TOP ACTIVATIONS
MAX = 0.248

the owner smiled . " Looks like you two are friends
's mom my . " Looks like the wave destroyed all
that sharing was better than wasting . And they enjoyed their
table . " Looks like mom has some mail
smiled and said , " Looks like you like the wardrobe
of the story : Gener osity is sometimes the best gift
smoothly . After applying the oil , Lily 's
smiled . " Looks like the frog likes you
's best for you . Taking a bath is good for
the tap . It 's wasting water . We should tell
are food . You are wasting them . You have to
than being jealous . Gener osity is the best way to
laughed and said , " Looks like that apple made you
the game . You are wasting your time ."
and cake with them . Taking things that do not belong
always have its rewards . Taking a break is important ,
asked . " You are wasting the food and the energy
no one is watching . Taking something that doesn 't belong
suggested . Without wasting any time , they went
happened . The fridge was wasting a lot of energy and

MIN ACTIVATIONS
MIN = -0.199

a big bird called an ostr ich . It had long
she left Lily with her babys itter .
a big bird called an ostr ich . He was very
and left her with her babys itter , Sarah . Sarah
a big bird called an ostr ich . The ostr ich
a big bird called an ostr ich was walking in the
a big bird called an ostr ich . The ostr ich
Tim asked a man , " Can I go
so they asked a kind man to help them . The
know , her mum was fore shadow ing ... the next
, Jack asked a wise man , who was walking by
they left her with a babys itter and went to climb
cheering . She asked a man , " What 's happening
, he asked the black smith why he used the scales
She asked a man for help . He was
L ily and her babys itter went to the park
The bird asked an old man : " What was that
very polite and asked the man who owned the bird if
So the car asked a man for help . The man
top . They asked a man who was bald to tell

INTERVAL 0.136 - 0.248
CONTAINS 3.649%

saw a pretty toy . She wanted to give it to
out from the pile . She went closer to look and
create something new . He used his creative mind to make
table and it is very long ". Then he started
find his favorite folder . He searched high and low ,

INTERVAL 0.025 - 0.136
CONTAINS 36.017%

toys and run around outside . One day , Lily 's
" I am Ben . I like to study the
who were always happy to play together . But
Tim . Tim was feeling sad . He didn 't know
she would always remember it . <|endoftext|> Once upon a time

INTERVAL -0.087 - 0.025
CONTAINS 46.780%

" Wow , Bob o , you are very brave ,"
" O w , ow , ow ! It hurts ,
with a shovel . But his daddy said no because the
When they arrived at the park , they saw that all
<|endoftext|> Once upon a time , there was a clever boy

INTERVAL -0.199 - -0.087
CONTAINS 13.554%

said . " I want to play with you ."
with me and my mom ?" she says .
. Tom said , " Let 's go for
box and we found this photo . We wanted to see
to come with you !" So , the p
Token the
Token ID262
Feature activation+8.52e-03

Pos logit contributions
 babys+0.017
 stub+0.015
 salon+0.013
ister+0.013
 nowhere+0.013
Neg logit contributions
ets-0.017
 textures-0.014
 They-0.014
essing-0.014
 sizes-0.014
Token owner
Token ID4870
Feature activation-1.15e-01

Pos logit contributions
ets+0.014
 They+0.014
 textures+0.013
 respect+0.013
ly+0.012
Neg logit contributions
 babys-0.016
 salon-0.013
 stub-0.013
ister-0.012
fer-0.012
Token smiled
Token ID13541
Feature activation-3.13e-02

Pos logit contributions
 babys+0.189
 stub+0.151
 salon+0.144
ister+0.133
 bumped+0.129
Neg logit contributions
ets-0.232
 textures-0.200
essing-0.197
 goals-0.196
 sizes-0.195
Token.
Token ID13
Feature activation+3.09e-02

Pos logit contributions
 babys+0.061
 stub+0.054
 nowhere+0.051
 crying+0.051
fer+0.047
Neg logit contributions
ets-0.051
ales-0.042
ws-0.041
angles-0.041
 sizes-0.040
Token "
Token ID366
Feature activation-2.49e-02

Pos logit contributions
ets+0.063
le+0.062
wed+0.051
 respect+0.050
ly+0.050
Neg logit contributions
 babys-0.052
-0.040
 stub-0.040
 crying-0.037
 Lee-0.036
TokenLooks
Token ID41102
Feature activation+2.48e-01

Pos logit contributions
 babys+0.041
 stub+0.036
 salon+0.032
ister+0.031
 nowhere+0.031
Neg logit contributions
ets-0.048
essing-0.040
 They-0.040
 textures-0.040
ly-0.039
Token like
Token ID588
Feature activation+1.31e-01

Pos logit contributions
ales+0.295
angles+0.287
en+0.278
ires+0.265
 Later+0.259
Neg logit contributions
 stub-0.442
 babys-0.427
 startled-0.380
 bumped-0.365
 pin-0.365
Token you
Token ID345
Feature activation+2.13e-02

Pos logit contributions
ets+0.228
 textures+0.185
 They+0.185
essing+0.183
le+0.181
Neg logit contributions
 babys-0.250
 stub-0.212
 salon-0.197
ister-0.193
 nowhere-0.187
Token two
Token ID734
Feature activation+8.10e-02

Pos logit contributions
ets+0.031
 They+0.025
 textures+0.025
essing+0.024
 sizes+0.024
Neg logit contributions
 babys-0.047
 stub-0.041
 salon-0.038
ister-0.037
 poster-0.036
Token are
Token ID389
Feature activation-8.35e-02

Pos logit contributions
ets+0.134
essing+0.117
 After+0.116
 textures+0.116
lated+0.115
Neg logit contributions
 babys-0.153
 stub-0.127
ister-0.119
 salon-0.117
 poster-0.110
Token friends
Token ID2460
Feature activation-3.06e-02

Pos logit contributions
 babys+0.154
 stub+0.127
ister+0.118
 salon+0.115
fer+0.109
Neg logit contributions
ets-0.152
 textures-0.129
essing-0.124
 They-0.124
lated-0.124
Token's
Token ID338
Feature activation-5.49e-02

Pos logit contributions
ets+0.013
 textures+0.010
 They+0.010
 sizes+0.009
essing+0.009
Neg logit contributions
 babys-0.023
 stub-0.020
 salon-0.019
ister-0.019
fer-0.018
Token mom
Token ID1995
Feature activation-1.43e-01

Pos logit contributions
 babys+0.107
 stub+0.091
 salon+0.087
ister+0.085
fer+0.082
Neg logit contributions
ets-0.090
 They-0.078
 textures-0.076
ly-0.072
essing-0.072
Tokenmy
Token ID1820
Feature activation-3.85e-02

Pos logit contributions
 babys+0.282
 stub+0.237
 salon+0.221
ister+0.217
 crying+0.207
Neg logit contributions
ets-0.247
 textures-0.202
 They-0.202
 goals-0.201
essing-0.193
Token.
Token ID13
Feature activation+3.41e-02

Pos logit contributions
 babys+0.092
 stub+0.079
 salon+0.074
ister+0.074
 crying+0.073
Neg logit contributions
ets-0.051
 textures-0.040
 goals-0.038
 They-0.038
 sizes-0.037
Token "
Token ID366
Feature activation-2.85e-02

