
Feature activation+5.89e+00

Pos logit contributions
aw+0.070
opter+0.059
 regretted+0.058
 gol+0.058
ime+0.057
Neg logit contributions
 first-0.053
 next-0.047
balls-0.043
 one-0.038
 last-0.036
Token.
Token ID13
Feature activation+3.34e-01

Pos logit contributions
aw+0.365
 regretted+0.343
 gol+0.331
opter+0.322
ime+0.307
Neg logit contributions
 first-0.172
 next-0.153
balls-0.136
ider-0.117
 last-0.099
Token They
Token ID1119
Feature activation-5.94e-01

Pos logit contributions
aw+0.017
 regretted+0.016
 gol+0.015
opter+0.014
ime+0.013
Neg logit contributions
 first-0.013
 next-0.012
balls-0.011
ider-0.011
 last-0.009
Token thanked
Token ID26280
Feature activation+8.19e-01

Pos logit contributions
 first+0.025
 next+0.023
balls+0.020
ider+0.018
 last+0.018
Neg logit contributions
aw-0.030
 regretted-0.026
 gol-0.025
opter-0.024
ime-0.023
Token her
Token ID607
Feature activation+1.24e-01

Pos logit contributions
aw+0.038
 regretted+0.033
 gol+0.032
opter+0.028
ime+0.027
Neg logit contributions
ider-0.035
 first-0.033
balls-0.032
 next-0.031
 hips-0.026
Token and
Token ID290
Feature activation-1.90e-01

Pos logit contributions
aw+0.007
 regretted+0.007
 gol+0.006
opter+0.006
ime+0.006
Neg logit contributions
 first-0.004
 next-0.004
balls-0.003
ider-0.003
 last-0.003
Token had
Token ID550
Feature activation+5.14e-01

Pos logit contributions
 first+0.000
 next+0.000
balls+0.000
ider+0.000
 last+0.000
Neg logit contributions
aw-0.000
 regretted-0.000
 gol-0.000
opter-0.000
ime-0.000
Token measured
Token ID8630
Feature activation-1.54e+00

Pos logit contributions
aw+0.027
 gol+0.024
 regretted+0.024
opter+0.023
ime+0.021
Neg logit contributions
 first-0.020
 next-0.018
balls-0.016
ider-0.015
 front-0.014
Token the
Token ID262
Feature activation-1.45e-01

Pos logit contributions
 first+0.055
 next+0.048
balls+0.042
ider+0.037
 last+0.035
Neg logit contributions
aw-0.085
 regretted-0.081
 gol-0.080
opter-0.075
ime-0.068
Token z
Token ID1976
Feature activation-1.89e+00

Pos logit contributions
 first+0.006
 next+0.006
balls+0.005
ider+0.005
 last+0.005
Neg logit contributions
aw-0.007
 regretted-0.006
 gol-0.006
opter-0.006
ime-0.005
Tokenig
Token ID328
Feature activation-2.56e+00

Pos logit contributions
 first+0.095
 next+0.088
balls+0.081
ider+0.078
 seek+0.073
Neg logit contributions
aw-0.078
 gol-0.065
 regretted-0.062
opter-0.057
ime-0.056
Tokenzag
Token ID50183
Feature activation-5.36e+00

Pos logit contributions
 first+0.085
 next+0.078
ider+0.077
balls+0.074
 front+0.062
Neg logit contributions
aw-0.132
 regretted-0.113
 gol-0.110
opter-0.108
ime-0.106
Token line
Token ID1627
Feature activation-1.70e+00

Pos logit contributions
 first+0.190
 next+0.174
ider+0.164
balls+0.163
 front+0.129
Neg logit contributions
aw-0.284
 regretted-0.255
 gol-0.244
opter-0.232
ime-0.225
Token and
Token ID290
Feature activation+2.80e-01

Pos logit contributions
 first+0.057
 next+0.051
balls+0.047
ider+0.045
 front+0.036
Neg logit contributions
aw-0.096
 regretted-0.089
 gol-0.085
opter-0.080
ime-0.076
Token the
Token ID262
Feature activation+1.36e+00

Pos logit contributions
aw+0.015
 gol+0.013
 regretted+0.013
opter+0.013
ime+0.012
Neg logit contributions
 first-0.011
 next-0.010
balls-0.009
ider-0.007
 one-0.007
Token spicy
Token ID26880
Feature activation+8.69e-01

Pos logit contributions
aw+0.069
 regretted+0.063
 gol+0.059
opter+0.058
ime+0.053
Neg logit contributions
 first-0.058
 next-0.053
balls-0.047
ider-0.043
 last-0.040
Token pepper
Token ID13385
Feature activation+8.26e-01

Pos logit contributions
aw+0.045
 regretted+0.042
 gol+0.040
opter+0.037
aden+0.036
Neg logit contributions
 first-0.034
 next-0.031
balls-0.029
ider-0.025
 last-0.023
Token can
Token ID460
Feature activation+1.90e-01

Pos logit contributions
 first+0.011
 next+0.009
 last+0.008
 one+0.008
balls+0.007
Neg logit contributions
aw-0.013
 regretted-0.011
 gol-0.011
opter-0.010
ime-0.010
Token make
Token ID787
Feature activation-1.71e+00

Pos logit contributions
aw+0.010
 regretted+0.009
 gol+0.009
opter+0.009
ime+0.008
Neg logit contributions
 first-0.007
 next-0.006
balls-0.006
ider-0.006
 front-0.004
Token the
Token ID262
Feature activation-3.09e-01

Pos logit contributions
 first+0.060
 next+0.053
balls+0.047
 one+0.040
ider+0.038
Neg logit contributions
aw-0.093
 regretted-0.092
 gol-0.087
opter-0.080
ime-0.075
Token z
Token ID1976
Feature activation-1.98e+00

Pos logit contributions
 first+0.014
 next+0.013
balls+0.011
ider+0.010
 last+0.010
Neg logit contributions
aw-0.015
 regretted-0.014
 gol-0.013
opter-0.012
ime-0.012
Tokenig
Token ID328
Feature activation-2.64e+00

Pos logit contributions
 first+0.102
 next+0.095
balls+0.091
ider+0.086
 Luna+0.080
Neg logit contributions
aw-0.077
 gol-0.062
 regretted-0.062
opter-0.057
ime-0.053
Tokenzag
Token ID50183
Feature activation-5.31e+00

Pos logit contributions
 first+0.097
 next+0.089
ider+0.085
balls+0.084
 particular+0.071
Neg logit contributions
aw-0.133
 regretted-0.116
opter-0.111
 gol-0.110
ime-0.104
Token another
Token ID1194
Feature activation-1.28e+00

Pos logit contributions
 first+0.210
 next+0.193
balls+0.183
ider+0.178
 front+0.148
Neg logit contributions
aw-0.263
 regretted-0.237
 gol-0.225
opter-0.214
ime-0.203
Token day
Token ID1110
Feature activation-1.32e+00

Pos logit contributions
 first+0.049
 next+0.045
balls+0.041
ider+0.040
 last+0.034
Neg logit contributions
aw-0.067
 regretted-0.061
 gol-0.058
opter-0.054
ime-0.052
Token.
Token ID13
Feature activation+5.83e-02

Pos logit contributions
 first+0.046
 next+0.043
balls+0.035
ider+0.034
 last+0.030
Neg logit contributions
aw-0.074
 regretted-0.071
 gol-0.068
opter-0.063
ime-0.059
Token I
Token ID314
Feature activation+1.34e+00

Pos logit contributions
aw+0.003
 regretted+0.003
 gol+0.003
opter+0.002
ime+0.002
Neg logit contributions
 first-0.002
 next-0.002
balls-0.002
ider-0.002
 last-0.002
Token'm
Token ID1101
Feature activation-9.61e-01

Pos logit contributions
aw+0.063
 regretted+0.055
 gol+0.053
opter+0.049
ime+0.047
Neg logit contributions
 first-0.060
 next-0.055
balls-0.050
ider-0.049
 last-0.044
Token back
Token ID736
Feature activation+2.60e-01

Pos logit contributions
aw+0.012
 regretted+0.011
 gol+0.011
opter+0.010
ime+0.009
Neg logit contributions
 first-0.010
 next-0.009
balls-0.009
ider-0.009
 hips-0.007
Token down
Token ID866
Feature activation+8.61e-01

Pos logit contributions
aw+0.014
 regretted+0.013
 gol+0.012
opter+0.011
ime+0.011
Neg logit contributions
 first-0.010
 next-0.009
balls-0.008
ider-0.008
 front-0.007
Token the
Token ID262
Feature activation+2.29e-01

Pos logit contributions
aw+0.045
 regretted+0.041
 gol+0.039
opter+0.036
ime+0.035
Neg logit contributions
 first-0.032
 next-0.029
balls-0.028
ider-0.027
 hips-0.022
Token z
Token ID1976
Feature activation-1.97e+00

Pos logit contributions
aw+0.012
 regretted+0.010
 gol+0.010
opter+0.009
ime+0.009
Neg logit contributions
 first-0.010
 next-0.009
balls-0.008
ider-0.007
 front-0.007
Tokenig
Token ID328
Feature activation-2.33e+00

Pos logit contributions
 first+0.103
 next+0.095
balls+0.092
ider+0.087
 hips+0.078
Neg logit contributions
aw-0.077
 regretted-0.064
 gol-0.062
opter-0.056
ime-0.053
Tokenzag
Token ID50183
Feature activation-5.21e+00

Pos logit contributions
 first+0.064
 next+0.055
balls+0.054
ider+0.053
 particular+0.041
Neg logit contributions
aw-0.136
 regretted-0.117
 gol-0.116
opter-0.111
ime-0.110
Token branch
Token ID8478
Feature activation-1.43e+00

Pos logit contributions
 first+0.210
 next+0.193
balls+0.188
ider+0.187
 hips+0.148
Neg logit contributions
aw-0.250
 regretted-0.220
 gol-0.211
opter-0.197
ime-0.190
Token and
Token ID290
Feature activation+7.28e-01

Pos logit contributions
 first+0.055
 next+0.051
balls+0.048
ider+0.046
 front+0.038
Neg logit contributions
aw-0.073
 regretted-0.066
 gol-0.063
opter-0.059
ime-0.056
Token lay
Token ID3830
Feature activation+5.47e-01

Pos logit contributions
aw+0.038
 gol+0.033
 regretted+0.033
opter+0.032
ime+0.031
Neg logit contributions
 first-0.029
 next-0.027
balls-0.024
ider-0.021
 seek-0.021
Token in
Token ID287
Feature activation-2.58e-02

Pos logit contributions
aw+0.026
 regretted+0.023
 gol+0.022
opter+0.021
ime+0.019
Neg logit contributions
 first-0.024
 next-0.022
balls-0.021
ider-0.020
 front-0.017
Token the
Token ID262
Feature activation+1.57e+00

Pos logit contributions
 first+0.001
balls+0.001
ider+0.001
 next+0.001
 hips+0.001
Neg logit contributions
aw-0.001
 regretted-0.001
 gol-0.001
opter-0.001
ime-0.001
TokenThe
Token ID464
Feature activation-8.60e-01

Pos logit contributions
 first+0.004
 next+0.004
balls+0.004
ider+0.003
 front+0.003
Neg logit contributions
aw-0.007
 regretted-0.007
 gol-0.006
opter-0.006
ime-0.006
Token flood
Token ID6947
Feature activation-8.97e-01

Pos logit contributions
 first+0.037
 next+0.034
balls+0.032
ider+0.031
 front+0.027
Neg logit contributions
aw-0.041
 regretted-0.037
 gol-0.035
opter-0.033
ime-0.031
Token was
Token ID373
Feature activation-1.06e+00

Pos logit contributions
 first+0.035
 next+0.033
balls+0.028
ider+0.026
 last+0.025
Neg logit contributions
aw-0.047
 gol-0.042
 regretted-0.041
opter-0.039
aden-0.037
Token gone
Token ID3750
Feature activation-1.35e+00

Pos logit contributions
 first+0.039
 next+0.036
balls+0.029
 last+0.026
ider+0.026
Neg logit contributions
aw-0.062
 gol-0.055
 regretted-0.054
opter-0.053
act-0.049
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
 first+0.049
 next+0.045
balls+0.033
ider+0.033
 last+0.032
Neg logit contributions
aw-0.080
 gol-0.072
 regretted-0.071
opter-0.067
aden-0.063
Token next
Token ID1306
Feature activation-5.19e+00

Pos logit contributions
 first+0.047
 next+0.045
balls+0.036
ider+0.036
 last+0.034
Neg logit contributions
aw-0.054
 regretted-0.047
opter-0.043
 gol-0.042
ime-0.040
Token day
Token ID1110
Feature activation-2.82e+00

Pos logit contributions
 first+0.192
 next+0.176
balls+0.157
ider+0.152
 last+0.129
Neg logit contributions
aw-0.284
 regretted-0.261
 gol-0.245
opter-0.233
ime-0.220
Token and
Token ID290
Feature activation-7.32e-01

Pos logit contributions
 first+0.088
 next+0.082
balls+0.059
 one+0.055
ider+0.055
Neg logit contributions
aw-0.169
 regretted-0.162
 gol-0.155
opter-0.155
act-0.142
Token the
Token ID262
Feature activation+9.47e-01

Pos logit contributions
 first+0.023
 next+0.021
balls+0.017
 one+0.015
 Mia+0.014
Neg logit contributions
aw-0.045
 gol-0.041
 regretted-0.039
opter-0.039
ime-0.038
Token man
Token ID582
Feature activation-1.02e+00

Pos logit contributions
aw+0.046
 regretted+0.041
opter+0.039
 gol+0.038
ime+0.037
Neg logit contributions
 first-0.043
 next-0.042
balls-0.035
ider-0.032
 front-0.032
Token took
Token ID1718
Feature activation-6.79e-01

Pos logit contributions
 first+0.037
 next+0.034
balls+0.025
ider+0.025
 last+0.025
Neg logit contributions
aw-0.055
 gol-0.052
opter-0.048
 regretted-0.047
 perspective-0.046
Token walked
Token ID6807
Feature activation-1.41e+00

Pos logit contributions
 first+0.038
 next+0.035
balls+0.030
ider+0.029
 last+0.026
Neg logit contributions
aw-0.045
 gol-0.041
 regretted-0.041
opter-0.038
ime-0.035
Token on
Token ID319
Feature activation-6.26e-01

Pos logit contributions
ider+0.063
balls+0.060
bes+0.056
 first+0.055
 hips+0.052
Neg logit contributions
aw-0.056
 regretted-0.045
 gol-0.042
 perspective-0.034
onder-0.032
Token the
Token ID262
Feature activation+1.90e-01

Pos logit contributions
 first+0.022
 next+0.020
balls+0.019
ider+0.019
 last+0.015
Neg logit contributions
aw-0.034
 regretted-0.031
 gol-0.030
opter-0.028
ime-0.027
Token z
Token ID1976
Feature activation-1.82e+00

Pos logit contributions
aw+0.008
 regretted+0.008
 gol+0.007
opter+0.007
ime+0.006
Neg logit contributions
 first-0.008
 next-0.008
balls-0.007
ider-0.007
 particular-0.006
Tokenig
Token ID328
Feature activation-2.26e+00

Pos logit contributions
 first+0.104
 next+0.097
balls+0.094
ider+0.087
 hips+0.083
Neg logit contributions
aw-0.064
 gol-0.047
 regretted-0.047
opter-0.042
ime-0.041
Tokenzag
Token ID50183
Feature activation-5.10e+00

Pos logit contributions
 first+0.063
ider+0.058
 next+0.057
balls+0.057
 sip+0.048
Neg logit contributions
aw-0.122
 regretted-0.104
 gol-0.102
opter-0.100
ane-0.100
Token path
Token ID3108
Feature activation+5.07e-01

Pos logit contributions
 first+0.221
ider+0.208
 next+0.207
balls+0.203
 seek+0.162
Neg logit contributions
aw-0.223
 regretted-0.194
 gol-0.182
opter-0.174
ime-0.167
Token.
Token ID13
Feature activation-4.05e-01

Pos logit contributions
aw+0.024
 regretted+0.022
 gol+0.020
opter+0.018
ime+0.018
Neg logit contributions
 first-0.020
balls-0.019
 next-0.018
ider-0.018
 particular-0.015
Token It
Token ID632
Feature activation-7.09e-02

Pos logit contributions
 first+0.016
 next+0.015
balls+0.013
ider+0.013
 front+0.011
Neg logit contributions
aw-0.021
 regretted-0.019
 gol-0.018
opter-0.017
ime-0.016
Token went
Token ID1816
Feature activation+1.93e-01

Pos logit contributions
 first+0.003
 next+0.003
balls+0.003
ider+0.003
 hips+0.003
Neg logit contributions
aw-0.003
 regretted-0.003
 gol-0.002
opter-0.002
ime-0.002
Token left
Token ID1364
Feature activation+4.10e-01

Pos logit contributions
aw+0.009
 regretted+0.008
 gol+0.007
opter+0.006
 perspective+0.006
Neg logit contributions
balls-0.007
 first-0.007
ider-0.007
 next-0.006
 particular-0.006
Token I
Token ID314
Feature activation+1.42e+00

Pos logit contributions
aw+0.015
 gol+0.013
 regretted+0.012
opter+0.012
aden+0.011
Neg logit contributions
ider-0.018
 first-0.017
balls-0.017
 next-0.016
 timer-0.015
Token have
Token ID423
Feature activation-1.34e+00

Pos logit contributions
aw+0.077
 regretted+0.071
 gol+0.068
opter+0.063
ime+0.061
Neg logit contributions
 first-0.051
 next-0.046
balls-0.043
ider-0.041
 front-0.034
Token the
Token ID262
Feature activation+1.53e-01

Pos logit contributions
 first+0.040
 next+0.035
balls+0.032
ider+0.030
 front+0.024
Neg logit contributions
aw-0.081
 regretted-0.075
 gol-0.072
opter-0.068
ime-0.066
Token z
Token ID1976
Feature activation-1.97e+00

Pos logit contributions
aw+0.008
 regretted+0.008
 gol+0.007
opter+0.007
ime+0.006
Neg logit contributions
 first-0.006
 next-0.005
balls-0.005
ider-0.004
 front-0.004
Tokenig
Token ID328
Feature activation-2.22e+00

Pos logit contributions
 first+0.102
 next+0.095
balls+0.091
ider+0.087
 last+0.079
Neg logit contributions
aw-0.077
 regretted-0.064
 gol-0.063
opter-0.056
ime-0.053
Tokenzag
Token ID50183
Feature activation-5.09e+00

Pos logit contributions
 first+0.069
 next+0.064
ider+0.062
balls+0.062
 particular+0.049
Neg logit contributions
aw-0.115
 gol-0.101
 regretted-0.100
opter-0.098
ane-0.094
Token?"
Token ID1701
Feature activation-4.41e-01

Pos logit contributions
 first+0.207
 next+0.191
balls+0.181
ider+0.176
 last+0.146
Neg logit contributions
aw-0.247
 regretted-0.222
 gol-0.213
opter-0.200
ime-0.189
Token
Token ID198
Feature activation+7.17e-01

Pos logit contributions
 first+0.016
 next+0.015
ider+0.014
balls+0.014
 last+0.011
Neg logit contributions
aw-0.023
 regretted-0.021
 gol-0.020
opter-0.019
ime-0.018
Token
Token ID198
Feature activation+2.43e-01

Pos logit contributions
aw+0.037
 regretted+0.034
 gol+0.032
opter+0.030
ime+0.029
Neg logit contributions
 first-0.027
 next-0.025
balls-0.023
ider-0.023
 last-0.018
TokenM
Token ID44
Feature activation-1.27e+00

Pos logit contributions
aw+0.014
 regretted+0.013
 gol+0.012
opter+0.012
ime+0.011
Neg logit contributions
 first-0.008
 next-0.007
balls-0.007
ider-0.006
 front-0.005
Tokenama
Token ID1689
Feature activation+2.38e-01

Pos logit contributions
 first+0.046
 next+0.044
ider+0.036
balls+0.035
 last+0.031
Neg logit contributions
aw-0.069
 regretted-0.064
 gol-0.061
opter-0.058
hing-0.053
Token bought
Token ID5839
Feature activation-5.06e-01

Pos logit contributions
 first+0.001
 next+0.001
balls+0.001
 last+0.000
ider+0.000
Neg logit contributions
aw-0.001
 regretted-0.001
 gol-0.001
opter-0.001
ime-0.001
Token the
Token ID262
Feature activation-7.68e-01

Pos logit contributions
 first+0.017
 next+0.015
balls+0.013
ider+0.011
 last+0.010
Neg logit contributions
aw-0.029
 regretted-0.027
 gol-0.026
opter-0.025
ime-0.024
Token blue
Token ID4171
Feature activation-1.48e+00

Pos logit contributions
 first+0.032
 next+0.029
balls+0.025
ider+0.023
 front+0.022
Neg logit contributions
aw-0.041
 regretted-0.037
 gol-0.035
opter-0.033
ime-0.031
Token z
Token ID1976
Feature activation-1.49e+00

Pos logit contributions
 first+0.064
 next+0.059
balls+0.055
ider+0.053
 front+0.046
Neg logit contributions
aw-0.071
 regretted-0.065
 gol-0.061
opter-0.057
ime-0.054
Tokenig
Token ID328
Feature activation-2.18e+00

Pos logit contributions
 first+0.080
 next+0.074
balls+0.071
ider+0.068
 last+0.062
Neg logit contributions
aw-0.055
 regretted-0.045
 gol-0.045
opter-0.039
ime-0.037
Tokenzag
Token ID50183
Feature activation-5.05e+00

Pos logit contributions
 first+0.065
ider+0.062
 next+0.058
balls+0.049
 sip+0.049
Neg logit contributions
aw-0.113
opter-0.096
ane-0.096
 gol-0.091
 regretted-0.091
Token.
Token ID13
Feature activation-8.99e-01

Pos logit contributions
 first+0.211
 next+0.195
ider+0.193
balls+0.186
 seek+0.153
Neg logit contributions
aw-0.232
 regretted-0.202
 gol-0.190
opter-0.185
ime-0.172
Token Tig
Token ID14189
Feature activation-1.71e-01

Pos logit contributions
 first+0.032
 next+0.029
balls+0.027
ider+0.026
 front+0.021
Neg logit contributions
aw-0.049
 regretted-0.045
 gol-0.043
opter-0.040
ime-0.039
Token was
Token ID373
Feature activation-3.78e-02

Pos logit contributions
 first+0.007
 next+0.006
balls+0.006
ider+0.006
 particular+0.005
Neg logit contributions
aw-0.009
 regretted-0.008
 gol-0.007
opter-0.007
ime-0.006
Token so
Token ID523
Feature activation-2.04e-01

Pos logit contributions
 first+0.001
 next+0.001
balls+0.001
ider+0.001
 front+0.001
Neg logit contributions
aw-0.002
 regretted-0.002
 gol-0.002
opter-0.002
ime-0.002
Token happy
Token ID3772
Feature activation-8.15e-02

Pos logit contributions
 first+0.008
 next+0.007
balls+0.006
ider+0.005
 last+0.005
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.010
opter-0.009
 perspective-0.009
Token.
Token ID13
Feature activation+3.28e-01

Pos logit contributions
 first+0.037
 next+0.034
balls+0.031
ider+0.029
 last+0.024
Neg logit contributions
aw-0.060
 regretted-0.056
 gol-0.054
opter-0.050
ime-0.048
Token<|endoftext|>
Token ID50256
Feature activation+4.16e-01

Pos logit contributions
aw+0.019
 regretted+0.017
 gol+0.016
opter+0.016
ime+0.015
Neg logit contributions
 first-0.011
 next-0.010
balls-0.009
ider-0.008
 Mia-0.008
TokenToday
Token ID8888
Feature activation-1.36e+00

Pos logit contributions
aw+0.024
 regretted+0.024
 gol+0.023
opter+0.022
 mustache+0.021
Neg logit contributions
 first-0.013
 next-0.012
balls-0.009
 Mia-0.008
ider-0.008
Token was
Token ID373
Feature activation+1.44e-01

Pos logit contributions
 first+0.048
 next+0.043
balls+0.035
ider+0.033
 one+0.032
Neg logit contributions
aw-0.078
 regretted-0.072
 gol-0.069
opter-0.064
hing-0.062
Token fog
Token ID19558
Feature activation-7.60e-01

Pos logit contributions
aw+0.009
 regretted+0.008
 gol+0.008
opter+0.008
ime+0.007
Neg logit contributions
 first-0.004
 next-0.004
balls-0.003
ider-0.003
 front-0.003
Tokengy
Token ID1360
Feature activation-4.97e+00

Pos logit contributions
 first+0.024
 next+0.021
balls+0.020
ider+0.019
 particular+0.016
Neg logit contributions
aw-0.042
 regretted-0.038
 gol-0.036
opter-0.035
ime-0.034
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
 first+0.181
 next+0.164
balls+0.150
ider+0.144
 last+0.120
Neg logit contributions
aw-0.266
 regretted-0.246
 gol-0.236
opter-0.221
ime-0.209
Token grey
Token ID13791
Feature activation+1.69e+00

Pos logit contributions
 first+0.039
 next+0.035
balls+0.030
ider+0.026
 one+0.026
Neg logit contributions
aw-0.067
 regretted-0.062
 gol-0.062
opter-0.057
ime-0.054
Token.
Token ID13
Feature activation+5.10e-01

Pos logit contributions
aw+0.101
 regretted+0.095
 gol+0.093
opter+0.087
ime+0.082
Neg logit contributions
 first-0.051
 next-0.046
balls-0.041
ider-0.038
 one-0.031
Token The
Token ID383
Feature activation-1.26e+00

Pos logit contributions
aw+0.026
 regretted+0.025
 gol+0.023
opter+0.022
ime+0.020
Neg logit contributions
 first-0.020
 next-0.018
balls-0.017
ider-0.016
 Mia-0.015
Token fog
Token ID19558
Feature activation+5.96e-01

Pos logit contributions
 first+0.063
 next+0.062
 one+0.048
balls+0.047
 front+0.047
Neg logit contributions
aw-0.055
 gol-0.050
 regretted-0.048
arre-0.044
opter-0.044
Token the
Token ID262
Feature activation-5.61e-02

Pos logit contributions
 first+0.026
 next+0.024
balls+0.021
ider+0.020
 last+0.017
Neg logit contributions
aw-0.044
 regretted-0.040
 gol-0.038
opter-0.036
ime-0.034
Token rain
Token ID6290
Feature activation-1.18e+00

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.002
 last+0.002
Neg logit contributions
aw-0.003
 regretted-0.002
 gol-0.002
opter-0.002
ime-0.002
Tokendrops
Token ID49253
Feature activation+2.15e-03

Pos logit contributions
 first+0.045
 next+0.041
ider+0.039
balls+0.039
 front+0.033
Neg logit contributions
aw-0.059
 regretted-0.053
 gol-0.050
opter-0.047
ime-0.045
Token z
Token ID1976
Feature activation-1.17e+00

Pos logit contributions
aw+0.000
 regretted+0.000
 gol+0.000
opter+0.000
ime+0.000
Neg logit contributions
 first-0.000
 next-0.000
balls-0.000
ider-0.000
 last-0.000
Tokenig
Token ID328
Feature activation-2.16e+00

Pos logit contributions
 first+0.061
 next+0.057
balls+0.054
ider+0.052
 front+0.046
Neg logit contributions
aw-0.046
 regretted-0.039
 gol-0.037
opter-0.034
ime-0.032
Tokenzag
Token ID50183
Feature activation-4.94e+00

Pos logit contributions
 first+0.077
 next+0.070
ider+0.069
balls+0.066
 particular+0.057
Neg logit contributions
aw-0.107
 regretted-0.094
opter-0.089
 gol-0.089
ime-0.086
Token down
Token ID866
Feature activation+1.07e+00

Pos logit contributions
 first+0.184
 next+0.168
balls+0.158
ider+0.155
 front+0.126
Neg logit contributions
aw-0.257
 regretted-0.233
 gol-0.221
opter-0.210
ime-0.202
Token the
Token ID262
Feature activation+1.48e-01

Pos logit contributions
aw+0.057
 regretted+0.053
 gol+0.050
opter+0.047
ime+0.045
Neg logit contributions
 first-0.040
 next-0.037
balls-0.033
ider-0.032
 front-0.027
Token window
Token ID4324
Feature activation-6.56e-01

Pos logit contributions
aw+0.007
 regretted+0.006
 gol+0.006
opter+0.005
ime+0.005
Neg logit contributions
 first-0.007
 next-0.006
balls-0.006
ider-0.006
 front-0.005
Token.
Token ID13
Feature activation+3.62e-01

Pos logit contributions
 first+0.025
 next+0.023
balls+0.022
ider+0.021
 front+0.017
Neg logit contributions
aw-0.034
 regretted-0.031
 gol-0.029
opter-0.027
ime-0.026
Token She
Token ID1375
Feature activation+5.35e-02

Pos logit contributions
aw+0.020
 regretted+0.018
 gol+0.018
opter+0.017
ime+0.016
Neg logit contributions
 first-0.013
 next-0.012
balls-0.011
ider-0.010
 Mia-0.009
Token settled
Token ID10282
Feature activation-2.40e-01

Pos logit contributions
 first+0.018
 next+0.017
balls+0.015
ider+0.014
 last+0.013
Neg logit contributions
aw-0.021
 gol-0.019
 regretted-0.018
opter-0.018
aden-0.016
Token back
Token ID736
Feature activation+2.13e-01

Pos logit contributions
 first+0.010
 next+0.010
balls+0.009
ider+0.008
 front+0.007
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.010
opter-0.010
ime-0.009
Token into
Token ID656
Feature activation-2.13e-01

Pos logit contributions
aw+0.011
 regretted+0.010
 gol+0.009
opter+0.009
ime+0.008
Neg logit contributions
 first-0.008
 next-0.007
balls-0.007
ider-0.007
 particular-0.006
Token the
Token ID262
Feature activation+7.14e-01

Pos logit contributions
 first+0.008
 next+0.007
balls+0.007
ider+0.007
 hips+0.006
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.009
opter-0.009
ime-0.008
Token go
Token ID467
Feature activation-6.10e-01

Pos logit contributions
aw+0.031
 regretted+0.028
 gol+0.026
opter+0.024
ime+0.022
Neg logit contributions
 first-0.034
 next-0.031
balls-0.030
ider-0.029
 hips-0.025
Tokenoe
Token ID2577
Feature activation-4.94e+00

Pos logit contributions
 first+0.021
 next+0.019
balls+0.018
ider+0.017
 particular+0.014
Neg logit contributions
aw-0.034
 regretted-0.031
 gol-0.030
opter-0.028
ime-0.027
Tokeny
Token ID88
Feature activation-1.46e+00