Pos logit contributions
 They+0.047
ets+0.045
 After+0.041
 until+0.040
 textures+0.037
Neg logit contributions
 babys-0.071
 stub-0.063
 salon-0.061
ister-0.060
fer-0.059
TokenLooks
Token ID41102
Feature activation+2.43e-01

Pos logit contributions
 babys+0.055
 stub+0.045
 salon+0.043
ister+0.043
 poster+0.041
Neg logit contributions
ets-0.048
 They-0.043
 textures-0.042
 sizes-0.040
 respect-0.039
Token like
Token ID588
Feature activation+1.30e-01

Pos logit contributions
ales+0.308
angles+0.300
en+0.295
ets+0.290
lated+0.281
Neg logit contributions
 stub-0.440
 babys-0.436
 bumped-0.368
 nowhere-0.362
 crying-0.359
Token the
Token ID262
Feature activation+3.32e-02

Pos logit contributions
ets+0.203
 They+0.170
 textures+0.167
 sizes+0.158
essing+0.158
Neg logit contributions
 babys-0.266
 stub-0.227
 salon-0.215
ister-0.212
fer-0.203
Token wave
Token ID6769
Feature activation+2.55e-02

Pos logit contributions
ets+0.063
 They+0.054
 textures+0.053
essing+0.052
 sizes+0.051
Neg logit contributions
 babys-0.058
 stub-0.048
 salon-0.045
ister-0.044
 poster-0.042
Token destroyed
Token ID6572
Feature activation+1.03e-01

Pos logit contributions
ets+0.036
 textures+0.030
 They+0.030
essing+0.028
 After+0.028
Neg logit contributions
 babys-0.055
 stub-0.048
 salon-0.046
ister-0.045
 poster-0.044
Token all
Token ID477
Feature activation+1.20e-01

Pos logit contributions
ets+0.143
 They+0.115
 textures+0.112
essing+0.108
 sizes+0.106
Neg logit contributions
 babys-0.230
 stub-0.199
 salon-0.192
ister-0.188
 poster-0.180
Token that
Token ID326
Feature activation+6.97e-02

Pos logit contributions
ets+0.058
 They+0.047
 textures+0.046
essing+0.044
 sizes+0.044
Neg logit contributions
 babys-0.086
 stub-0.075
 salon-0.071
ister-0.070
fer-0.067
Token sharing
Token ID7373
Feature activation+1.18e-01

Pos logit contributions
ets+0.101
 They+0.094
 textures+0.092
 respect+0.087
 sizes+0.086
Neg logit contributions
 babys-0.143
 stub-0.123
ister-0.117
 salon-0.116
fer-0.113
Token was
Token ID373
Feature activation-9.09e-02

Pos logit contributions
ets+0.135
 They+0.103
 textures+0.101
essing+0.096
ly+0.094
Neg logit contributions
 babys-0.289
 stub-0.254
 salon-0.244
ister-0.240
 poster-0.233
Token better
Token ID1365
Feature activation+5.95e-02

Pos logit contributions
 babys+0.166
 nowhere+0.139
 stub+0.138
ister+0.127
 salon+0.127
Neg logit contributions
ets-0.159
ly-0.134
le-0.129
ales-0.127
ness-0.125
Token than
Token ID621
Feature activation+7.79e-02

Pos logit contributions
ets+0.068
lated+0.061
ales+0.058
 textures+0.057
bit+0.056
Neg logit contributions
 babys-0.129
 stub-0.113
 nowhere-0.110
ister-0.108
 poster-0.107
Token wasting
Token ID24430
Feature activation+2.41e-01

Pos logit contributions
ets+0.158
 They+0.138
 textures+0.136
essing+0.132
 sizes+0.131
Neg logit contributions
 babys-0.124
 stub-0.101
 salon-0.094
ister-0.091
fer-0.086
Token.
Token ID13
Feature activation+4.42e-02

Pos logit contributions
ets+0.331
essing+0.283
lated+0.276
 After+0.275
 They+0.270
Neg logit contributions
 babys-0.496
 stub-0.427
 nowhere-0.402
 salon-0.400
ister-0.397
Token And
Token ID843
Feature activation+5.07e-02

Pos logit contributions
ets+0.040
ly+0.028
le+0.028
 textures+0.024
wed+0.022
Neg logit contributions
 babys-0.125
 stub-0.109
 salon-0.105
ister-0.104
 nowhere-0.102
Token they
Token ID484
Feature activation+6.22e-02

Pos logit contributions
ets+0.087
 textures+0.071
 They+0.070
ly+0.068
essing+0.068
Neg logit contributions
 babys-0.098
 stub-0.083
 salon-0.080
ister-0.077
 nowhere-0.074
Token enjoyed
Token ID8359
Feature activation+7.45e-02

Pos logit contributions
ets+0.103
 textures+0.089
ly+0.088
essing+0.086
 sizes+0.086
Neg logit contributions
 babys-0.119
 stub-0.101
 salon-0.097
ister-0.092
 nowhere-0.092
Token their
Token ID511
Feature activation+1.30e-02

Pos logit contributions
ets+0.136
 They+0.113
 textures+0.112
ly+0.110
essing+0.109
Neg logit contributions
 babys-0.136
 stub-0.114
 salon-0.108
ister-0.105
 nowhere-0.100
Token table
Token ID3084
Feature activation-2.26e-02

Pos logit contributions
ets+0.093
 They+0.081
 textures+0.078
wed+0.078
 After+0.078
Neg logit contributions
 babys-0.086
 stub-0.067
 salon-0.065
 poster-0.063
 principal-0.061
Token.
Token ID13
Feature activation+4.76e-02

Pos logit contributions
 babys+0.053
 salon+0.047
 stub+0.045
ister+0.044
 nowhere+0.043
Neg logit contributions
ets-0.026
 textures-0.021
essing-0.021
lated-0.020
 After-0.020
Token
Token ID198
Feature activation-9.09e-02

Pos logit contributions
ets+0.043
 textures+0.029
le+0.026
 sizes+0.026
essing+0.026
Neg logit contributions
 babys-0.133
 stub-0.117
 salon-0.112
ister-0.112
 principal-0.109
Token
Token ID198
Feature activation-8.85e-02

Pos logit contributions
 babys+0.184
 stub+0.158
 salon+0.154
fer+0.145
ister+0.143
Neg logit contributions
ets-0.138
 They-0.130
 After-0.116
 until-0.114
 textures-0.113
Token"
Token ID1
Feature activation-4.54e-02

Pos logit contributions
 babys+0.164
 stub+0.136
ister+0.133
 salon+0.128
 principal+0.122
Neg logit contributions
ets-0.163
 textures-0.140
 sizes-0.133
essing-0.132
le-0.131
TokenLooks
Token ID41102
Feature activation+2.40e-01

Pos logit contributions
 babys+0.081
 stub+0.070
ister+0.065
 salon+0.064
fer+0.059
Neg logit contributions
ets-0.080
 They-0.073
 textures-0.070
 respect-0.068
ly-0.066
Token like
Token ID588
Feature activation+1.24e-01

Pos logit contributions
ales+0.277
en+0.276
angles+0.265
lated+0.261
 textures+0.256
Neg logit contributions
 babys-0.449
 stub-0.430
 bumped-0.376
 startled-0.372
 crying-0.371
Token mom
Token ID1995
Feature activation-8.54e-02

Pos logit contributions
ets+0.199
 They+0.166
 textures+0.164
essing+0.157
 sizes+0.156
Neg logit contributions
 babys-0.249
 stub-0.212
 salon-0.202
ister-0.197
 poster-0.188
Token has
Token ID468
Feature activation+6.93e-02

Pos logit contributions
 babys+0.189
 stub+0.160
 salon+0.157
ister+0.154
 poster+0.146
Neg logit contributions
ets-0.121
 textures-0.100
 They-0.097
essing-0.092
 After-0.091
Token some
Token ID617
Feature activation+5.10e-02

Pos logit contributions
ets+0.119
 They+0.103
 textures+0.102
essing+0.100
lated+0.098
Neg logit contributions
 babys-0.131
 stub-0.108
 salon-0.103
 nowhere-0.096
ister-0.096
Token mail
Token ID6920
Feature activation+2.59e-02

Pos logit contributions
ets+0.093
 They+0.083
essing+0.082
 textures+0.081
lated+0.080
Neg logit contributions
 babys-0.092
 salon-0.068
 stub-0.068
ister-0.066
 poster-0.063
Token smiled
Token ID13541
Feature activation-2.11e-02

Pos logit contributions
 babys+0.141
 stub+0.112
 salon+0.105
ister+0.099
 nowhere+0.097
Neg logit contributions
ets-0.204
 textures-0.177
 They-0.176
 sizes-0.173
essing-0.172
Token and
Token ID290
Feature activation-1.27e-02

Pos logit contributions
 babys+0.045
 stub+0.039
 nowhere+0.037
 crying+0.036
ister+0.035
Neg logit contributions
ets-0.031
ales-0.025
 sizes-0.025
ws-0.025
 textures-0.024
Token said
Token ID531
Feature activation-9.07e-02

Pos logit contributions
 babys+0.025
 stub+0.021
 salon+0.020
ister+0.020
fer+0.019
Neg logit contributions
ets-0.021
 They-0.018
 textures-0.017
 until-0.017
ly-0.017
Token,
Token ID11
Feature activation-8.59e-02

Pos logit contributions
 babys+0.187
 stub+0.160
 salon+0.152
ister+0.149
fer+0.142
Neg logit contributions
ets-0.143
 textures-0.117
 They-0.117
 sizes-0.112
essing-0.112
Token "
Token ID366
Feature activation-3.61e-02

Pos logit contributions
 babys+0.188
 stub+0.167
 salon+0.162
ister+0.159
fer+0.153
Neg logit contributions
ets-0.108
 They-0.107
 until-0.098
 After-0.094
 textures-0.088
TokenLooks
Token ID41102
Feature activation+2.39e-01

Pos logit contributions
 babys+0.054
 stub+0.045
 salon+0.043
Re+0.042
ister+0.040
Neg logit contributions
ets-0.074
essing-0.062
ws-0.061
 goals-0.060
ly-0.060
Token like
Token ID588
Feature activation+1.23e-01

Pos logit contributions
ales+0.323
angles+0.302
en+0.300
 Later+0.291
lated+0.277
Neg logit contributions
 stub-0.365
 babys-0.356
 startled-0.324
 pin-0.318
 mis-0.315
Token you
Token ID345
Feature activation+1.69e-02

Pos logit contributions
ets+0.229
lated+0.190
le+0.187
essing+0.185
ly+0.183
Neg logit contributions
 babys-0.220
 stub-0.178
 salon-0.173
 nowhere-0.167
ister-0.163
Token like
Token ID588
Feature activation+1.22e-01

Pos logit contributions
ets+0.024
lated+0.021
 textures+0.021
erve+0.020
ires+0.020
Neg logit contributions
 babys-0.035
 stub-0.030
 salon-0.028
ister-0.027
 bumped-0.027
Token the
Token ID262
Feature activation+2.33e-02

Pos logit contributions
ets+0.199
 textures+0.163
 They+0.163
essing+0.158
ly+0.156
Neg logit contributions
 babys-0.244
 stub-0.204
 salon-0.196
ister-0.190
 nowhere-0.184
Token wardrobe
Token ID35593
Feature activation-4.24e-02

Pos logit contributions
ets+0.040
 They+0.034
 textures+0.032
essing+0.032
 After+0.031
Neg logit contributions
 babys-0.046
 stub-0.038
 salon-0.036
ister-0.035
 poster-0.034
Token of
Token ID286
Feature activation+9.11e-02

Pos logit contributions
 babys+0.001
ister+0.001
 stub+0.001
 poster+0.001
 salon+0.001
Neg logit contributions
ets-0.001
 textures-0.001
 sizes-0.001
ws-0.001
wed-0.001
Token the
Token ID262
Feature activation+3.52e-02

Pos logit contributions
ets+0.121
 They+0.103
 textures+0.098
 respect+0.096
 until+0.094
Neg logit contributions
 babys-0.205
 stub-0.178
 salon-0.172
ister-0.166
fer-0.163
Token story
Token ID1621
Feature activation-5.99e-02

Pos logit contributions
ets+0.080
 They+0.071
 textures+0.070
essing+0.068
 sizes+0.068
Neg logit contributions
 babys-0.048
 stub-0.038
 salon-0.035
ister-0.033
fer-0.031
Token:
Token ID25
Feature activation-9.44e-02

Pos logit contributions
 babys+0.095
ister+0.079
 salon+0.074
 stub+0.072
 poster+0.071
Neg logit contributions
ets-0.118
 textures-0.106
 sizes-0.100
le-0.100
ales-0.099
Token Gener
Token ID2980
Feature activation+4.44e-02

Pos logit contributions
 babys+0.169
 stub+0.142
 salon+0.139
 poster+0.136
't+0.135
Neg logit contributions
ets-0.167
lated-0.150
ly-0.138
le-0.136
ales-0.132
Tokenosity
Token ID16579
Feature activation+2.39e-01

Pos logit contributions
ets+0.078
 textures+0.070
le+0.067
lated+0.067
 until+0.067
Neg logit contributions
 babys-0.072
ister-0.060
 salon-0.059
 stub-0.059
 poster-0.053
Token is
Token ID318
Feature activation-1.10e-01

Pos logit contributions
ets+0.350
ales+0.301
lated+0.298
wed+0.286
essing+0.283
Neg logit contributions
 babys-0.474
ister-0.395
 poster-0.395
 salon-0.389
 stub-0.387
Token sometimes
Token ID3360
Feature activation+1.02e-01

Pos logit contributions
 babys+0.219
 stub+0.183
 nowhere+0.182
ister+0.178
 salon+0.172
Neg logit contributions
ets-0.165
 textures-0.137
ly-0.136
le-0.135
ales-0.133
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
ets+0.159
lated+0.139
ales+0.136
bit+0.134
wed+0.134
Neg logit contributions
 babys-0.190
 stub-0.164
 nowhere-0.158
 poster-0.156
ister-0.154
Token best
Token ID1266
Feature activation+3.71e-02