Pos logit contributions
 first+0.218
 next+0.203
balls+0.188
ider+0.181
 last+0.158
Neg logit contributions
aw-0.227
 regretted-0.208
 gol-0.197
opter-0.184
ime-0.169
Token mud
Token ID17492
Feature activation+7.55e-01

Pos logit contributions
 first+0.062
 next+0.057
balls+0.054
ider+0.053
 hips+0.045
Neg logit contributions
aw-0.068
 regretted-0.062
 gol-0.059
opter-0.053
ime-0.051
Token.
Token ID13
Feature activation+8.45e-01

Pos logit contributions
aw+0.042
 regretted+0.039
 gol+0.037
opter+0.035
ime+0.033
Neg logit contributions
 first-0.026
 next-0.023
balls-0.021
ider-0.020
 front-0.016
Token He
Token ID679
Feature activation+3.15e-01

Pos logit contributions
aw+0.048
 regretted+0.044
 gol+0.042
opter+0.041
ime+0.039
Neg logit contributions
 first-0.029
 next-0.026
balls-0.024
ider-0.022
 Mia-0.019
Token was
Token ID373
Feature activation+3.24e-01

Pos logit contributions
aw+0.016
 regretted+0.014
 gol+0.014
opter+0.013
ime+0.013
Neg logit contributions
 first-0.012
 next-0.011
balls-0.010
ider-0.010
 last-0.009
Token would
Token ID561
Feature activation+1.83e+00

Pos logit contributions
aw+0.008
 gol+0.007
opter+0.007
 regretted+0.007
ime+0.006
Neg logit contributions
 first-0.005
 next-0.004
balls-0.004
 one-0.003
 last-0.003
Token have
Token ID423
Feature activation-8.75e-01

Pos logit contributions
aw+0.115
 regretted+0.102
 gol+0.099
opter+0.094
ime+0.091
Neg logit contributions
 first-0.059
 next-0.051
balls-0.043
ider-0.039
 last-0.037
Token to
Token ID284
Feature activation+2.79e-01

Pos logit contributions
 first+0.032
 next+0.029
balls+0.025
ider+0.023
 last+0.021
Neg logit contributions
aw-0.048
 regretted-0.044
 gol-0.043
opter-0.041
ime-0.039
Token take
Token ID1011
Feature activation-1.19e-01

Pos logit contributions
aw+0.017
 regretted+0.015
 gol+0.014
opter+0.014
ime+0.013
Neg logit contributions
 first-0.009
 next-0.008
balls-0.007
ider-0.007
 last-0.006
Token the
Token ID262
Feature activation-8.72e-01

Pos logit contributions
 first+0.005
 next+0.004
balls+0.004
 one+0.003
ider+0.003
Neg logit contributions
aw-0.006
 regretted-0.006
 gol-0.006
opter-0.005
ime-0.005
Token next
Token ID1306
Feature activation-4.93e+00

Pos logit contributions
 first+0.033
 next+0.030
balls+0.028
ider+0.027
 last+0.023
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.040
opter-0.038
ime-0.036
Token one
Token ID530
Feature activation-2.80e+00

Pos logit contributions
 first+0.202
 next+0.186
balls+0.184
ider+0.179
 hips+0.152
Neg logit contributions
aw-0.231
 regretted-0.207
 gol-0.205
opter-0.183
ime-0.178
Token,
Token ID11
Feature activation+2.97e-01

Pos logit contributions
 first+0.091
 next+0.082
balls+0.076
ider+0.073
 front+0.057
Neg logit contributions
aw-0.161
 regretted-0.148
 gol-0.142
opter-0.134
ime-0.128
Token but
Token ID475
Feature activation+2.73e-01

Pos logit contributions
aw+0.017
 regretted+0.015
 gol+0.015
opter+0.015
ime+0.014
Neg logit contributions
 first-0.010
 next-0.009
balls-0.008
ider-0.008
 front-0.007
Token it
Token ID340
Feature activation+9.01e-01

Pos logit contributions
aw+0.016
 regretted+0.015
 gol+0.014
opter+0.013
ime+0.013
Neg logit contributions
 first-0.009
 next-0.008
balls-0.007
ider-0.007
 last-0.005
Token was
Token ID373
Feature activation+4.45e-01

Pos logit contributions
aw+0.043
 regretted+0.040
 gol+0.037
opter+0.035
ime+0.033
Neg logit contributions
 first-0.036
 next-0.034
balls-0.032
ider-0.032
 front-0.027
Token never
Token ID1239
Feature activation+3.49e-01

Pos logit contributions
aw+0.075
 gol+0.066
 regretted+0.064
opter+0.062
ime+0.060
Neg logit contributions
 first-0.062
 next-0.058
balls-0.049
ider-0.046
 last-0.044
Token refused
Token ID6520
Feature activation+9.20e-01

Pos logit contributions
aw+0.019
opter+0.016
 gol+0.016
anes+0.015
ane+0.015
Neg logit contributions
 first-0.014
 next-0.012
 last-0.010
 seek-0.010
 one-0.010
Token the
Token ID262
Feature activation+3.82e-01

Pos logit contributions
aw+0.059
opter+0.054
 gol+0.052
 regretted+0.052
hing+0.048
Neg logit contributions
 first-0.028
 next-0.026
balls-0.019
 one-0.017
 last-0.016
Token z
Token ID1976
Feature activation-1.60e+00

Pos logit contributions
aw+0.019
 regretted+0.017
 gol+0.016
opter+0.015
ime+0.014
Neg logit contributions
 first-0.016
 next-0.015
balls-0.014
ider-0.013
 last-0.011
Tokenig
Token ID328
Feature activation-2.13e+00

Pos logit contributions
 first+0.088
 next+0.082
balls+0.079
ider+0.074
 hips+0.070
Neg logit contributions
aw-0.056
 gol-0.045
 regretted-0.045
opter-0.040
ime-0.038
Tokenzag
Token ID50183
Feature activation-4.92e+00

Pos logit contributions
 first+0.058
 next+0.050
ider+0.047
balls+0.046
 timer+0.037
Neg logit contributions
aw-0.120
 regretted-0.107
 gol-0.104
opter-0.102
ime-0.101
Token again
Token ID757
Feature activation-1.63e+00

Pos logit contributions
 first+0.180
 next+0.163
balls+0.155
ider+0.150
 front+0.122
Neg logit contributions
aw-0.258
 regretted-0.236
 gol-0.225
opter-0.212
ime-0.203
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
 first+0.054
 next+0.049
balls+0.045
ider+0.043
 front+0.034
Neg logit contributions
aw-0.093
 regretted-0.086
 gol-0.082
opter-0.078
ime-0.074
Token<|endoftext|>
Token ID50256
Feature activation+7.22e-01

Pos logit contributions
aw+0.030
 regretted+0.027
 gol+0.026
opter+0.025
ime+0.024
Neg logit contributions
 first-0.018
 next-0.016
balls-0.014
ider-0.013
 front-0.011
TokenJohn
Token ID7554
Feature activation-1.82e-01

Pos logit contributions
aw+0.039
 regretted+0.037
 gol+0.035
opter+0.033
 mustache+0.031
Neg logit contributions
 first-0.026
 next-0.025
balls-0.021
ider-0.019
 front-0.018
Token had
Token ID550
Feature activation+7.02e-01

Pos logit contributions
 first+0.006
 next+0.006
 one+0.004
 last+0.004
 Mia+0.004
Neg logit contributions
aw-0.010
 gol-0.010
opter-0.009
 regretted-0.009
 perspective-0.009
Token mom
Token ID1995
Feature activation+4.86e-02

Pos logit contributions
aw+0.094
 regretted+0.088
 gol+0.083
opter+0.076
ime+0.073
Neg logit contributions
 first-0.064
 next-0.058
ider-0.055
balls-0.055
 seek-0.043
Token brought
Token ID3181
Feature activation-5.99e-01

Pos logit contributions
aw+0.002
 regretted+0.002
 gol+0.002
opter+0.002
ime+0.002
Neg logit contributions
 first-0.002
 next-0.002
balls-0.002
ider-0.002
 last-0.002
Token the
Token ID262
Feature activation-1.35e+00

Pos logit contributions
 first+0.025
ider+0.024
 next+0.023
balls+0.023
 seek+0.018
Neg logit contributions
aw-0.029
 regretted-0.025
 gol-0.024
opter-0.022
ime-0.021
Token fortune
Token ID15807
Feature activation-3.12e-01

Pos logit contributions
 first+0.062
 next+0.057
balls+0.057
ider+0.055
 hips+0.048
Neg logit contributions
aw-0.056
 regretted-0.052
 gol-0.048
opter-0.044
ime-0.041
Token-
Token ID12
Feature activation-2.77e+00

Pos logit contributions
 first+0.013
 next+0.012
balls+0.011
ider+0.011
 front+0.009
Neg logit contributions
aw-0.016
 regretted-0.014
 gol-0.013
opter-0.012
ime-0.012
Tokente
Token ID660
Feature activation-4.92e+00

Pos logit contributions
 first+0.119
 next+0.107
ider+0.107
balls+0.106
 hips+0.094
Neg logit contributions
aw-0.132
 regretted-0.112
 gol-0.106
opter-0.099
ime-0.096
Tokenller
Token ID6051
Feature activation-3.13e+00

Pos logit contributions
 first+0.195
 next+0.178
balls+0.167
ider+0.162
 front+0.135
Neg logit contributions
aw-0.250
 regretted-0.227
 gol-0.216
opter-0.203
ime-0.193
Token toy
Token ID13373
Feature activation+1.62e-01

Pos logit contributions
 first+0.136
ider+0.131
 next+0.125
balls+0.124
 particular+0.106
Neg logit contributions
aw-0.142
 regretted-0.122
 gol-0.115
opter-0.101
ime-0.100
Token home
Token ID1363
Feature activation+3.79e-01

Pos logit contributions
aw+0.009
 regretted+0.008
 gol+0.008
opter+0.007
ime+0.007
Neg logit contributions
 first-0.006
 next-0.005
balls-0.005
ider-0.005
 last-0.004
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
aw+0.020
 regretted+0.018
 gol+0.016
opter+0.015
ime+0.015
Neg logit contributions
 first-0.014
 next-0.012
balls-0.012
ider-0.012
 particular-0.010
Token When
Token ID1649
Feature activation-5.34e-01

Pos logit contributions
 first+0.006
 next+0.005
balls+0.005
ider+0.005
 front+0.004
Neg logit contributions
aw-0.009
 regretted-0.009
 gol-0.008
opter-0.008
ime-0.007
Token they
Token ID484
Feature activation-5.13e-01

Pos logit contributions
 first+0.022
ider+0.022
balls+0.021
 next+0.020
 hips+0.017
Neg logit contributions
aw-0.034
 regretted-0.032
 gol-0.029
opter-0.029
ime-0.028
Token took
Token ID1718
Feature activation-6.65e-01

Pos logit contributions
 first+0.023
 next+0.020
balls+0.018
 last+0.017
ider+0.017
Neg logit contributions
aw-0.025
 gol-0.022
 regretted-0.021
opter-0.020
ime-0.018
Token it
Token ID340
Feature activation-2.07e+00

Pos logit contributions
 first+0.025
 next+0.022
balls+0.021
ider+0.021
 front+0.016
Neg logit contributions
aw-0.036
 regretted-0.032
 gol-0.031
opter-0.029
ime-0.028
Token out
Token ID503
Feature activation-1.03e+00

Pos logit contributions
 first+0.091
 next+0.084
ider+0.081
balls+0.081
 hips+0.068
Neg logit contributions
aw-0.091
 regretted-0.081
 gol-0.076
opter-0.071
ime-0.069
Token the
Token ID262
Feature activation-6.80e-01

Pos logit contributions
 first+0.044
 next+0.040
balls+0.039
ider+0.038
 front+0.032
Neg logit contributions
aw-0.048
 regretted-0.044
 gol-0.041
opter-0.038
ime-0.037
Token next
Token ID1306
Feature activation-4.91e+00

Pos logit contributions
 first+0.026
balls+0.024
ider+0.024
 next+0.024
 seek+0.020
Neg logit contributions
aw-0.032
 regretted-0.030
 gol-0.027
opter-0.025
ime-0.025
Token day
Token ID1110
Feature activation-2.52e+00

Pos logit contributions
 first+0.201
balls+0.194
ider+0.191
 next+0.181
 hips+0.159
Neg logit contributions
aw-0.218
 gol-0.194
 regretted-0.191
ime-0.179
opter-0.168
Token,
Token ID11
Feature activation+4.89e-01

Pos logit contributions
 first+0.089
 next+0.082
balls+0.068
ider+0.063
 last+0.058
Neg logit contributions
aw-0.141
 regretted-0.136
 gol-0.128
opter-0.120
umper-0.112
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
aw+0.030
 regretted+0.027
 gol+0.026
opter+0.025
ime+0.024
Neg logit contributions
 first-0.015
 next-0.013
balls-0.012
ider-0.011
 front-0.009
Token jelly
Token ID27644
Feature activation+8.22e-01

Pos logit contributions
aw+0.049
 regretted+0.045
 gol+0.042
opter+0.039
ime+0.037
Neg logit contributions
 first-0.045
 next-0.042
balls-0.040
ider-0.039
 front-0.033
Token was
Token ID373
Feature activation-3.12e-01

Pos logit contributions
aw+0.042
 regretted+0.038
 gol+0.035
opter+0.033
ime+0.032
Neg logit contributions
 first-0.032
 next-0.029
balls-0.028
ider-0.027
 front-0.023
Token up
Token ID510
Feature activation-2.09e+00

Pos logit contributions
 first+0.036
 next+0.034
balls+0.029
ider+0.028
 front+0.026
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.041
opter-0.038
ime-0.035
Token.
Token ID13
Feature activation-5.61e-01

Pos logit contributions
 first+0.074
balls+0.066
 next+0.065
ider+0.063
 hips+0.050
Neg logit contributions
aw-0.112
 regretted-0.103
 gol-0.097
opter-0.091
ime-0.089
Token It
Token ID632
Feature activation-9.09e-01

Pos logit contributions
 first+0.020
 next+0.019
balls+0.015
ider+0.015
 front+0.014
Neg logit contributions
aw-0.031
 regretted-0.029
 gol-0.028
opter-0.027
act-0.025
Token was
Token ID373
Feature activation-6.74e-01

Pos logit contributions
 first+0.036
 next+0.032
balls+0.031
ider+0.031
 hips+0.025
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.039
opter-0.037
ime-0.035
Token the
Token ID262
Feature activation-6.65e-01

Pos logit contributions
 first+0.025
 next+0.023
balls+0.018
 last+0.018
 one+0.017
Neg logit contributions
aw-0.038
 gol-0.035
 regretted-0.034
opter-0.033
act-0.030
Token next
Token ID1306
Feature activation-4.91e+00

Pos logit contributions
 first+0.025
 next+0.023
balls+0.020
ider+0.019
 last+0.018
Neg logit contributions
aw-0.036
 regretted-0.033
 gol-0.032
opter-0.030
ime-0.028
Token day
Token ID1110
Feature activation-2.52e+00

Pos logit contributions
 first+0.183
 next+0.167
balls+0.152
ider+0.146
 last+0.123
Neg logit contributions
aw-0.264
 regretted-0.243
 gol-0.232
opter-0.218
ime-0.206
Token and
Token ID290
Feature activation-6.08e-01

Pos logit contributions
 first+0.088
 next+0.084
balls+0.062
 one+0.060
 last+0.058
Neg logit contributions
aw-0.140
 regretted-0.134
 gol-0.133
opter-0.125
act-0.118
Token he
Token ID339
Feature activation+9.41e-01

Pos logit contributions
 first+0.024
 next+0.023
 one+0.017
balls+0.017
 last+0.017
Neg logit contributions
aw-0.033
 gol-0.031
 regretted-0.029
act-0.027
opter-0.027
Token was
Token ID373
Feature activation+2.14e-01

Pos logit contributions
aw+0.050
 gol+0.046
opter+0.042
 regretted+0.042
ime+0.040
Neg logit contributions
 first-0.037
 next-0.034
balls-0.028
ider-0.026
 last-0.025
Token feeling
Token ID4203
Feature activation-2.42e-01

Pos logit contributions
aw+0.012
 gol+0.011
 regretted+0.010
opter+0.010
ime+0.009
Neg logit contributions
 first-0.008
 next-0.007
balls-0.006
ider-0.006
 front-0.005
Token
Token ID198
Feature activation-6.21e-02

Pos logit contributions
aw+0.023
 regretted+0.021
 gol+0.020
opter+0.019
ime+0.018
Neg logit contributions
 first-0.016
 next-0.014
balls-0.013
ider-0.013
 front-0.010
TokenWhen
Token ID2215
Feature activation-1.05e+00

Pos logit contributions
 first+0.003
 next+0.002
balls+0.002
ider+0.002
 front+0.002
Neg logit contributions
aw-0.003
 regretted-0.003
 gol-0.003
opter-0.003
ime-0.002
Token they
Token ID484
Feature activation-9.35e-01

Pos logit contributions
 first+0.038
 next+0.034
ider+0.034
balls+0.033
 hips+0.027
Neg logit contributions
aw-0.054
 regretted-0.050
 gol-0.048
opter-0.045
ime-0.043
Token took
Token ID1718
Feature activation-6.11e-01

Pos logit contributions
 first+0.042
 next+0.038
balls+0.033
 last+0.032
ider+0.031
Neg logit contributions
aw-0.044
 gol-0.039
 regretted-0.038
opter-0.036
 perspective-0.033
Token their
Token ID511
Feature activation-2.67e+00

Pos logit contributions
 first+0.023
 next+0.021
balls+0.019
ider+0.019
 front+0.015
Neg logit contributions
aw-0.033
 regretted-0.030
 gol-0.028
opter-0.027
ime-0.025
Token next
Token ID1306
Feature activation-4.89e+00

Pos logit contributions
 first+0.109
ider+0.106
 next+0.100
balls+0.099
 seek+0.086
Neg logit contributions
aw-0.122
 regretted-0.109
ime-0.093
 gol-0.093
 mustache-0.092
Token bite
Token ID13197
Feature activation-2.73e+00

Pos logit contributions
 first+0.183
 next+0.167
balls+0.162
ider+0.159
 hips+0.128
Neg logit contributions
aw-0.248
 regretted-0.225
 gol-0.218
opter-0.201
ime-0.198
Token,
Token ID11
Feature activation+3.89e-01

Pos logit contributions
 first+0.097
 next+0.086
balls+0.077
ider+0.066
 last+0.063
Neg logit contributions
aw-0.154
 regretted-0.146
 gol-0.142
opter-0.130
aden-0.124
Token the
Token ID262
Feature activation+1.09e+00

Pos logit contributions
aw+0.024
 regretted+0.022
 gol+0.021
opter+0.020
ime+0.019
Neg logit contributions
 first-0.012
 next-0.011
balls-0.010
ider-0.009
 front-0.007
Token toast
Token ID27805
Feature activation-5.28e-02

Pos logit contributions
aw+0.055
 gol+0.050
 regretted+0.050
opter+0.047
ime+0.043
Neg logit contributions
 first-0.045
 next-0.042
balls-0.037
ider-0.035
 last-0.032
Token was
Token ID373
Feature activation-2.88e-01

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.002
 last+0.001
Neg logit contributions
aw-0.003
 regretted-0.003
 gol-0.002
opter-0.002
ime-0.002
Token"
Token ID1
Feature activation-2.01e+00

Pos logit contributions
 first+0.022
 next+0.020
balls+0.017
ider+0.017
 front+0.014
Neg logit contributions
aw-0.034
 regretted-0.032
 gol-0.030
opter-0.029
ime-0.028
TokenLet
Token ID5756
Feature activation-3.31e-01

Pos logit contributions
 first+0.082
 next+0.075
balls+0.070
ider+0.068
 front+0.058
Neg logit contributions
aw-0.100
 regretted-0.091
 gol-0.087
opter-0.081
ime-0.077
Token's
Token ID338
Feature activation-4.20e-02

Pos logit contributions
 first+0.012
 next+0.011
balls+0.009
ider+0.008
 front+0.008
Neg logit contributions
aw-0.018
 regretted-0.017
 gol-0.017
opter-0.015
ime-0.015
Token set
Token ID900
Feature activation-9.42e-01

Pos logit contributions
 first+0.001
 next+0.001
balls+0.001
ider+0.001
 last+0.001
Neg logit contributions
aw-0.002
 regretted-0.002
 gol-0.002
opter-0.002
ime-0.002
Token the
Token ID262
Feature activation-6.18e-01

Pos logit contributions
ider+0.042
 first+0.040
balls+0.038
 next+0.038
 particular+0.034
Neg logit contributions
aw-0.039
 regretted-0.030
 gol-0.030
opter-0.029
ime-0.028
Token timer
Token ID19781
Feature activation-4.89e+00

Pos logit contributions
 first+0.020
ider+0.019
balls+0.018
 next+0.017
 hips+0.016
Neg logit contributions
aw-0.031
 regretted-0.029
opter-0.025
 gol-0.025
 mustache-0.025
Token for
Token ID329
Feature activation-5.03e-01

Pos logit contributions
 first+0.185
 next+0.171
balls+0.166
ider+0.162
 particular+0.140
Neg logit contributions
aw-0.240
 regretted-0.211
 gol-0.201
opter-0.194
ime-0.182
Token 30
Token ID1542
Feature activation-2.85e+00

Pos logit contributions
 first+0.019
ider+0.018
balls+0.018
 next+0.017
 particular+0.015
Neg logit contributions
aw-0.024
 regretted-0.021
 gol-0.020
opter-0.019
ime-0.019
Token minutes
Token ID2431
Feature activation-3.82e+00

Pos logit contributions
 first+0.096
balls+0.086
 next+0.086
ider+0.080
 Luna+0.069
Neg logit contributions
aw-0.161
 regretted-0.138
opter-0.128
 gol-0.127
ime-0.125
Token,"
Token ID553
Feature activation-7.82e-01

Pos logit contributions
 first+0.151
 next+0.139
balls+0.135
ider+0.131
 particular+0.111
Neg logit contributions
aw-0.186
 regretted-0.167
 gol-0.159
opter-0.149
ime-0.143
Token dad
Token ID9955
Feature activation+2.41e+00

Pos logit contributions
 first+0.024
 next+0.021
balls+0.018
ider+0.016
 Mia+0.014
Neg logit contributions
aw-0.048
 regretted-0.044
 gol-0.043
opter-0.041
ime-0.040
TokenThe
Token ID464
Feature activation-1.05e+00

Pos logit contributions
 first+0.005
balls+0.005
 next+0.005
ider+0.004
 last+0.004
Neg logit contributions
aw-0.008
 regretted-0.007
 gol-0.007
ime-0.007
opter-0.007
Token doctor
Token ID6253
Feature activation-1.54e+00

Pos logit contributions
 first+0.050
 next+0.046
balls+0.044
ider+0.043
 hips+0.037
Neg logit contributions
aw-0.045
 regretted-0.040
 gol-0.038
opter-0.034
ime-0.033
Token put
Token ID1234
Feature activation-7.28e-01

Pos logit contributions
 first+0.059
 next+0.054
balls+0.048
ider+0.046
 one+0.040
Neg logit contributions
aw-0.080
 gol-0.072
 regretted-0.072
opter-0.067
ime-0.064
Token the
Token ID262
Feature activation-1.03e+00

Pos logit contributions
 first+0.024
 next+0.021
ider+0.020
balls+0.020
 seek+0.015
Neg logit contributions
aw-0.041
 regretted-0.037
 gol-0.036
opter-0.033
ime-0.033
Token st
Token ID336
Feature activation-1.33e+00

Pos logit contributions
 first+0.047
 next+0.043
balls+0.040
ider+0.039
 front+0.034
Neg logit contributions
aw-0.048
 regretted-0.042
 gol-0.042
opter-0.039
ime-0.036
Tokeneth
Token ID2788
Feature activation-4.87e+00

Pos logit contributions
 first+0.050
 next+0.046
balls+0.044
ider+0.044
 front+0.036
Neg logit contributions
aw-0.069
 regretted-0.064
 gol-0.063
opter-0.056
ime-0.053
Tokenoscope
Token ID40326
Feature activation-3.77e+00

Pos logit contributions
 first+0.164
 next+0.146
balls+0.140
ider+0.134
 seek+0.108
Neg logit contributions
aw-0.272
 regretted-0.248
 gol-0.231
opter-0.219
ime-0.215
Token on
Token ID319
Feature activation-3.85e-01

Pos logit contributions
 first+0.144
 next+0.133
balls+0.110
ider+0.102
 one+0.096
Neg logit contributions
aw-0.200
 regretted-0.195
 gol-0.190
opter-0.179
 perspective-0.165
Token Molly
Token ID30236
Feature activation-1.14e+00

Pos logit contributions
ider+0.016
balls+0.014
 first+0.014
 next+0.014
 seek+0.012
Neg logit contributions
aw-0.017
 regretted-0.015
 gol-0.013
ime-0.013
 mustache-0.012
Token's
Token ID338
Feature activation-6.89e-01

Pos logit contributions
 first+0.038
 next+0.034
balls+0.028
ider+0.026
 hips+0.024
Neg logit contributions
aw-0.067
 gol-0.063
 regretted-0.062
opter-0.059
ime-0.054
Token chest
Token ID7721
Feature activation+2.83e-01

Pos logit contributions
 first+0.030
 next+0.028
balls+0.026
ider+0.026
 front+0.022
Neg logit contributions
aw-0.032
 regretted-0.029
 gol-0.028
opter-0.026
ime-0.024
Token fly
Token ID6129
Feature activation-1.14e+00

Pos logit contributions
aw+0.099
 regretted+0.091
 gol+0.087
opter+0.082
ime+0.078
Neg logit contributions
 first-0.063
 next-0.057
balls-0.052
ider-0.050
 last-0.042
Token like
Token ID588
Feature activation+3.55e-01

Pos logit contributions
 first+0.043
 next+0.039
balls+0.034
ider+0.031
 last+0.028
Neg logit contributions
aw-0.061
 regretted-0.058
 gol-0.056
opter-0.052
ime-0.049
Token the
Token ID262
Feature activation+4.47e-01

Pos logit contributions
aw+0.021
 regretted+0.020
 gol+0.019
opter+0.019
arre+0.018
Neg logit contributions
 first-0.012
 next-0.011
balls-0.009
 one-0.008
 last-0.007
Token z
Token ID1976
Feature activation-1.63e+00

Pos logit contributions
aw+0.022
 regretted+0.021
 gol+0.020
opter+0.019
arre+0.018
Neg logit contributions
 first-0.019
 next-0.018
balls-0.015
ider-0.014
 last-0.014
Tokenig
Token ID328
Feature activation-1.91e+00

Pos logit contributions
 first+0.087
 next+0.081
balls+0.078
ider+0.074
 front+0.067
Neg logit contributions
aw-0.061
 regretted-0.050
 gol-0.048
opter-0.044
ime-0.042
Tokenzag
Token ID50183
Feature activation-4.85e+00

Pos logit contributions
 first+0.047
 next+0.040
balls+0.037
ider+0.036
 front+0.026
Neg logit contributions
aw-0.122
 regretted-0.110
 gol-0.106
opter-0.104
ime-0.101
Token if
Token ID611
Feature activation-3.11e-01

Pos logit contributions
 first+0.192
 next+0.175
balls+0.160
ider+0.154
 last+0.133
Neg logit contributions
aw-0.247
 regretted-0.228
 gol-0.219
opter-0.201
ime-0.190
Token he
Token ID339
Feature activation+1.08e+00

Pos logit contributions
 first+0.011
 next+0.010
balls+0.008
ider+0.007
 one+0.007
Neg logit contributions
aw-0.018
 regretted-0.016
 gol-0.016
opter-0.015
arre-0.015
Token just
Token ID655
Feature activation+3.64e-01

Pos logit contributions
aw+0.052
 gol+0.047
 regretted+0.046
opter+0.043
ime+0.039
Neg logit contributions
 first-0.046
 next-0.042
balls-0.036
ider-0.036
 last-0.034
Token opened
Token ID4721
Feature activation-1.65e+00

Pos logit contributions
aw+0.018
 gol+0.016
 regretted+0.015
opter+0.015
arre+0.014
Neg logit contributions
 first-0.015
 next-0.014
 last-0.012
ider-0.012
balls-0.011
Token his
Token ID465
Feature activation-6.48e-02

Pos logit contributions
 first+0.059
 next+0.054
balls+0.043
 one+0.040
 front+0.040
Neg logit contributions
aw-0.093
 regretted-0.089
 gol-0.086
opter-0.082
arre-0.076
Token ready
Token ID3492
Feature activation-1.51e-01

Pos logit contributions
aw+0.008
 regretted+0.007
 gol+0.007
opter+0.007
ime+0.006
Neg logit contributions
 first-0.006
 next-0.006
balls-0.005
ider-0.005
 front-0.004
Token to
Token ID284
Feature activation-8.52e-01

Pos logit contributions
 first+0.005
 next+0.004
balls+0.004
ider+0.004
 last+0.003
Neg logit contributions
aw-0.009
 regretted-0.008
 gol-0.008
opter-0.007
ime-0.007
Token take
Token ID1011
Feature activation-5.94e-01

Pos logit contributions
 first+0.030
 next+0.027
balls+0.021
 last+0.021
 front+0.020
Neg logit contributions
aw-0.050
 regretted-0.046
 gol-0.044
opter-0.041
ime-0.038
Token on
Token ID319
Feature activation-1.50e+00

Pos logit contributions
 first+0.019
 next+0.017
balls+0.014
 one+0.012
 last+0.012
Neg logit contributions
aw-0.035
 regretted-0.034
 gol-0.033
opter-0.031
ime-0.028
Token the
Token ID262
Feature activation-3.25e-01

Pos logit contributions
 first+0.058
 next+0.052
balls+0.049
ider+0.048
 last+0.039
Neg logit contributions
aw-0.078
 regretted-0.071
 gol-0.067
opter-0.063
ime-0.060
Token next
Token ID1306
Feature activation-4.83e+00

Pos logit contributions
 first+0.013
balls+0.013
ider+0.012
 next+0.012
 Luna+0.010
Neg logit contributions
aw-0.015
 regretted-0.013
 gol-0.013
opter-0.011
 mustache-0.011
Token adventure
Token ID8855
Feature activation-9.99e-01

Pos logit contributions
balls+0.198
 first+0.197
ider+0.190
 next+0.177
 hips+0.163
Neg logit contributions
aw-0.208
 gol-0.186
 regretted-0.175
ime-0.165
opter-0.160
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
 first+0.034
 next+0.031
balls+0.027
ider+0.026
 last+0.022
Neg logit contributions
aw-0.056
 regretted-0.053
 gol-0.051
opter-0.048
ime-0.045
Token<|endoftext|>
Token ID50256
Feature activation+5.09e-01