Pos logit contributions
ets+0.016
 They+0.013
 textures+0.012
ly+0.012
essing+0.012
Neg logit contributions
 babys-0.021
 stub-0.018
 salon-0.017
 poster-0.017
ister-0.017
Token gift
Token ID6979
Feature activation-2.88e-02

Pos logit contributions
ets+0.057
lated+0.052
ales+0.050
wed+0.049
bit+0.048
Neg logit contributions
 babys-0.072
 poster-0.058
 stub-0.058
ister-0.056
 nowhere-0.055
Token smoothly
Token ID21461
Feature activation+1.50e-01

Pos logit contributions
ets+0.091
 textures+0.084
ires+0.080
essing+0.079
 sizes+0.078
Neg logit contributions
 babys-0.122
 stub-0.109
 nowhere-0.100
 bumped-0.100
 salon-0.099
Token.
Token ID13
Feature activation+3.29e-02

Pos logit contributions
ets+0.175
 textures+0.142
 They+0.140
essing+0.135
 respect+0.133
Neg logit contributions
 babys-0.347
 stub-0.308
 salon-0.295
 nowhere-0.289
ister-0.286
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
ets+0.064
le+0.056
 textures+0.055
 sizes+0.054
 goals+0.053
Neg logit contributions
 babys-0.057
 stub-0.047
 salon-0.044
stand-0.039
-0.039
Token
Token ID198
Feature activation-9.84e-02

Pos logit contributions
 babys+0.221
 stub+0.185
 salon+0.185
fer+0.181
ister+0.174
Neg logit contributions
ets-0.148
 They-0.137
 until-0.125
 After-0.125
 respect-0.113
TokenAfter
Token ID3260
Feature activation+1.38e-01

Pos logit contributions
 babys+0.198
 stub+0.172
 salon+0.165
ister+0.160
 poster+0.151
Neg logit contributions
ets-0.156
 textures-0.130
 They-0.129
 sizes-0.126
essing-0.123
Token applying
Token ID11524
Feature activation+2.38e-01

Pos logit contributions
ets+0.217
 They+0.199
 until+0.190
 After+0.183
 textures+0.181
Neg logit contributions
 babys-0.270
 stub-0.236
 salon-0.222
ister-0.220
fer-0.213
Token the
Token ID262
Feature activation+4.10e-02

Pos logit contributions
ets+0.381
 They+0.313
 textures+0.311
essing+0.301
 sizes+0.297
Neg logit contributions
 babys-0.485
 stub-0.411
 salon-0.393
ister-0.383
 nowhere-0.364
Token oil
Token ID3056
Feature activation+1.36e-02

Pos logit contributions
ets+0.065
 They+0.054
 textures+0.053
essing+0.052
le+0.051
Neg logit contributions
 babys-0.085
 stub-0.071
 salon-0.067
ister-0.066
 poster-0.064
Token,
Token ID11
Feature activation-5.38e-02

Pos logit contributions
ets+0.019
 They+0.016
 textures+0.015
 until+0.015
ly+0.015
Neg logit contributions
 babys-0.030
 stub-0.026
 salon-0.025
ister-0.024
fer-0.023
Token Lily
Token ID20037
Feature activation+3.68e-02

Pos logit contributions
 babys+0.119
 stub+0.103
 salon+0.098
ister+0.096
fer+0.092
Neg logit contributions
ets-0.076
 They-0.063
 textures-0.061
essing-0.058
 sizes-0.058
Token's
Token ID338
Feature activation-2.47e-02

Pos logit contributions
ets+0.058
 They+0.048
 textures+0.048
essing+0.046
 sizes+0.045
Neg logit contributions
 babys-0.075
 stub-0.065
 salon-0.061
ister-0.060
fer-0.057
Token smiled
Token ID13541
Feature activation-2.40e-02

Pos logit contributions
 babys+0.168
 stub+0.141
 salon+0.133
ister+0.128
 nowhere+0.122
Neg logit contributions
ets-0.171
 They-0.146
 textures-0.145
essing-0.140
 sizes-0.138
Token.
Token ID13
Feature activation+4.05e-02

Pos logit contributions
 babys+0.052
 stub+0.046
 nowhere+0.043
ister+0.042
 salon+0.041
Neg logit contributions
ets-0.034
 textures-0.027
 sizes-0.026
ales-0.026
essing-0.025
Token
Token ID198
Feature activation-9.44e-02

Pos logit contributions
ets+0.067
 They+0.058
 textures+0.055
 until+0.053
 After+0.053
Neg logit contributions
 babys-0.079
 stub-0.068
 salon-0.065
ister-0.063
fer-0.061
Token
Token ID198
Feature activation-9.16e-02

Pos logit contributions
 babys+0.185
 stub+0.156
 salon+0.150
ister+0.143
fer+0.141
Neg logit contributions
ets-0.155
 They-0.138
 textures-0.128
 until-0.126
 After-0.126
Token"
Token ID1
Feature activation-4.85e-02

Pos logit contributions
 babys+0.171
 stub+0.146
ister+0.138
 salon+0.137
 poster+0.128
Neg logit contributions
ets-0.160
 textures-0.136
essing-0.130
 sizes-0.130
 They-0.128
TokenLooks
Token ID41102
Feature activation+2.36e-01

Pos logit contributions
 babys+0.096
 stub+0.079
ister+0.076
 salon+0.076
 principal+0.071
Neg logit contributions
ets-0.079
 They-0.072
 textures-0.069
 sizes-0.065
 respect-0.065
Token like
Token ID588
Feature activation+1.21e-01

Pos logit contributions
ales+0.267
angles+0.252
en+0.245
ets+0.241
lated+0.240
Neg logit contributions
 babys-0.441
 stub-0.440
 startled-0.377
 crying-0.371
 bumped-0.370
Token the
Token ID262
Feature activation+2.45e-02

Pos logit contributions
ets+0.181
 They+0.155
 textures+0.150
 respect+0.143
 sizes+0.141
Neg logit contributions
 babys-0.257
 stub-0.220
 salon-0.212
ister-0.207
fer-0.200
Token frog
Token ID21264
Feature activation-4.14e-02

Pos logit contributions
ets+0.044
 They+0.038
 textures+0.038
 sizes+0.036
ly+0.036
Neg logit contributions
 babys-0.044
 stub-0.036
 salon-0.035
ister-0.034
fer-0.032
Token likes
Token ID7832
Feature activation+9.67e-02

Pos logit contributions
 babys+0.090
 stub+0.078
 salon+0.074
ister+0.074
 poster+0.071
Neg logit contributions
ets-0.058
 textures-0.048
 They-0.046
lated-0.046
essing-0.046
Token you
Token ID345
Feature activation+3.40e-03

Pos logit contributions
ets+0.155
 They+0.130
 textures+0.128
essing+0.122
 sizes+0.121
Neg logit contributions
 babys-0.195
 stub-0.166
 salon-0.158
ister-0.154
fer-0.147
Token's
Token ID338
Feature activation+5.36e-03

Pos logit contributions
ets+0.080
 They+0.073
 textures+0.068
 respect+0.067
 goals+0.065
Neg logit contributions
 babys-0.131
 stub-0.109
 salon-0.106
ister-0.105
fer-0.104
Token best
Token ID1266
Feature activation+5.48e-02