Pos logit contributions
 first+0.005
 next+0.005
balls+0.004
ider+0.004
 Mia+0.004
Neg logit contributions
aw-0.008
 regretted-0.008
 gol-0.007
opter-0.007
ime-0.006
TokenOnce
Token ID7454
Feature activation-2.71e-01

Pos logit contributions
aw+0.028
 regretted+0.027
 gol+0.026
opter+0.024
 mustache+0.023
Neg logit contributions
 first-0.018
 next-0.017
balls-0.014
ider-0.013
 front-0.012
Token upon
Token ID2402
Feature activation+1.50e+00

Pos logit contributions
 first+0.011
 next+0.010
balls+0.009
ider+0.008
 last+0.008
Neg logit contributions
aw-0.014
 regretted-0.013
 gol-0.012
opter-0.011
ime-0.010
Token each
Token ID1123
Feature activation-2.51e-01

Pos logit contributions
 first+0.029
 next+0.026
ider+0.026
balls+0.026
 seek+0.021
Neg logit contributions
aw-0.041
 regretted-0.036
 gol-0.034
opter-0.031
ime-0.031
Token other
Token ID584
Feature activation+4.36e-01

Pos logit contributions
ider+0.012
balls+0.011
 first+0.011
 next+0.011
 seek+0.010
Neg logit contributions
aw-0.010
 regretted-0.008
 gol-0.007
ime-0.007
 tant-0.007
Token's
Token ID338
Feature activation-2.16e+00

Pos logit contributions
aw+0.024
 regretted+0.022
 gol+0.021
opter+0.021
ime+0.019
Neg logit contributions
 first-0.016
 next-0.014
balls-0.013
ider-0.012
 last-0.010
Token hair
Token ID4190
Feature activation-5.91e-02

Pos logit contributions
 first+0.087
 next+0.080
ider+0.076
balls+0.075
 particular+0.064
Neg logit contributions
aw-0.105
 regretted-0.095
 gol-0.090
opter-0.081
ime-0.080
Token and
Token ID290
Feature activation+1.89e-01

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.002
 last+0.001
Neg logit contributions
aw-0.003
 regretted-0.003
 gol-0.003
opter-0.003
ime-0.003
Token clothes
Token ID8242
Feature activation+3.91e+00

Pos logit contributions
aw+0.010
 regretted+0.009
 gol+0.008
opter+0.008
ime+0.007
Neg logit contributions
 first-0.008
 next-0.007
balls-0.007
ider-0.006
 front-0.005
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
aw+0.254
 regretted+0.238
 gol+0.238
opter+0.230
ime+0.217
Neg logit contributions
 first-0.113
 next-0.100
balls-0.081
ider-0.065
 last-0.064
Token They
Token ID1119
Feature activation-3.77e-01

Pos logit contributions
aw+0.006
 regretted+0.006
 gol+0.005
opter+0.005
ime+0.005
Neg logit contributions
 first-0.004
 next-0.004
balls-0.004
ider-0.004
 last-0.003
Token are
Token ID389
Feature activation-1.91e-01

Pos logit contributions
 first+0.014
 next+0.012
balls+0.011
 last+0.010
ider+0.010
Neg logit contributions
aw-0.021
 gol-0.019
 regretted-0.018
opter-0.018
ime-0.017
Token very
Token ID845
Feature activation-1.88e-01

Pos logit contributions
 first+0.008
 next+0.008
balls+0.007
ider+0.007
 last+0.006
Neg logit contributions
aw-0.009
 regretted-0.008
 gol-0.008
opter-0.008
ime-0.007
Token loud
Token ID7812
Feature activation+2.48e-01

Pos logit contributions
 first+0.009
 next+0.009
balls+0.008
ider+0.008
 last+0.007
Neg logit contributions
aw-0.008
 regretted-0.007
 gol-0.007
opter-0.006
ime-0.006
Token you
Token ID345
Feature activation+1.18e+00

Pos logit contributions
 first+0.019
 next+0.017
balls+0.015
ider+0.014
 last+0.012
Neg logit contributions
aw-0.032
 regretted-0.029
 gol-0.028
opter-0.026
ime-0.025
Token are
Token ID389
Feature activation+1.71e-01

Pos logit contributions
aw+0.064
 regretted+0.056
 gol+0.054
opter+0.052
ime+0.049
Neg logit contributions
 first-0.047
 next-0.041
balls-0.035
 last-0.034
ider-0.033
Token kind
Token ID1611
Feature activation+2.01e-01

Pos logit contributions
aw+0.009
 regretted+0.008
 gol+0.008
opter+0.007
ime+0.007
Neg logit contributions
 first-0.007
 next-0.006
balls-0.006
ider-0.005
 last-0.005
Token and
Token ID290
Feature activation-1.12e+00

Pos logit contributions
aw+0.013
 gol+0.012
opter+0.012
 regretted+0.011
aden+0.011
Neg logit contributions
 first-0.006
 next-0.006
 one-0.004
balls-0.004
 last-0.004
Token help
Token ID1037
Feature activation-2.34e-01

Pos logit contributions
 first+0.045
 next+0.041
balls+0.040
ider+0.039
 front+0.033
Neg logit contributions
aw-0.054
 regretted-0.050
 gol-0.047
opter-0.043
ime-0.041
Token others
Token ID1854
Feature activation+3.99e+00

Pos logit contributions
 first+0.010
 next+0.010
balls+0.008
 last+0.007
 one+0.007
Neg logit contributions
aw-0.012
 regretted-0.010
 gol-0.010
opter-0.009
aden-0.009
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
aw+0.232
 regretted+0.207
 gol+0.206
opter+0.189
aden+0.180
Neg logit contributions
 first-0.149
 next-0.135
balls-0.110
ider-0.103
 last-0.096
Token you
Token ID345
Feature activation+2.03e+00

Pos logit contributions
aw+0.075
 regretted+0.068
 gol+0.066
opter+0.064
ime+0.059
Neg logit contributions
 first-0.041
 next-0.038
balls-0.030
ider-0.026
 one-0.025
Token can
Token ID460
Feature activation+1.11e+00

Pos logit contributions
aw+0.100
 gol+0.083
 regretted+0.081
opter+0.073
aden+0.072
Neg logit contributions
 first-0.097
 next-0.086
balls-0.074
 last-0.073
ider-0.071
Token make
Token ID787
Feature activation-9.85e-01

Pos logit contributions
aw+0.056
 regretted+0.052
 gol+0.049
opter+0.046
ime+0.044
Neg logit contributions
 first-0.041
 next-0.038
balls-0.037
ider-0.036
 hips-0.029
Token them
Token ID606
Feature activation+5.58e-02

Pos logit contributions
 first+0.036
 next+0.033
balls+0.027
 one+0.026
 some+0.024
Neg logit contributions
aw-0.053
 regretted-0.051
 gol-0.049
opter-0.046
ane-0.043
Token of
Token ID286
Feature activation-4.63e-01

Pos logit contributions
aw+0.041
 regretted+0.036
 gol+0.034
opter+0.032
ime+0.030
Neg logit contributions
 first-0.042
 next-0.039
balls-0.037
ider-0.036
 front-0.031
Token toys
Token ID14958
Feature activation+1.87e+00

Pos logit contributions
 first+0.018
 next+0.016
balls+0.014
ider+0.013
 one+0.013
Neg logit contributions
aw-0.024
 regretted-0.023
 gol-0.021
opter-0.021
ime-0.019
Token and
Token ID290
Feature activation-5.30e-01

Pos logit contributions
aw+0.105
 regretted+0.100
 gol+0.094
opter+0.092
ime+0.087
Neg logit contributions
 first-0.066
 next-0.060
balls-0.052
ider-0.050
 last-0.042
Token books
Token ID3835
Feature activation+2.82e+00

Pos logit contributions
 first+0.021
 next+0.019
balls+0.018
ider+0.017
 last+0.015
Neg logit contributions
aw-0.027
 regretted-0.024
 gol-0.024
opter-0.022
ime-0.021
Token and
Token ID290
Feature activation+7.71e-02

Pos logit contributions
aw+0.162
 regretted+0.150
 gol+0.143
opter+0.135
ime+0.129
Neg logit contributions
 first-0.092
 next-0.083
balls-0.076
ider-0.073
 front-0.058
Token clothes
Token ID8242
Feature activation+4.46e+00

Pos logit contributions
aw+0.004
 regretted+0.003
 gol+0.003
opter+0.003
ime+0.003
Neg logit contributions
 first-0.003
 next-0.003
balls-0.003
ider-0.002
 last-0.002
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
aw+0.267
 regretted+0.249
 gol+0.240
opter+0.227
ime+0.219
Neg logit contributions
 first-0.139
 next-0.124
balls-0.111
ider-0.104
 last-0.083
Token But
Token ID887
Feature activation-1.04e+00

Pos logit contributions
aw+0.006
 regretted+0.006
 gol+0.005
opter+0.005
ime+0.005
Neg logit contributions
 first-0.005
 next-0.004
balls-0.004
ider-0.004
 seek-0.003
Token sometimes
Token ID3360
Feature activation-1.60e+00

Pos logit contributions
balls+0.031
ider+0.030
 first+0.028
 next+0.026
 hips+0.025
Neg logit contributions
aw-0.052
 regretted-0.051
 gol-0.047
opter-0.041
ateful-0.039
Token they
Token ID484
Feature activation-4.11e-01

Pos logit contributions
 first+0.033
 next+0.027
balls+0.018
 one+0.015
 Mia+0.013
Neg logit contributions
aw-0.116
 regretted-0.107
 gol-0.107
opter-0.101
ime-0.098
Token do
Token ID466
Feature activation+1.26e-01

Pos logit contributions
 first+0.015
 next+0.013
balls+0.011
 last+0.010
ider+0.010
Neg logit contributions
aw-0.024
 gol-0.021
 regretted-0.021
opter-0.020
ime-0.019
Token decorations
Token ID39011
Feature activation+4.27e-01

Pos logit contributions
 first+0.029
 next+0.026
balls+0.022
ider+0.019
 front+0.019
Neg logit contributions
aw-0.045
 regretted-0.043
 gol-0.042
opter-0.040
ime-0.037
Token of
Token ID286
Feature activation+3.45e-01

Pos logit contributions
aw+0.025
 regretted+0.024
 gol+0.022
opter+0.021
ime+0.020
Neg logit contributions
 first-0.015
 next-0.014
balls-0.012
ider-0.010
 last-0.010
Token all
Token ID477
Feature activation+1.53e+00

Pos logit contributions
aw+0.020
 regretted+0.019
 gol+0.019
opter+0.017
arre+0.016
Neg logit contributions
 first-0.012
 next-0.010
balls-0.008
 one-0.008
 front-0.008
Token shapes
Token ID15268
Feature activation+1.82e+00

Pos logit contributions
aw+0.080
 regretted+0.075
 gol+0.071
opter+0.066
arre+0.060
Neg logit contributions
 first-0.060
 next-0.055
balls-0.047
ider-0.042
 last-0.042
Token and
Token ID290
Feature activation+1.16e-01

Pos logit contributions
aw+0.103
 regretted+0.098
 gol+0.094
opter+0.087
ime+0.082
Neg logit contributions
 first-0.064
 next-0.059
balls-0.053
ider-0.046
 last-0.041
Token sizes
Token ID10620
Feature activation+4.05e+00

Pos logit contributions
aw+0.006
 regretted+0.005
 gol+0.005
opter+0.005
ime+0.004
Neg logit contributions
 first-0.005
 next-0.005
balls-0.004
ider-0.004
 one-0.004
Token.
Token ID13
Feature activation+6.59e-01

Pos logit contributions
aw+0.258
 regretted+0.252
 gol+0.240
opter+0.221
arre+0.211
Neg logit contributions
 first-0.115
 next-0.101
balls-0.089
ider-0.070
 last-0.067
Token He
Token ID679
Feature activation+1.75e-01

Pos logit contributions
aw+0.032
 regretted+0.029
 gol+0.027
opter+0.026
ime+0.025
Neg logit contributions
 first-0.027
 next-0.025
ider-0.024
balls-0.023
 seek-0.019
Token noticed
Token ID6810
Feature activation+4.14e-01

Pos logit contributions
aw+0.009
 gol+0.008
 regretted+0.008
opter+0.007
ime+0.007
Neg logit contributions
 first-0.007
 next-0.007
balls-0.006
ider-0.005
 one-0.005
Token many
Token ID867
Feature activation-2.36e-01

Pos logit contributions
aw+0.025
 regretted+0.024
 gol+0.024
opter+0.023
arre+0.022
Neg logit contributions
 first-0.013
 next-0.011
balls-0.009
 one-0.009
 some-0.008
Token were
Token ID547
Feature activation-8.71e-01

Pos logit contributions
 first+0.010
 next+0.009
 one+0.007
 particular+0.007
balls+0.007
Neg logit contributions
aw-0.011
 gol-0.011
 regretted-0.011
opter-0.010
severe-0.009
Token stickers
Token ID28568
Feature activation+1.24e+00

Pos logit contributions
 first+0.021
 next+0.019
balls+0.016
ider+0.014
 one+0.013
Neg logit contributions
aw-0.040
 regretted-0.037
 gol-0.036
opter-0.034
ime-0.032
Token,
Token ID11
Feature activation+3.83e-01

Pos logit contributions
aw+0.071
 regretted+0.068
 gol+0.065
opter+0.061
ime+0.057
Neg logit contributions
 first-0.044
 next-0.039
balls-0.034
ider-0.030
 last-0.028
Token colors
Token ID7577
Feature activation+2.96e+00

Pos logit contributions
aw+0.017
 regretted+0.016
 gol+0.015
opter+0.014
ime+0.013
Neg logit contributions
 first-0.017
 next-0.016
balls-0.015
ider-0.014
 front-0.012
Token,
Token ID11
Feature activation+1.04e+00

Pos logit contributions
aw+0.158
 regretted+0.149
 gol+0.141
opter+0.131
ime+0.124
Neg logit contributions
 first-0.112
 next-0.102
balls-0.093
ider-0.086
 last-0.076
Token and
Token ID290
Feature activation+7.13e-01

Pos logit contributions
aw+0.051
 regretted+0.046
 gol+0.044
opter+0.041
ime+0.039
Neg logit contributions
 first-0.043
 next-0.040
balls-0.037
ider-0.035
 front-0.030
Token drawings
Token ID23388
Feature activation+3.93e+00

Pos logit contributions
aw+0.036
 regretted+0.032
 gol+0.031
opter+0.030
ime+0.028
Neg logit contributions
 first-0.030
 next-0.028
balls-0.025
ider-0.023
 one-0.022
Token to
Token ID284
Feature activation+1.22e+00

Pos logit contributions
aw+0.237
 regretted+0.225
 gol+0.216
opter+0.203
ime+0.194
Neg logit contributions
 first-0.126
 next-0.114
balls-0.100
ider-0.092
 last-0.078
Token decor
Token ID11705
Feature activation-1.55e-01

Pos logit contributions
aw+0.068
 regretted+0.063
 gol+0.060
opter+0.056
ime+0.054
Neg logit contributions
 first-0.042
 next-0.037
balls-0.035
ider-0.034
 front-0.027
Tokenate
Token ID378
Feature activation+1.22e-01

Pos logit contributions
 first+0.008
 next+0.008
balls+0.007
ider+0.007
 front+0.006
Neg logit contributions
aw-0.006
 regretted-0.005
 gol-0.005
opter-0.004
ime-0.004
Token her
Token ID607
Feature activation+8.03e-01