Pos logit contributions
ets+0.008
 They+0.007
 textures+0.007
 sizes+0.006
essing+0.006
Neg logit contributions
 babys-0.011
 stub-0.010
 salon-0.009
ister-0.009
 poster-0.009
Token for
Token ID329
Feature activation+4.49e-02

Pos logit contributions
ets+0.066
lated+0.054
 They+0.054
 textures+0.051
 sizes+0.050
Neg logit contributions
 babys-0.130
 stub-0.113
 salon-0.107
ister-0.105
 principal-0.101
Token you
Token ID345
Feature activation+1.32e-02

Pos logit contributions
ets+0.082
 textures+0.071
 They+0.070
 sizes+0.069
lated+0.068
Neg logit contributions
 babys-0.079
 stub-0.065
 salon-0.063
ister-0.063
 nowhere-0.059
Token.
Token ID13
Feature activation+5.26e-02

Pos logit contributions
ets+0.013
 textures+0.011
lated+0.011
 They+0.010
 After+0.010
Neg logit contributions
 babys-0.032
 stub-0.029
 salon-0.027
ister-0.027
 nowhere-0.026
Token Taking
Token ID20879
Feature activation+2.35e-01

Pos logit contributions
ets+0.092
ly+0.075
le+0.075
 textures+0.075
lated+0.074
Neg logit contributions
 babys-0.102
 stub-0.085
 salon-0.077
 principal-0.076
stand-0.074
Token a
Token ID257
Feature activation-1.56e-03

Pos logit contributions
ets+0.385
 They+0.333
 textures+0.327
essing+0.320
 sizes+0.313
Neg logit contributions
 babys-0.445
 stub-0.382
 salon-0.357
ister-0.341
 nowhere-0.337
Token bath
Token ID7837
Feature activation-1.01e-02

Pos logit contributions
 babys+0.003
fer+0.003
ister+0.003
 salon+0.003
chard+0.003
Neg logit contributions
ets-0.002
 proper-0.002
 respect-0.002
 They-0.002
 until-0.002
Token is
Token ID318
Feature activation-8.41e-02

Pos logit contributions
 babys+0.023
 stub+0.020
 salon+0.019
ister+0.019
 poster+0.018
Neg logit contributions
ets-0.013
 textures-0.011
 They-0.011
essing-0.010
 sizes-0.010
Token good
Token ID922
Feature activation+7.53e-02

Pos logit contributions
 babys+0.164
 stub+0.141
 salon+0.131
ister+0.126
 nowhere+0.124
Neg logit contributions
ets-0.136
 They-0.115
 textures-0.114
ly-0.111
 sizes-0.110
Token for
Token ID329
Feature activation+3.50e-02

Pos logit contributions
ets+0.095
lated+0.079
essing+0.075
 They+0.074
 textures+0.074
Neg logit contributions
 babys-0.178
 stub-0.153
 salon-0.144
ister-0.141
 poster-0.138
Token the
Token ID262
Feature activation+1.38e-02

Pos logit contributions
ets+0.048
 They+0.039
 textures+0.038
essing+0.037
 sizes+0.036
Neg logit contributions
 babys-0.066
 stub-0.056
 salon-0.054
ister-0.054
 nowhere-0.052
Token tap
Token ID9814
Feature activation-4.44e-03

Pos logit contributions
ets+0.027
 They+0.024
 textures+0.023
essing+0.023
ly+0.022
Neg logit contributions
 babys-0.023
 stub-0.019
 salon-0.018
ister-0.017
 poster-0.017
Token.
Token ID13
Feature activation+5.21e-02

Pos logit contributions
 babys+0.009
 salon+0.009
ister+0.008
 stub+0.008
 poster+0.008
Neg logit contributions
ets-0.006
 textures-0.005
lated-0.005
 After-0.005
essing-0.005
Token It
Token ID632
Feature activation+4.28e-02

Pos logit contributions
ets+0.078
le+0.061
wed+0.060
 textures+0.060
ly+0.059
Neg logit contributions
 babys-0.115
 stub-0.098
ister-0.093
 salon-0.091
-0.089
Token's
Token ID338
Feature activation-1.10e-02

Pos logit contributions
ets+0.067
 textures+0.057
ly+0.054
 After+0.054
 They+0.054
Neg logit contributions
 babys-0.084
 stub-0.073
 salon-0.067
 poster-0.067
 bumped-0.066
Token wasting
Token ID24430
Feature activation+2.34e-01

Pos logit contributions
 babys+0.019
 stub+0.016
 nowhere+0.015
 salon+0.015
ister+0.014
Neg logit contributions
ets-0.021
ly-0.017
 They-0.017
 textures-0.017
le-0.017
Token water
Token ID1660
Feature activation+1.79e-02

Pos logit contributions
ets+0.335
 They+0.274
essing+0.271
 textures+0.269
ly+0.264
Neg logit contributions
 babys-0.496
 stub-0.426
 salon-0.399
ister-0.396
 nowhere-0.392
Token.
Token ID13
Feature activation+4.73e-02

Pos logit contributions
ets+0.019
 textures+0.017
essing+0.016
 After+0.015
 They+0.015
Neg logit contributions
 babys-0.042
 stub-0.036
ister-0.036
 salon-0.035
 poster-0.033
Token We
Token ID775
Feature activation+6.60e-02

Pos logit contributions
ets+0.073
le+0.059
wed+0.058
ly+0.058
 textures+0.057
Neg logit contributions
 babys-0.100
 stub-0.085
ister-0.079
 salon-0.078
-0.076
Token should
Token ID815
Feature activation+8.94e-03

Pos logit contributions
ets+0.099
 textures+0.089
ly+0.087
lated+0.087
ires+0.086
Neg logit contributions
 babys-0.130
 stub-0.116
 bumped-0.106
ister-0.100
 salon-0.100
Token tell
Token ID1560
Feature activation+2.09e-02

Pos logit contributions
ets+0.018
ly+0.015
 sizes+0.015
lated+0.015
 goals+0.015
Neg logit contributions
 babys-0.015
ister-0.012
 stub-0.012
 salon-0.012
't-0.011
Token are
Token ID389
Feature activation-8.94e-02

Pos logit contributions
ets+0.299
lated+0.271
 After+0.267
essing+0.253
 Later+0.249
Neg logit contributions
 babys-0.320
 stub-0.249
 salon-0.248
ister-0.242
 poster-0.237
Token food
Token ID2057
Feature activation-1.71e-02

Pos logit contributions
 babys+0.154
 nowhere+0.119
 stub+0.117
 salon+0.117
chard+0.113
Neg logit contributions
ets-0.161
 After-0.141
est-0.140
le-0.140
ly-0.137
Token.
Token ID13
Feature activation+5.12e-02

Pos logit contributions
 babys+0.039
ister+0.033
 stub+0.032
 salon+0.032
 poster+0.031
Neg logit contributions
ets-0.021
 After-0.018
lated-0.017
 textures-0.017
essing-0.016
Token You
Token ID921
Feature activation+8.40e-02

Pos logit contributions
ets+0.060
lated+0.046
ly+0.045
le+0.044
 textures+0.044
Neg logit contributions
 babys-0.129
 stub-0.106
-0.101
stand-0.101
 principal-0.101
Token are
Token ID389
Feature activation-9.33e-02

Pos logit contributions
ets+0.133
lated+0.124
 textures+0.124
 After+0.122
ly+0.119
Neg logit contributions
 babys-0.157
 stub-0.136
 salon-0.124
 bumped-0.124
ister-0.119
Token wasting
Token ID24430
Feature activation+2.34e-01

Pos logit contributions
 babys+0.158
 stub+0.125
 nowhere+0.116
 salon+0.114
ister+0.108
Neg logit contributions
ets-0.182
 textures-0.157
 They-0.155
ly-0.154
le-0.152
Token them
Token ID606
Feature activation-1.91e-02

Pos logit contributions
ets+0.353
essing+0.300
lated+0.298
 textures+0.287
 They+0.286
Neg logit contributions
 babys-0.464
 stub-0.384
 nowhere-0.369
 salon-0.356
ister-0.352
Token.
Token ID13
Feature activation+5.71e-02

Pos logit contributions
 babys+0.046
 stub+0.040
 salon+0.038
ister+0.038
 nowhere+0.037
Neg logit contributions
ets-0.020
 textures-0.016
lated-0.016
 They-0.016
 After-0.015
Token You
Token ID921
Feature activation+8.72e-02

Pos logit contributions
ets+0.084
ly+0.068
lated+0.068
le+0.067
 textures+0.067
Neg logit contributions
 babys-0.126
 stub-0.103
 principal-0.097
ister-0.097
stand-0.095
Token have
Token ID423
Feature activation+6.62e-02

Pos logit contributions
ets+0.138
 textures+0.127
lated+0.127
 After+0.125
ly+0.123
Neg logit contributions
 babys-0.164
 stub-0.139
 salon-0.128
 bumped-0.127
ister-0.123
Token to
Token ID284
Feature activation-7.16e-02

Pos logit contributions
ets+0.124
 They+0.106
 textures+0.105
essing+0.102
ly+0.101
Neg logit contributions
 babys-0.116
 stub-0.097
 salon-0.091
ister-0.087
 nowhere-0.084
Token than
Token ID621
Feature activation+6.36e-02

Pos logit contributions
ets+0.076
lated+0.073
bit+0.071
 Later+0.069
 After+0.069
Neg logit contributions
 babys-0.126
 stub-0.111
 nowhere-0.110
fer-0.109
 poster-0.108
Token being
Token ID852
Feature activation+2.14e-02

Pos logit contributions
ets+0.123
 They+0.106
 textures+0.104
essing+0.101
 sizes+0.100
Neg logit contributions
 babys-0.108
 stub-0.089
 salon-0.084
ister-0.081
fer-0.076
Token jealous
Token ID19354
Feature activation+9.42e-02

Pos logit contributions
ets+0.038
 They+0.032
 textures+0.032
essing+0.031
ly+0.030
Neg logit contributions
 babys-0.039
 stub-0.033
 salon-0.030
ister-0.030
 nowhere-0.029
Token.
Token ID13
Feature activation+3.03e-02

Pos logit contributions
ets+0.129
lated+0.118
ales+0.117
 After+0.116
ws+0.115
Neg logit contributions
 babys-0.181
 stub-0.158
 nowhere-0.145
 salon-0.143
ister-0.142
Token Gener
Token ID2980
Feature activation+3.02e-02

Pos logit contributions
ets+0.050
 textures+0.041
ly+0.040
le+0.039
 sizes+0.038
Neg logit contributions
 babys-0.061
 stub-0.051
 salon-0.049
ister-0.048
 nowhere-0.046
Tokenosity
Token ID16579
Feature activation+2.33e-01

Pos logit contributions
ets+0.057
 textures+0.052
le+0.051
 goals+0.050
lated+0.049
Neg logit contributions
 babys-0.045
ister-0.037
 stub-0.036
 salon-0.036
fer-0.032
Token is
Token ID318
Feature activation-1.07e-01

Pos logit contributions
ets+0.341
lated+0.305
ales+0.304
wed+0.290
 After+0.286
Neg logit contributions
 babys-0.432
 poster-0.379
ister-0.373
 salon-0.370
 stub-0.357
Token the
Token ID262
Feature activation-6.24e-03

Pos logit contributions
 babys+0.193
 nowhere+0.164
 stub+0.162
 salon+0.151
ister+0.151
Neg logit contributions
ets-0.178
ly-0.156
le-0.151
ales-0.148
 textures-0.146
Token best
Token ID1266
Feature activation+2.75e-02

Pos logit contributions
 babys+0.013
 stub+0.011
 salon+0.010
 nowhere+0.010
ister+0.010
Neg logit contributions
ets-0.010
 They-0.008
essing-0.008
ly-0.008
 After-0.008
Token way
Token ID835
Feature activation-1.63e-02

Pos logit contributions
ets+0.046
lated+0.041
 Later+0.040
 After+0.040
wed+0.040
Neg logit contributions
 babys-0.050
 stub-0.041
fer-0.039
 poster-0.039
ister-0.039
Token to
Token ID284
Feature activation-6.53e-02

Pos logit contributions
 babys+0.022
 stub+0.019
 nowhere+0.017
ister+0.017
 salon+0.016
Neg logit contributions
ets-0.033
ws-0.030
lated-0.030
 textures-0.030
bit-0.030
Token laughed
Token ID13818
Feature activation+5.17e-03

Pos logit contributions
 babys+0.023
 stub+0.019
 salon+0.018
ister+0.018
fer+0.017
Neg logit contributions
ets-0.021
 They-0.018
 textures-0.017
 sizes-0.017
essing-0.017
Token and
Token ID290
Feature activation-9.57e-03

Pos logit contributions
ets+0.008
 textures+0.007
ws+0.007
ales+0.007
wed+0.007
Neg logit contributions
 babys-0.010
 stub-0.009
 nowhere-0.009
 crying-0.008
ister-0.008
Token said
Token ID531
Feature activation-9.13e-02

Pos logit contributions
 babys+0.017
 stub+0.014
 salon+0.014
ister+0.014
fer+0.013
Neg logit contributions
ets-0.017
 They-0.015
 textures-0.014
 sizes-0.014
 until-0.014
Token,
Token ID11
Feature activation-9.21e-02

Pos logit contributions
 babys+0.199
 stub+0.171
 salon+0.164
ister+0.160
fer+0.155
Neg logit contributions
ets-0.131
 They-0.111
 textures-0.105
ly-0.102
 until-0.102
Token "
Token ID366
Feature activation-4.25e-02

Pos logit contributions
 babys+0.181
 stub+0.154
 salon+0.146
ister+0.142
fer+0.136
Neg logit contributions
ets-0.151
 They-0.130
 textures-0.125
 until-0.120
essing-0.120
TokenLooks
Token ID41102
Feature activation+2.33e-01

Pos logit contributions
 babys+0.073
 stub+0.063
 salon+0.058
ister+0.055
 nowhere+0.053
Neg logit contributions
ets-0.080
 They-0.068
 textures-0.067
essing-0.066
ly-0.064
Token like
Token ID588
Feature activation+1.15e-01