Pos logit contributions
aw+0.007
 regretted+0.006
 gol+0.006
opter+0.005
ime+0.005
Neg logit contributions
 first-0.004
 next-0.004
balls-0.004
ider-0.004
 front-0.003
Token journal
Token ID3989
Feature activation+1.55e+00

Pos logit contributions
aw+0.038
 regretted+0.034
 gol+0.033
opter+0.031
ime+0.029
Neg logit contributions
 first-0.036
 next-0.034
balls-0.030
ider-0.029
 front-0.026
Token measure
Token ID3953
Feature activation-1.93e+00

Pos logit contributions
 first+0.031
 next+0.029
balls+0.026
ider+0.024
 last+0.021
Neg logit contributions
aw-0.042
 regretted-0.039
 gol-0.037
opter-0.035
ime-0.033
Token and
Token ID290
Feature activation-1.84e-01

Pos logit contributions
 first+0.067
 next+0.061
balls+0.056
ider+0.053
 front+0.043
Neg logit contributions
aw-0.107
 regretted-0.099
 gol-0.095
opter-0.089
ime-0.085
Token she
Token ID673
Feature activation+1.37e+00

Pos logit contributions
 first+0.007
 next+0.006
balls+0.006
ider+0.005
 one+0.005
Neg logit contributions
aw-0.010
 regretted-0.009
 gol-0.009
opter-0.008
ime-0.008
Token asked
Token ID1965
Feature activation+6.26e-01

Pos logit contributions
aw+0.068
 gol+0.060
 regretted+0.060
opter+0.055
ime+0.052
Neg logit contributions
 first-0.057
 next-0.053
balls-0.048
ider-0.045
 one-0.040
Token her
Token ID607
Feature activation+2.62e-01

Pos logit contributions
aw+0.040
 regretted+0.038
 gol+0.038
opter+0.036
ime+0.034
Neg logit contributions
 first-0.019
 next-0.016
balls-0.013
 one-0.011
 Mia-0.011
Token parents
Token ID3397
Feature activation+9.02e-01

Pos logit contributions
aw+0.017
 regretted+0.016
 gol+0.015
opter+0.015
hing+0.014
Neg logit contributions
 first-0.008
 next-0.007
balls-0.006
ider-0.005
 Mia-0.005
Token to
Token ID284
Feature activation+8.14e-01

Pos logit contributions
aw+0.045
 regretted+0.041
 gol+0.039
opter+0.036
ime+0.034
Neg logit contributions
 first-0.036
 next-0.033
balls-0.031
ider-0.030
 front-0.026
Token help
Token ID1037
Feature activation-1.23e-01

Pos logit contributions
aw+0.051
 regretted+0.047
 gol+0.044
opter+0.042
act+0.040
Neg logit contributions
 first-0.026
 next-0.023
balls-0.018
ider-0.017
 front-0.016
Token.
Token ID13
Feature activation-1.46e-01

Pos logit contributions
 first+0.005
ider+0.004
 next+0.004
balls+0.004
 seek+0.003
Neg logit contributions
aw-0.006
 regretted-0.005
 gol-0.005
ime-0.005
opter-0.005
Token Her
Token ID2332
Feature activation-5.79e-01

Pos logit contributions
 first+0.006
 next+0.005
balls+0.005
ider+0.005
 seek+0.004
Neg logit contributions
aw-0.007
 regretted-0.006
 gol-0.006
opter-0.006
ime-0.005
Token parents
Token ID3397
Feature activation+2.05e+00

Pos logit contributions
 first+0.022
 next+0.020
balls+0.017
 front+0.013
ider+0.013
Neg logit contributions
aw-0.035
 gol-0.030
 regretted-0.030
opter-0.029
hing-0.028
Token and
Token ID290
Feature activation+3.58e-01

Pos logit contributions
 first+0.019
 next+0.018
balls+0.016
ider+0.015
 last+0.013
Neg logit contributions
aw-0.023
 regretted-0.021
 gol-0.020
opter-0.019
ime-0.018
Token sphere
Token ID16558
Feature activation+3.31e-01

Pos logit contributions
aw+0.021
 regretted+0.019
 gol+0.018
opter+0.017
ime+0.017
Neg logit contributions
 first-0.012
 next-0.011
balls-0.009
ider-0.008
 one-0.008
Token spun
Token ID26843
Feature activation-1.38e+00

Pos logit contributions
aw+0.015
 regretted+0.014
 gol+0.013
opter+0.012
ime+0.012
Neg logit contributions
 first-0.015
 next-0.013
balls-0.012
ider-0.011
 last-0.011
Token around
Token ID1088
Feature activation+1.02e-01

Pos logit contributions
 first+0.051
 next+0.046
balls+0.042
ider+0.039
 last+0.033
Neg logit contributions
aw-0.075
 regretted-0.070
 gol-0.066
opter-0.062
ime-0.060
Token and
Token ID290
Feature activation-2.73e-01

Pos logit contributions
aw+0.005
 gol+0.004
 regretted+0.004
opter+0.004
ime+0.004
Neg logit contributions
 first-0.004
ider-0.004
balls-0.004
 next-0.004
 hips-0.003
Token around
Token ID1088
Feature activation+1.75e+00

Pos logit contributions
 first+0.012
 next+0.011
balls+0.010
ider+0.009
 last+0.008
Neg logit contributions
aw-0.013
 regretted-0.012
 gol-0.011
opter-0.011
ime-0.010
Token as
Token ID355
Feature activation+1.29e+00

Pos logit contributions
aw+0.094
 regretted+0.086
 gol+0.083
opter+0.077
ime+0.074
Neg logit contributions
 first-0.062
 next-0.056
balls-0.054
ider-0.053
 front-0.042
Token fast
Token ID3049
Feature activation+1.81e+00

Pos logit contributions
aw+0.077
 regretted+0.072
 gol+0.069
opter+0.065
ime+0.062
Neg logit contributions
 first-0.039
 next-0.035
balls-0.032
ider-0.030
 last-0.023
Token as
Token ID355
Feature activation+8.98e-01

Pos logit contributions
aw+0.114
 regretted+0.108
 gol+0.102
opter+0.099
ime+0.096
Neg logit contributions
 first-0.047
 next-0.042
balls-0.037
ider-0.033
 one-0.028
Token they
Token ID484
Feature activation+3.51e-01

Pos logit contributions
aw+0.055
 regretted+0.051
 gol+0.049
opter+0.046
ime+0.045
Neg logit contributions
 first-0.026
 next-0.023
balls-0.021
ider-0.020
 last-0.015
Token could
Token ID714
Feature activation+2.24e+00

Pos logit contributions
aw+0.016
 regretted+0.014
 gol+0.014
opter+0.013
 mustache+0.013
Neg logit contributions
 first-0.016
 next-0.015
balls-0.013
ider-0.012
 last-0.012
Token you
Token ID345
Feature activation-5.83e-01

Pos logit contributions
aw+0.019
 gol+0.013
ime+0.012
opter+0.012
 regretted+0.011
Neg logit contributions
 first-0.021
balls-0.021
ider-0.020
 hips-0.020
sing-0.019
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
 first+0.025
balls+0.025
ider+0.025
 next+0.024
 particular+0.022
Neg logit contributions
aw-0.025
 regretted-0.020
 gol-0.019
opter-0.018
ime-0.017
Token thank
Token ID5875
Feature activation+5.29e-01

Pos logit contributions
 first+0.008
 next+0.008
balls+0.006
ider+0.006
 Mia+0.006
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.009
opter-0.009
ime-0.009
Token you
Token ID345
Feature activation+2.02e-01

Pos logit contributions
aw+0.026
 gol+0.022
 regretted+0.022
opter+0.020
ime+0.019
Neg logit contributions
 first-0.021
balls-0.020
ider-0.020
 next-0.019
 hips-0.016
Token,"
Token ID553
Feature activation-9.71e-01

Pos logit contributions
aw+0.009
 regretted+0.008
 gol+0.008
opter+0.007
ime+0.007
Neg logit contributions
 first-0.008
 next-0.008
balls-0.008
ider-0.007
 particular-0.006
Token L
Token ID406
Feature activation+1.28e+00

Pos logit contributions
 first+0.033
 next+0.030
balls+0.027
ider+0.026
 front+0.021
Neg logit contributions
aw-0.055
 regretted-0.051
 gol-0.049
opter-0.046
ime-0.044
Tokenila
Token ID10102
Feature activation+6.84e-01

Pos logit contributions
aw+0.066
 regretted+0.064
 gol+0.059
opter+0.056
 perspective+0.053
Neg logit contributions
 first-0.048
 next-0.043
balls-0.038
ider-0.037
 Mia-0.032
Token and
Token ID290
Feature activation+1.33e+00

Pos logit contributions
aw+0.035
 regretted+0.033
 gol+0.031
opter+0.030
ime+0.029
Neg logit contributions
 first-0.027
 next-0.025
balls-0.022
ider-0.020
 front-0.018
Token Tom
Token ID4186
Feature activation+9.24e-01

Pos logit contributions
aw+0.060
 regretted+0.053
 gol+0.051
opter+0.046
ime+0.043
Neg logit contributions
 first-0.061
 next-0.056
balls-0.053
ider-0.052
 particular-0.045
Token say
Token ID910
Feature activation+1.55e+00

Pos logit contributions
aw+0.058
 regretted+0.055
 gol+0.052
opter+0.051
ime+0.049
Neg logit contributions
 first-0.028
 next-0.024
balls-0.019
 last-0.017
ider-0.016
Token.
Token ID13
Feature activation-5.54e-01

Pos logit contributions
aw+0.082
 regretted+0.072
 gol+0.070
opter+0.065
ime+0.062
Neg logit contributions
 first-0.056
 next-0.049
balls-0.047
ider-0.046
 particular-0.042
Token there
Token ID612
Feature activation+1.13e+00

Pos logit contributions
aw+0.000
 regretted+0.000
 gol+0.000
opter+0.000
ime+0.000
Neg logit contributions
 first-0.000
 next-0.000
balls-0.000
ider-0.000
 last-0.000
Token was
Token ID373
Feature activation+1.89e+00

Pos logit contributions
aw+0.066
 regretted+0.060
 gol+0.059
opter+0.055
ime+0.052
Neg logit contributions
 first-0.039
 next-0.034
balls-0.029
ider-0.026
 particular-0.024
Token a
Token ID257
Feature activation-6.38e-01

Pos logit contributions
aw+0.114
 regretted+0.105
 gol+0.101
opter+0.095
ime+0.092
Neg logit contributions
 first-0.056
 next-0.050
balls-0.046
ider-0.044
 front-0.034
Token small
Token ID1402
Feature activation+9.12e-02

Pos logit contributions
 first+0.031
 next+0.029
balls+0.027
ider+0.026
 last+0.023
Neg logit contributions
aw-0.026
 regretted-0.024
 gol-0.022
opter-0.020
ime-0.019
Token boy
Token ID2933
Feature activation-9.17e-01

Pos logit contributions
aw+0.004
 regretted+0.004
 gol+0.004
opter+0.003
ime+0.003
Neg logit contributions
 first-0.004
 next-0.004
balls-0.003
ider-0.003
 one-0.003
Token called
Token ID1444
Feature activation+9.78e-01

Pos logit contributions
 first+0.041
balls+0.039
ider+0.037
 next+0.037
 hips+0.032
Neg logit contributions
aw-0.042
 regretted-0.036
 gol-0.034
ime-0.031
opter-0.029
Token Tony
Token ID8832
Feature activation-1.17e+00

Pos logit contributions
aw+0.044
 regretted+0.039
 gol+0.039
opter+0.035
ime+0.034
Neg logit contributions
 first-0.043
 next-0.040
ider-0.037
balls-0.037
 front-0.031
Token.
Token ID13
Feature activation+8.92e-01

Pos logit contributions
 first+0.030
 next+0.027
balls+0.020
ider+0.018
 one+0.017
Neg logit contributions
aw-0.075
 regretted-0.072
 gol-0.071
opter-0.067
arre-0.063
Token He
Token ID679
Feature activation+4.35e-02

Pos logit contributions
aw+0.038
 regretted+0.033
 gol+0.032
opter+0.029
ime+0.028
Neg logit contributions
 first-0.042
 next-0.039
balls-0.037
ider-0.037
 last-0.031
Token was
Token ID373
Feature activation+1.20e-01

Pos logit contributions
aw+0.002
 regretted+0.002
 gol+0.002
opter+0.001
ime+0.001
Neg logit contributions
 first-0.002
 next-0.002
balls-0.002
ider-0.002
 particular-0.002
Token only
Token ID691
Feature activation-2.03e+00

Pos logit contributions
aw+0.006
 regretted+0.006
 gol+0.006
opter+0.005
ime+0.005
Neg logit contributions
 first-0.004
 next-0.004
balls-0.004
ider-0.004
 hips-0.003
Token ran
Token ID4966
Feature activation-2.10e-01

Pos logit contributions
 first+0.030
 next+0.027
balls+0.026
ider+0.022
 last+0.021
Neg logit contributions
aw-0.036
 regretted-0.032
 gol-0.032
opter-0.030
ime-0.030
Token,
Token ID11
Feature activation-3.37e-01

Pos logit contributions
 first+0.008
 next+0.008
balls+0.007
ider+0.007
 front+0.006
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.009
opter-0.009
ime-0.008
Token and
Token ID290
Feature activation-2.65e-01

Pos logit contributions
 first+0.014
ider+0.014
 next+0.013
 particular+0.013
balls+0.012
Neg logit contributions
aw-0.014
 regretted-0.012
 gol-0.012
 mustache-0.010
opter-0.010
Token they
Token ID484
Feature activation+2.09e-01

Pos logit contributions
 first+0.010
 next+0.010
ider+0.009
balls+0.009
 front+0.007
Neg logit contributions
aw-0.013
 regretted-0.012
 gol-0.012
opter-0.011
ime-0.010
Token had
Token ID550
Feature activation+5.50e-01

Pos logit contributions
aw+0.011
 regretted+0.009
 gol+0.009
opter+0.009
ime+0.009
Neg logit contributions
 first-0.009
 next-0.008
balls-0.007
ider-0.006
 last-0.006
Token fun
Token ID1257
Feature activation+8.14e-01

Pos logit contributions
aw+0.030
 regretted+0.028
 gol+0.028
opter+0.027
ime+0.025
Neg logit contributions
 first-0.020
 next-0.017
balls-0.016
ider-0.014
 one-0.013
Token.
Token ID13
Feature activation-6.35e-01

Pos logit contributions
aw+0.040
 gol+0.034
 regretted+0.034
opter+0.031
 perspective+0.030
Neg logit contributions
 first-0.032
 next-0.028
ider-0.028
balls-0.027
 particular-0.025
Token Blue
Token ID4518
Feature activation-2.43e-01

Pos logit contributions
 first+0.026
 next+0.023
ider+0.022
balls+0.022
 seek+0.019
Neg logit contributions
aw-0.031
 regretted-0.028
 gol-0.026
opter-0.024
ime-0.022
Token's
Token ID338
Feature activation+3.76e-01

Pos logit contributions
 first+0.009
 next+0.008
balls+0.007
ider+0.007
 last+0.006
Neg logit contributions
aw-0.013
 gol-0.012
 regretted-0.012
opter-0.011
ime-0.010
Token old
Token ID1468
Feature activation+7.88e-01