Pos logit contributions
ales+0.248
angles+0.231
en+0.225
ets+0.222
ires+0.215
Neg logit contributions
 babys-0.464
 stub-0.461
 bumped-0.392
 startled-0.385
 nowhere-0.380
Token that
Token ID326
Feature activation+7.87e-02

Pos logit contributions
ets+0.174
 They+0.148
 textures+0.146
 respect+0.138
 until+0.137
Neg logit contributions
 babys-0.239
 stub-0.204
 salon-0.193
ister-0.192
fer-0.186
Token apple
Token ID17180
Feature activation-3.36e-02

Pos logit contributions
ets+0.109
 They+0.091
 textures+0.089
 until+0.083
 sizes+0.083
Neg logit contributions
 babys-0.175
 stub-0.151
 salon-0.145
ister-0.141
fer-0.137
Token made
Token ID925
Feature activation+7.34e-03

Pos logit contributions
 babys+0.072
 stub+0.062
 salon+0.060
ister+0.059
 poster+0.056
Neg logit contributions
ets-0.049
 They-0.040
 textures-0.039
essing-0.038
 sizes-0.037
Token you
Token ID345
Feature activation-1.81e-02

Pos logit contributions
ets+0.012
 They+0.010
 textures+0.010
essing+0.010
 sizes+0.010
Neg logit contributions
 babys-0.014
 stub-0.012
ister-0.011
 salon-0.011
 nowhere-0.010
Token the
Token ID262
Feature activation+2.21e-02

Pos logit contributions
ets+0.088
 They+0.069
 textures+0.068
essing+0.064
 sizes+0.064
Neg logit contributions
 babys-0.168
 stub-0.147
 salon-0.141
ister-0.139
 poster-0.133
Token game
Token ID983
Feature activation-1.72e-02

Pos logit contributions
ets+0.034
 textures+0.028
 They+0.027
 sizes+0.027
ness+0.026
Neg logit contributions
 babys-0.045
 stub-0.039
ister-0.038
fer-0.037
 salon-0.037
Token.
Token ID13
Feature activation+5.47e-02

Pos logit contributions
 babys+0.040
 salon+0.036
 stub+0.035
ister+0.035
 poster+0.034
Neg logit contributions
ets-0.019
 textures-0.016
 After-0.015
essing-0.015
lated-0.015
Token You
Token ID921
Feature activation+8.45e-02

Pos logit contributions
ets+0.075
 textures+0.060
ly+0.058
le+0.058
lated+0.056
Neg logit contributions
 babys-0.124
 stub-0.106
ister-0.102
 salon-0.100
 principal-0.098
Token are
Token ID389
Feature activation-9.34e-02

Pos logit contributions
ets+0.128
 textures+0.116
ly+0.110
 After+0.109
lated+0.109
Neg logit contributions
 babys-0.166
 stub-0.143
 salon-0.134
ister-0.134
 bumped-0.129
Token wasting
Token ID24430
Feature activation+2.33e-01

Pos logit contributions
 babys+0.165
 stub+0.137
 salon+0.129
ister+0.125
 nowhere+0.119
Neg logit contributions
ets-0.174
 They-0.149
 textures-0.148
essing-0.142
 sizes-0.141
Token your
Token ID534
Feature activation+1.07e-01

Pos logit contributions
ets+0.352
 They+0.291
 textures+0.287
essing+0.286
ly+0.279
Neg logit contributions
 babys-0.477
 stub-0.403
 salon-0.384
ister-0.376
 nowhere-0.373
Token time
Token ID640
Feature activation-3.49e-02

Pos logit contributions
ets+0.176
 textures+0.135
 They+0.133
 respect+0.129
 sizes+0.128
Neg logit contributions
 babys-0.225
 salon-0.197
 stub-0.197
ister-0.194
fer-0.189
Token."
Token ID526
Feature activation-3.99e-02

Pos logit contributions
 babys+0.085
 stub+0.075
 salon+0.073
ister+0.072
 poster+0.069
Neg logit contributions
ets-0.036
 textures-0.030
 They-0.029
essing-0.027
lated-0.027
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
 babys+0.084
 stub+0.073
 salon+0.073
fer+0.068
ister+0.067
Neg logit contributions
 They-0.056
ets-0.054
 until-0.048
 After-0.048
 respect-0.045
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
 babys+0.197
 stub+0.165
 salon+0.156
ister+0.152
fer+0.144
Neg logit contributions
ets-0.190
 They-0.163
 textures-0.159
essing-0.153
 sizes-0.153
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
 babys+0.089
ister+0.073
 salon+0.073
 stub+0.072
 nowhere+0.071
Neg logit contributions
ets-0.061
 After-0.052
 They-0.051
lated-0.051
 textures-0.050
Token cake
Token ID12187
Feature activation-7.28e-02

Pos logit contributions
 babys+0.034
 stub+0.029
 salon+0.028
ister+0.027
 nowhere+0.027
Neg logit contributions
ets-0.024
lated-0.019
 They-0.019
le-0.018
essing-0.018
Token with
Token ID351
Feature activation+5.29e-02

Pos logit contributions
 babys+0.146
ister+0.123
 salon+0.120
fer+0.114
 poster+0.114
Neg logit contributions
ets-0.100
lated-0.090
 After-0.088
ulously-0.083
ales-0.082
Token them
Token ID606
Feature activation-6.05e-02

Pos logit contributions
ets+0.085
lated+0.072
essing+0.069
 After+0.068
 They+0.067
Neg logit contributions
 babys-0.105
 stub-0.085
 nowhere-0.083
ister-0.079
 crying-0.076
Token.
Token ID13
Feature activation+3.79e-02

Pos logit contributions
 babys+0.119
 nowhere+0.097
ister+0.095
 stub+0.095
 crying+0.092
Neg logit contributions
ets-0.082
lated-0.079
ales-0.072
erve-0.071
 textures-0.070
Token Taking
Token ID20879
Feature activation+2.33e-01

Pos logit contributions
ets+0.065
ly+0.054
le+0.053
 textures+0.052
lated+0.051
Neg logit contributions
 babys-0.076
 stub-0.061
 nowhere-0.059
 salon-0.058
ister-0.058
Token things
Token ID1243
Feature activation+1.96e-02

Pos logit contributions
ets+0.333
 textures+0.299
 They+0.296
essing+0.294
lated+0.294
Neg logit contributions
 babys-0.443
 stub-0.373
 nowhere-0.358
 salon-0.343
 poster-0.342
Token that
Token ID326
Feature activation+9.97e-02

Pos logit contributions
ets+0.031
 textures+0.027
 They+0.026
 sizes+0.026
essing+0.026
Neg logit contributions
 babys-0.038
 stub-0.032
 salon-0.030
ister-0.030
 nowhere-0.029
Token do
Token ID466
Feature activation+2.33e-02

Pos logit contributions
ets+0.142
 They+0.118
 textures+0.115
 sizes+0.108
essing+0.108
Neg logit contributions
 babys-0.219
 stub-0.190
 salon-0.182
ister-0.177
fer-0.171
Token not
Token ID407
Feature activation-1.84e-03