Pos logit contributions
aw+0.020
 regretted+0.018
 gol+0.017
opter+0.016
ime+0.015
Neg logit contributions
 first-0.014
 next-0.013
balls-0.012
ider-0.012
 front-0.010
Token friends
Token ID2460
Feature activation+2.16e+00

Pos logit contributions
aw+0.037
 regretted+0.033
 gol+0.032
opter+0.030
ime+0.028
Neg logit contributions
 first-0.036
 next-0.033
balls-0.030
ider-0.029
 last-0.026
Token them
Token ID606
Feature activation-4.09e-01

Pos logit contributions
ider+0.009
 first+0.009
balls+0.009
 next+0.008
 hips+0.007
Neg logit contributions
aw-0.009
 regretted-0.007
 gol-0.007
ime-0.006
onder-0.006
Token and
Token ID290
Feature activation-4.26e-01

Pos logit contributions
 first+0.014
 next+0.013
balls+0.011
ider+0.011
 last+0.009
Neg logit contributions
aw-0.023
 regretted-0.021
 gol-0.021
opter-0.019
ime-0.019
Token asked
Token ID1965
Feature activation+3.85e-01

Pos logit contributions
 first+0.016
 next+0.014
balls+0.013
ider+0.011
 Mia+0.011
Neg logit contributions
aw-0.023
 regretted-0.020
 gol-0.020
opter-0.020
ime-0.019
Token,
Token ID11
Feature activation-3.54e-01

Pos logit contributions
aw+0.019
 regretted+0.017
 gol+0.016
opter+0.015
ime+0.015
Neg logit contributions
 first-0.016
 next-0.015
balls-0.014
ider-0.013
 last-0.011
Token "
Token ID366
Feature activation-1.57e-02

Pos logit contributions
 first+0.015
 next+0.013
balls+0.013
ider+0.013
 hips+0.011
Neg logit contributions
aw-0.016
 regretted-0.015
 gol-0.014
opter-0.013
ime-0.012
TokenTom
Token ID13787
Feature activation-1.93e+00

Pos logit contributions
 first+0.001
ider+0.001
balls+0.001
 next+0.001
 hips+0.001
Neg logit contributions
aw-0.001
 regretted-0.001
 gol-0.001
opter-0.001
 musician-0.000
Token,
Token ID11
Feature activation+4.11e-01

Pos logit contributions
 first+0.075
 next+0.068
balls+0.059
ider+0.056
 last+0.050
Neg logit contributions
aw-0.103
 regretted-0.094
 gol-0.090
opter-0.085
ime-0.079
Token are
Token ID389
Feature activation+4.50e-01

Pos logit contributions
aw+0.019
 regretted+0.017
 gol+0.016
opter+0.016
ime+0.015
Neg logit contributions
 first-0.019
 next-0.018
balls-0.016
ider-0.015
 last-0.014
Token you
Token ID345
Feature activation+1.64e-01

Pos logit contributions
aw+0.022
 regretted+0.019
 gol+0.019
opter+0.017
ime+0.016
Neg logit contributions
 first-0.018
ider-0.016
 next-0.016
balls-0.016
 front-0.014
Token sure
Token ID1654
Feature activation-4.09e-01

Pos logit contributions
aw+0.007
 regretted+0.007
 gol+0.006
opter+0.006
ime+0.005
Neg logit contributions
 first-0.007
 next-0.007
balls-0.007
ider-0.006
 particular-0.006
Token you
Token ID345
Feature activation+9.70e-01

Pos logit contributions
 first+0.014
 next+0.013
balls+0.011
ider+0.010
 last+0.009
Neg logit contributions
aw-0.024
 gol-0.022
 regretted-0.022
opter-0.020
arre-0.019
Token.
Token ID13
Feature activation-4.94e-02

Pos logit contributions
aw+0.052
 regretted+0.045
 gol+0.042
ime+0.039
 mustache+0.037
Neg logit contributions
 first-0.046
 particular-0.041
balls-0.040
ider-0.039
 seek-0.039
Token
Token ID198
Feature activation-8.35e-02

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.002
 last+0.001
Neg logit contributions
aw-0.002
 regretted-0.002
 gol-0.002
opter-0.002
ime-0.002
Token
Token ID198
Feature activation-4.05e-01

Pos logit contributions
 first+0.003
 next+0.002
balls+0.002
ider+0.002
 Mia+0.002
Neg logit contributions
aw-0.005
 regretted-0.005
 gol-0.004
opter-0.004
ime-0.004
Token"
Token ID1
Feature activation-1.89e+00

Pos logit contributions
 first+0.017
 next+0.015
balls+0.015
ider+0.014
 last+0.012
Neg logit contributions
aw-0.020
 regretted-0.018
 gol-0.017
opter-0.016
ime-0.015
TokenOkay
Token ID16454
Feature activation+2.99e-01

Pos logit contributions
 first+0.081
balls+0.072
 next+0.070
ider+0.067
 hips+0.067
Neg logit contributions
aw-0.085
 gol-0.078
 regretted-0.075
opter-0.062
 musician-0.060
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
aw+0.010
 regretted+0.008
 gol+0.007
opter+0.007
ime+0.006
Neg logit contributions
balls-0.014
ider-0.014
 first-0.014
 next-0.013
 particular-0.012
Token I
Token ID314
Feature activation+8.92e-01

Pos logit contributions
 first+0.068
 next+0.060
balls+0.058
ider+0.054
 front+0.052
Neg logit contributions
aw-0.069
 gol-0.058
 regretted-0.057
opter-0.052
onder-0.047
Token will
Token ID481
Feature activation-4.46e-01

Pos logit contributions
aw+0.044
 regretted+0.039
 gol+0.037
opter+0.036
ime+0.035
Neg logit contributions
 first-0.038
 next-0.035
balls-0.031
ider-0.030
 last-0.028
Token be
Token ID307
Feature activation-1.37e+00

Pos logit contributions
 first+0.014
 next+0.012
balls+0.011
ider+0.010
 last+0.008
Neg logit contributions
aw-0.027
 regretted-0.025
 gol-0.024
opter-0.023
ime-0.022
Token more
Token ID517
Feature activation-1.28e+00

Pos logit contributions
 first+0.056
 next+0.052
balls+0.047
ider+0.045
 front+0.039
Neg logit contributions
aw-0.068
 regretted-0.063
 gol-0.060
opter-0.058
ime-0.054
Token careful
Token ID8161
Feature activation-9.19e-01

Pos logit contributions
 first+0.042
 next+0.042
ider+0.031
balls+0.029
 seek+0.027
Neg logit contributions
aw-0.074
opter-0.069
 regretted-0.067
 gol-0.065
ane-0.065
Token,
Token ID11
Feature activation+4.68e-01

Pos logit contributions
 first+0.027
 next+0.025
balls+0.024
ider+0.023
 front+0.020
Neg logit contributions
aw-0.031
 regretted-0.029
 gol-0.027
opter-0.025
ime-0.024
Token the
Token ID262
Feature activation+8.81e-01

Pos logit contributions
aw+0.026
 regretted+0.023
 gol+0.023
opter+0.021
ime+0.020
Neg logit contributions
 first-0.017
 next-0.016
balls-0.014
ider-0.013
 one-0.012
Token earth
Token ID4534
Feature activation+1.35e+00

Pos logit contributions
aw+0.042
 regretted+0.035
 gol+0.034
opter+0.031
aden+0.031
Neg logit contributions
 first-0.043
 next-0.041
balls-0.035
ider-0.033
 front-0.032
Token slowly
Token ID6364
Feature activation-1.06e+00

Pos logit contributions
aw+0.066
 gol+0.059
 regretted+0.056
opter+0.055
aden+0.054
Neg logit contributions
 first-0.056
 next-0.055
balls-0.047
ider-0.044
 one-0.040
Token got
Token ID1392
Feature activation-4.07e-01

Pos logit contributions
 first+0.041
 next+0.041
balls+0.032
 last+0.032
 one+0.031
Neg logit contributions
aw-0.050
 gol-0.050
opter-0.046
aden-0.045
 regretted-0.045
Token brighter
Token ID26083
Feature activation-1.46e+00

Pos logit contributions
 first+0.013
 next+0.012
balls+0.009
ider+0.008
 last+0.008
Neg logit contributions
aw-0.025
 gol-0.023
 regretted-0.022
opter-0.022
ime-0.020
Token and
Token ID290
Feature activation-2.00e+00

Pos logit contributions
 first+0.053
 next+0.050
balls+0.042
ider+0.041
 front+0.035
Neg logit contributions
aw-0.079
 regretted-0.073
 gol-0.071
opter-0.067
ime-0.063
Token brighter
Token ID26083
Feature activation+3.41e-01

Pos logit contributions
 first+0.078
 next+0.070
balls+0.070
ider+0.068
 hips+0.056
Neg logit contributions
aw-0.100
 regretted-0.092
 gol-0.085
opter-0.079
ime-0.076
Token.
Token ID13
Feature activation-8.49e-02

Pos logit contributions
aw+0.020
 regretted+0.019
 gol+0.018
opter+0.017
ime+0.016
Neg logit contributions
 first-0.011
 next-0.010
balls-0.008
ider-0.008
 front-0.007
Token Everyone
Token ID11075
Feature activation+1.53e+00

Pos logit contributions
 first+0.003
 next+0.003
balls+0.002
ider+0.002
 one+0.002
Neg logit contributions
aw-0.005
 regretted-0.005
 gol-0.004
opter-0.004
aden-0.004
Token smiled
Token ID13541
Feature activation-9.23e-01

Pos logit contributions
aw+0.084
 gol+0.081
 regretted+0.076
opter+0.074
aden+0.073
Neg logit contributions
 first-0.050
 next-0.049
balls-0.035
 one-0.032
 last-0.031
Token farmer
Token ID18739
Feature activation+4.24e-01

Pos logit contributions
 first+0.048
 next+0.045
balls+0.042
ider+0.040
 front+0.036
Neg logit contributions
aw-0.043
 regretted-0.038
 gol-0.036
opter-0.034
ime-0.032
Token's
Token ID338
Feature activation+7.55e-02

Pos logit contributions
aw+0.021
 regretted+0.019
 gol+0.019
opter+0.017
ime+0.016
Neg logit contributions
 first-0.017
 next-0.016
balls-0.014
ider-0.014
 last-0.012
Token dog
Token ID3290
Feature activation-1.98e-01

Pos logit contributions
aw+0.004
 gol+0.003
 regretted+0.003
opter+0.003
hing+0.003
Neg logit contributions
 first-0.003
 next-0.003
balls-0.003
ider-0.002
 front-0.002
Token then
Token ID788
Feature activation-1.16e+00

Pos logit contributions
 first+0.007
 next+0.007
balls+0.006
ider+0.006
 front+0.005
Neg logit contributions
aw-0.010
 regretted-0.010
 gol-0.009
opter-0.009
ime-0.008
Token jumped
Token ID11687
Feature activation-8.81e-01

Pos logit contributions
 first+0.046
 next+0.043
balls+0.038
ider+0.034
 one+0.033
Neg logit contributions
aw-0.058
 gol-0.053
opter-0.051
 regretted-0.051
ime-0.047
Token into
Token ID656
Feature activation-6.82e-01

Pos logit contributions
 first+0.033
 next+0.030
balls+0.029
ider+0.028
 last+0.023
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.040
opter-0.037
ime-0.035
Token the
Token ID262
Feature activation+6.09e-01

Pos logit contributions
 first+0.027
ider+0.026
balls+0.025
 next+0.025
 hips+0.020
Neg logit contributions
aw-0.032
 regretted-0.029
 gol-0.029
ime-0.026
opter-0.025
Token hole
Token ID7604
Feature activation+6.84e-01

Pos logit contributions
aw+0.028
 gol+0.025
 regretted+0.025
opter+0.023
ime+0.022
Neg logit contributions
 first-0.027
 next-0.026
balls-0.024
ider-0.023
 front-0.021
Token and
Token ID290
Feature activation+3.24e-01

Pos logit contributions
aw+0.033
 regretted+0.030
 gol+0.028
opter+0.026
ime+0.025
Neg logit contributions
 first-0.027
 next-0.025
balls-0.024
ider-0.023
 particular-0.020
Token picked
Token ID6497
Feature activation+7.96e-01

Pos logit contributions
aw+0.016
 regretted+0.014
 gol+0.013
opter+0.012
ime+0.012
Neg logit contributions
 first-0.014
 next-0.012
balls-0.012
ider-0.011
 front-0.010
Token up
Token ID510
Feature activation-3.63e-01

Pos logit contributions
aw+0.042
 regretted+0.038
 gol+0.036
opter+0.034
ime+0.032
Neg logit contributions
 first-0.030
 next-0.027
ider-0.025
balls-0.025
 hips-0.020
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
 first+0.097
balls+0.088
ider+0.085
 next+0.085
 hips+0.070
Neg logit contributions
aw-0.113
 regretted-0.095
 gol-0.089
opter-0.085
ime-0.084
Token<|endoftext|>
Token ID50256
Feature activation-5.86e-02

Pos logit contributions
 first+0.043
 next+0.039
balls+0.037
ider+0.036
 last+0.029
Neg logit contributions
aw-0.057
 regretted-0.052
 gol-0.050
opter-0.046
ime-0.044
TokenOnce
Token ID7454
Feature activation-7.74e-01

Pos logit contributions
 first+0.002
 next+0.002
balls+0.002
ider+0.001
 front+0.001
Neg logit contributions
aw-0.003
 regretted-0.003
 gol-0.003
opter-0.003
 mustache-0.003
Token upon
Token ID2402
Feature activation+1.16e+00

Pos logit contributions
 first+0.030
 next+0.026
balls+0.022
 last+0.020
 particular+0.020
Neg logit contributions
aw-0.043
 regretted-0.039
 gol-0.038
opter-0.034
 mustache-0.032
Token a
Token ID257
Feature activation+3.00e-01

Pos logit contributions
aw+0.064
 regretted+0.057
 gol+0.053
opter+0.050
ime+0.050
Neg logit contributions
 first-0.040
balls-0.036
ider-0.035
 next-0.035
 hips-0.028
Token time
Token ID640
Feature activation+5.95e-02

Pos logit contributions
aw+0.008
 regretted+0.006
 gol+0.005
ime+0.005
arre+0.004
Neg logit contributions
balls-0.018
 first-0.018
ider-0.017
 next-0.017
 hips-0.015
Token,
Token ID11
Feature activation+6.05e-01

Pos logit contributions
aw+0.003
 regretted+0.002
 gol+0.002
opter+0.002
ime+0.002
Neg logit contributions
 first-0.003
 next-0.002
balls-0.002
ider-0.002
 front-0.002
Token there
Token ID612
Feature activation+6.05e-02

Pos logit contributions
aw+0.025
 regretted+0.022
 gol+0.020
opter+0.019
ime+0.018
Neg logit contributions
 first-0.028
 next-0.026
balls-0.026
ider-0.025
 hips-0.022
Token was
Token ID373
Feature activation+5.07e-01

Pos logit contributions
aw+0.004
 regretted+0.003
 gol+0.003
opter+0.003
 mustache+0.003
Neg logit contributions
 first-0.002
 next-0.002
balls-0.001
 particular-0.001
 Mia-0.001
Token a
Token ID257
Feature activation-8.75e-01

Pos logit contributions
aw+0.028
 gol+0.024
 regretted+0.023
ime+0.021
opter+0.021
Neg logit contributions
 first-0.018
ider-0.017
balls-0.017
 next-0.016
 hips-0.014
Token fine
Token ID3734
Feature activation-4.49e-01

Pos logit contributions
 first+0.041
 next+0.039
balls+0.035
ider+0.034
 particular+0.030
Neg logit contributions
aw-0.039
 regretted-0.034
 gol-0.032
opter-0.030
ime-0.029
Token and
Token ID290
Feature activation-9.59e-01

Pos logit contributions
aw+0.057
 regretted+0.051
 gol+0.049
opter+0.045
ime+0.043
Neg logit contributions
 first-0.047
 next-0.043
balls-0.040
ider-0.040
 particular-0.033
Token looked
Token ID3114
Feature activation-5.08e-01

Pos logit contributions
 first+0.048
 next+0.045
balls+0.044
ider+0.043
 front+0.037
Neg logit contributions
aw-0.038
 regretted-0.033
 gol-0.031
opter-0.028
ime-0.026
Token for
Token ID329
Feature activation+2.83e-01

Pos logit contributions
 first+0.018
 next+0.016
balls+0.014
ider+0.012
 one+0.011
Neg logit contributions
aw-0.029
 regretted-0.027
 gol-0.026
opter-0.026
ime-0.025
Token shells
Token ID19679
Feature activation+3.29e+00

Pos logit contributions
aw+0.013
 regretted+0.012
 gol+0.012
opter+0.011
arre+0.010
Neg logit contributions
 first-0.013
 next-0.012
balls-0.010
 one-0.009
 front-0.009
Token.
Token ID13
Feature activation+3.25e-01

Pos logit contributions
aw+0.192
 regretted+0.181
 gol+0.173
opter+0.164
ime+0.157
Neg logit contributions
 first-0.107
 next-0.095
balls-0.087
ider-0.080
 last-0.066
Token One
Token ID1881
Feature activation-2.85e+00

Pos logit contributions
aw+0.016
 regretted+0.013
 gol+0.012
ime+0.011
arre+0.011
Neg logit contributions
 first-0.013
ider-0.012
 next-0.012
balls-0.012
 seek-0.010
Token day
Token ID1110
Feature activation-7.14e-01

Pos logit contributions
 first+0.109
balls+0.102
ider+0.100
 next+0.099
 hips+0.084
Neg logit contributions
aw-0.144
 regretted-0.129
 gol-0.122
opter-0.113
ime-0.112
Token,
Token ID11
Feature activation-1.20e-01

Pos logit contributions
 first+0.030
 next+0.028
balls+0.026
ider+0.026
 front+0.022
Neg logit contributions
aw-0.034
 regretted-0.031
 gol-0.029
opter-0.027
ime-0.026
Token they
Token ID484
Feature activation-8.54e-01

Pos logit contributions
ider+0.004
 first+0.004
 next+0.004
balls+0.003
 hips+0.003
Neg logit contributions
aw-0.007
 regretted-0.006
 gol-0.005
opter-0.005
ime-0.005
Token saw
Token ID2497
Feature activation+2.12e-02

Pos logit contributions
 first+0.034
 next+0.031
 one+0.024
 soon+0.022
balls+0.022
Neg logit contributions
aw-0.046
opter-0.041
 gol-0.040
 regretted-0.039
severe-0.038
Token a
Token ID257
Feature activation-8.09e-01

Pos logit contributions
aw+0.001
 regretted+0.001
 gol+0.001
opter+0.001
ime+0.001
Neg logit contributions
 first-0.001
 next-0.000
balls-0.000
 one-0.000
 last-0.000
Token two
Token ID734
Feature activation-1.62e+00

Pos logit contributions
 first+0.035
 next+0.032
balls+0.029
ider+0.027
 front+0.024
Neg logit contributions
aw-0.046
 regretted-0.042
 gol-0.042
opter-0.039
ime-0.037
Token tiny
Token ID7009
Feature activation+4.09e-01

Pos logit contributions
 first+0.070
 next+0.065
balls+0.060
ider+0.057
 last+0.050
Neg logit contributions
aw-0.075
 gol-0.069
 regretted-0.068
opter-0.062
ime-0.057
Token fair
Token ID3148
Feature activation-9.41e-02

Pos logit contributions
aw+0.020
 regretted+0.018
 gol+0.017
opter+0.016
ime+0.015
Neg logit contributions
 first-0.017
 next-0.016
balls-0.015
ider-0.014
 front-0.012
Tokenies
Token ID444
Feature activation+1.29e+00

Pos logit contributions
 first+0.004
 next+0.004
balls+0.003
ider+0.003
 one+0.003
Neg logit contributions
aw-0.005
 regretted-0.004
 gol-0.004
opter-0.004
hing-0.003
Token.
Token ID13
Feature activation-5.74e-01

Pos logit contributions
aw+0.074
 regretted+0.069
 gol+0.066
opter+0.063
ime+0.060
Neg logit contributions
 first-0.043
 next-0.039
balls-0.035
ider-0.033
 last-0.027
Token One
Token ID1881
Feature activation-2.79e+00

Pos logit contributions
 first+0.020
 next+0.019
balls+0.017
ider+0.017
 last+0.014
Neg logit contributions
aw-0.032
 regretted-0.027
 gol-0.027
opter-0.024
ime-0.023
Token was
Token ID373
Feature activation+1.15e-01

Pos logit contributions
 first+0.134
balls+0.133
ider+0.129
 next+0.123
 hips+0.116
Neg logit contributions
aw-0.113
 regretted-0.099
 gol-0.091
ime-0.083
opter-0.081
Token sick
Token ID6639
Feature activation-8.18e-02

Pos logit contributions
aw+0.007
 regretted+0.006
 gol+0.006
opter+0.006
ime+0.005
Neg logit contributions
 first-0.004
 next-0.003
balls-0.003
ider-0.003
 front-0.002
Token,
Token ID11
Feature activation-2.62e-01

Pos logit contributions
 first+0.003
 next+0.003
balls+0.002
ider+0.002
 last+0.002
Neg logit contributions
aw-0.004
 regretted-0.004
 gol-0.004
opter-0.004
ime-0.004
Token and
Token ID290
Feature activation+5.38e-02

Pos logit contributions
 first+0.010
 next+0.009
balls+0.008
ider+0.008
 last+0.007
Neg logit contributions
aw-0.014
 regretted-0.013
 gol-0.012
opter-0.011
ime-0.011
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
aw+0.003
 regretted+0.003
 gol+0.003
opter+0.003
ime+0.002
Neg logit contributions
 first-0.002
 next-0.002
balls-0.001
ider-0.001
 one-0.001
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
 first+0.011
ider+0.010
 next+0.009
balls+0.009
 hips+0.009
Neg logit contributions
aw-0.014
 gol-0.011
 regretted-0.011
opter-0.010
hing-0.010
Token have
Token ID423
Feature activation-1.26e+00

Pos logit contributions
 first+0.037
 next+0.034
ider+0.033
balls+0.032
 front+0.025
Neg logit contributions
aw-0.056
 regretted-0.053
 gol-0.051
opter-0.047
ime-0.045
Token fun
Token ID1257
Feature activation+2.95e-01

Pos logit contributions
 first+0.050
 next+0.045
balls+0.042
ider+0.037
 one+0.034
Neg logit contributions
aw-0.063
 regretted-0.060
 gol-0.058
opter-0.054
ime-0.051
Token together
Token ID1978
Feature activation-2.93e+00

Pos logit contributions
aw+0.014
 regretted+0.011
 gol+0.011
opter+0.010
ime+0.010
Neg logit contributions
 first-0.012
ider-0.010
 next-0.010
balls-0.010
 particular-0.009
Token.
Token ID13
Feature activation+9.54e-02

Pos logit contributions
 first+0.105
 next+0.094
balls+0.091
ider+0.090
 front+0.073
Neg logit contributions
aw-0.156
 regretted-0.137
 gol-0.131
opter-0.121
ime-0.118
Token One
Token ID1881
Feature activation-2.78e+00

Pos logit contributions
aw+0.004
 gol+0.004
 regretted+0.003
opter+0.003
ime+0.003
Neg logit contributions
 first-0.004
ider-0.004
balls-0.004
 next-0.004
 hips-0.003
Token day
Token ID1110
Feature activation-6.88e-01

Pos logit contributions
balls+0.130
ider+0.130
 first+0.123
 hips+0.114
 next+0.109
Neg logit contributions
aw-0.112
 regretted-0.097
 gol-0.090
ime-0.087
 musician-0.079
Token,
Token ID11
Feature activation-3.00e-02

Pos logit contributions
 first+0.027
 next+0.024
balls+0.023
ider+0.022
 last+0.018
Neg logit contributions
aw-0.036
 regretted-0.033
 gol-0.031
opter-0.029
ime-0.028
Token the
Token ID262
Feature activation+7.18e-01

Pos logit contributions
 first+0.001
 next+0.001
ider+0.001
balls+0.001
 hips+0.001
Neg logit contributions
aw-0.002
 regretted-0.001
 gol-0.001
opter-0.001
ime-0.001
Token onion
Token ID21670
Feature activation+2.42e-01

Pos logit contributions
aw+0.035
 regretted+0.030
 gol+0.030
opter+0.028
aden+0.025
Neg logit contributions
 first-0.033
 next-0.032
balls-0.028
ider-0.026
 last-0.024
Token and
Token ID290
Feature activation+5.26e-02

Pos logit contributions
aw+0.013
 gol+0.012
opter+0.012
aden+0.011
 regretted+0.011
Neg logit contributions
 first-0.009
 next-0.009
balls-0.007
 one-0.007
ider-0.006
Token named
Token ID3706
Feature activation-1.29e+00

Pos logit contributions
 first+0.023
balls+0.022
ider+0.020
 next+0.020
 hips+0.018
Neg logit contributions
aw-0.022
 regretted-0.019
 gol-0.018
ime-0.016
opter-0.015
Token Anna
Token ID11735
Feature activation-2.89e+00

Pos logit contributions
ider+0.049
balls+0.048
 first+0.047
 next+0.046
 hips+0.039
Neg logit contributions
aw-0.058
 regretted-0.048
 gol-0.047
ime-0.044
opter-0.044
Token.
Token ID13
Feature activation+5.40e-01

Pos logit contributions
 first+0.084
 next+0.077
balls+0.062
ider+0.059
 front+0.049
Neg logit contributions
aw-0.176
 regretted-0.164
 gol-0.162
opter-0.152
ime-0.143
Token She
Token ID1375
Feature activation-2.80e-01

Pos logit contributions
aw+0.022
 regretted+0.018
 gol+0.016
ime+0.015
opter+0.015
Neg logit contributions
 first-0.026
 next-0.024
balls-0.023
ider-0.023
 timer-0.019
Token was
Token ID373
Feature activation+1.59e-02

Pos logit contributions
 first+0.014
 next+0.013
balls+0.012
ider+0.012
 last+0.011
Neg logit contributions
aw-0.011
 regretted-0.010
 gol-0.010
opter-0.009
ime-0.008
Token three
Token ID1115
Feature activation-2.69e+00

Pos logit contributions
aw+0.001
 regretted+0.001
 gol+0.001
ime+0.001
 mustache+0.001
Neg logit contributions
 first-0.001
ider-0.001
balls-0.001
 next-0.001
 hips-0.001
Token years
Token ID812
Feature activation+1.07e-01

Pos logit contributions
 first+0.111
 next+0.101
balls+0.098
ider+0.095
 last+0.080
Neg logit contributions
aw-0.135
 regretted-0.120
 gol-0.110
opter-0.104
ime-0.101
Token old
Token ID1468
Feature activation+1.71e+00

Pos logit contributions
aw+0.006
 regretted+0.005
 gol+0.005
opter+0.005
arre+0.005
Neg logit contributions
 first-0.004
 next-0.004
balls-0.003
ider-0.003
 front-0.003
Token and
Token ID290
Feature activation+5.97e-01

Pos logit contributions
aw+0.094
 regretted+0.087
 gol+0.085
opter+0.081
ime+0.076
Neg logit contributions
 first-0.060
 next-0.055
balls-0.048
ider-0.046
 front-0.039
Token liked
Token ID8288
Feature activation+5.94e-01

Pos logit contributions
aw+0.019
 regretted+0.017
 gol+0.014
opter+0.013
ime+0.012
Neg logit contributions
 first-0.033
ider-0.031
 next-0.031
balls-0.031
 hips-0.027
Token to
Token ID284
Feature activation+9.25e-01

Pos logit contributions
aw+0.039
 regretted+0.037
opter+0.036
 gol+0.036
ime+0.032
Neg logit contributions
 first-0.016
 next-0.015
balls-0.012
 one-0.009
 Mia-0.008
Token also
Token ID635
Feature activation-2.56e+00

Pos logit contributions
aw+0.023
 regretted+0.021
 gol+0.019
ime+0.016
 musician+0.016
Neg logit contributions
balls-0.023
 first-0.023
ider-0.022
 next-0.022
 hips-0.019
Token a
Token ID257
Feature activation-7.44e-01

Pos logit contributions
 first+0.103
 next+0.095
balls+0.092
ider+0.089
 hips+0.077
Neg logit contributions
aw-0.124
 regretted-0.112
 gol-0.108
opter-0.096
ime-0.094
Token bit
Token ID1643
Feature activation-1.31e+00

Pos logit contributions
 first+0.033
 next+0.031
balls+0.028
ider+0.027
 front+0.024
Neg logit contributions
aw-0.035
 regretted-0.031
 gol-0.029
opter-0.027
ime-0.026
Token scared
Token ID12008
Feature activation+4.62e-01

Pos logit contributions
 first+0.061
 next+0.056
balls+0.052
ider+0.052
 last+0.045
Neg logit contributions
aw-0.058
 regretted-0.051
 gol-0.049
opter-0.047
ime-0.043
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
aw+0.025
 regretted+0.023
 gol+0.022
opter+0.021
ime+0.019
Neg logit contributions
 first-0.017
 next-0.016
balls-0.013
ider-0.013
 one-0.012
Token One
Token ID1881
Feature activation-2.78e+00

Pos logit contributions
aw+0.017
 regretted+0.015
 gol+0.015
opter+0.014
ime+0.013
Neg logit contributions
 first-0.010
 next-0.009
balls-0.009
ider-0.008
 last-0.007
Token day
Token ID1110
Feature activation-8.73e-01

Pos logit contributions
balls+0.125
 first+0.121
ider+0.121
 hips+0.108
 next+0.107
Neg logit contributions
aw-0.119
 regretted-0.107
 gol-0.096
ime-0.091
opter-0.086
Token,
Token ID11
Feature activation-1.06e-01

Pos logit contributions
 first+0.032
 next+0.029
balls+0.027
ider+0.025
 one+0.021
Neg logit contributions
aw-0.047
 regretted-0.044
 gol-0.042
opter-0.039
ime-0.037
Token she
Token ID673
Feature activation+1.14e-01

Pos logit contributions
 first+0.004
 next+0.003
balls+0.003
ider+0.003
 hips+0.002
Neg logit contributions
aw-0.006
 regretted-0.005
 gol-0.005
opter-0.005
ime-0.005
Token wanted
Token ID2227
Feature activation+1.73e+00

Pos logit contributions
aw+0.006
 gol+0.005
opter+0.005
 regretted+0.005
 perspective+0.005
Neg logit contributions
 first-0.005
 next-0.005
balls-0.003
 one-0.003
ider-0.003
Token to
Token ID284
Feature activation-2.60e-01

Pos logit contributions
aw+0.086
 regretted+0.079
 gol+0.073
opter+0.066
ime+0.066
Neg logit contributions
 first-0.066
ider-0.061
 next-0.060
balls-0.060
 hips-0.048