Pos logit contributions
ets+0.038
ly+0.036
 textures+0.035
ished+0.034
lated+0.034
Neg logit contributions
 babys-0.039
 poster-0.032
 nowhere-0.032
 stub-0.032
ister-0.032
Token belong
Token ID5594
Feature activation+3.18e-02

Pos logit contributions
 babys+0.003
 stub+0.003
 nowhere+0.003
 crying+0.003
 bumped+0.002
Neg logit contributions
ets-0.003
ished-0.003
lated-0.003
hew-0.003
erve-0.003
Token always
Token ID1464
Feature activation+1.17e-01

Pos logit contributions
 babys+0.065
 stub+0.054
ister+0.051
 salon+0.050
 poster+0.047
Neg logit contributions
ets-0.068
 textures-0.059
 They-0.058
essing-0.058
 sizes-0.057
Token have
Token ID423
Feature activation+5.43e-02

Pos logit contributions
ets+0.190
 They+0.162
 textures+0.155
lated+0.154
essing+0.152
Neg logit contributions
 babys-0.228
 stub-0.195
 salon-0.181
ister-0.178
 poster-0.174
Token its
Token ID663
Feature activation+5.79e-02

Pos logit contributions
ets+0.093
 They+0.080
 textures+0.077
essing+0.077
lated+0.076
Neg logit contributions
 babys-0.100
 stub-0.087
 nowhere-0.079
 salon-0.078
ister-0.075
Token rewards
Token ID11530
Feature activation+3.55e-02

Pos logit contributions
ets+0.087
 They+0.076
lated+0.073
essing+0.069
ly+0.069
Neg logit contributions
 babys-0.118
 stub-0.103
 nowhere-0.093
 salon-0.092
ister-0.089
Token.
Token ID13
Feature activation+5.47e-02

Pos logit contributions
ets+0.042
 They+0.035
 textures+0.034
essing+0.032
lated+0.032
Neg logit contributions
 babys-0.082
 stub-0.072
 salon-0.070
ister-0.070
 nowhere-0.067
Token Taking
Token ID20879
Feature activation+2.32e-01

Pos logit contributions
ets+0.109
lated+0.091
wed+0.090
 textures+0.089
ly+0.087
Neg logit contributions
 babys-0.094
 stub-0.076
ister-0.071
-0.070
lyss-0.069
Token a
Token ID257
Feature activation-1.09e-02

Pos logit contributions
ets+0.361
 They+0.323
 textures+0.318
essing+0.316
lated+0.316
Neg logit contributions
 babys-0.412
 stub-0.368
 nowhere-0.344
 poster-0.325
 salon-0.323
Token break
Token ID2270
Feature activation+5.02e-02

Pos logit contributions
 babys+0.023
 salon+0.019
 stub+0.019
ister+0.019
fer+0.019
Neg logit contributions
ets-0.017
 until-0.013
 respect-0.013
 They-0.013
ly-0.013
Token is
Token ID318
Feature activation-8.92e-02

Pos logit contributions
ets+0.073
 textures+0.066
essing+0.065
lated+0.064
 They+0.063
Neg logit contributions
 babys-0.096
 stub-0.081
ister-0.080
 salon-0.078
 poster-0.074
Token important
Token ID1593
Feature activation+1.12e-01

Pos logit contributions
 babys+0.169
 stub+0.145
 nowhere+0.133
 salon+0.132
ister+0.132
Neg logit contributions
ets-0.146
 textures-0.125
 They-0.124
lated-0.120
 sizes-0.120
Token,
Token ID11
Feature activation-6.80e-02

Pos logit contributions
ets+0.175
lated+0.160
 They+0.151
ales+0.148
essing+0.146
Neg logit contributions
 babys-0.217
 stub-0.184
 salon-0.171
 poster-0.168
ister-0.167
Token asked
Token ID1965
Feature activation-7.93e-03

Pos logit contributions
 babys+0.062
 stub+0.056
 salon+0.055
ister+0.053
fer+0.053
Neg logit contributions
ets-0.031
 They-0.030
ly-0.028
le-0.026
en-0.024
Token.
Token ID13
Feature activation+2.64e-02

Pos logit contributions
 babys+0.022
 stub+0.019
 salon+0.019
ister+0.018
fer+0.018
Neg logit contributions
ets-0.007
 They-0.005
 textures-0.005
essing-0.004
 sizes-0.004
Token "
Token ID366
Feature activation-3.12e-02

Pos logit contributions
 They+0.034
 He+0.024
 But+0.024
 After+0.024
 until+0.023
Neg logit contributions
 babys-0.062
fer-0.062
 salon-0.061
ister-0.059
 stub-0.058
TokenYou
Token ID1639
Feature activation+9.91e-02

Pos logit contributions
 babys+0.064
 stub+0.055
 salon+0.052
ister+0.052
fer+0.048
Neg logit contributions
ets-0.046
 They-0.045
 textures-0.039
 respect-0.038
 After-0.037
Token are
Token ID389
Feature activation-9.49e-02

Pos logit contributions
ets+0.161
 textures+0.142
lated+0.138
 goals+0.136
 until+0.134
Neg logit contributions
 babys-0.195
 stub-0.165
 salon-0.149
 bumped-0.148
ister-0.148
Token wasting
Token ID24430
Feature activation+2.32e-01

Pos logit contributions
 babys+0.171
 stub+0.148
 salon+0.141
ister+0.135
fer+0.131
Neg logit contributions
ets-0.171
 They-0.150
 textures-0.141
essing-0.139
 sizes-0.137
Token the
Token ID262
Feature activation+5.17e-02

Pos logit contributions
ets+0.380
 They+0.313
essing+0.311
 textures+0.309
lated+0.303
Neg logit contributions
 babys-0.452
 stub-0.371
 salon-0.357
ister-0.351
 nowhere-0.344
Token food
Token ID2057
Feature activation+3.62e-03

Pos logit contributions
ets+0.087
 They+0.074
 textures+0.072
essing+0.070
 sizes+0.070
Neg logit contributions
 babys-0.101
 stub-0.084
 salon-0.079
ister-0.078
 poster-0.075
Token and
Token ID290
Feature activation+8.34e-03

Pos logit contributions
ets+0.004
 textures+0.003
 They+0.003
 After+0.003
essing+0.003
Neg logit contributions
 babys-0.008
ister-0.007
 stub-0.007
 salon-0.007
 poster-0.007
Token the
Token ID262
Feature activation+3.74e-02

Pos logit contributions
ets+0.015
 They+0.012
 textures+0.012
essing+0.012
le+0.012
Neg logit contributions
 babys-0.015
 stub-0.013
 salon-0.012
ister-0.012
 nowhere-0.012
Token energy
Token ID2568
Feature activation+4.81e-02

Pos logit contributions
ets+0.068
 They+0.057
 textures+0.055
essing+0.055
 sizes+0.054
Neg logit contributions
 babys-0.070
 stub-0.057
 salon-0.054
ister-0.052
 poster-0.050
Token no
Token ID645
Feature activation+3.33e-02

Pos logit contributions
ets+0.105
lated+0.087
le+0.085
 They+0.085
essing+0.084
Neg logit contributions
 babys-0.097
 stub-0.084
 salon-0.076
 nowhere-0.075
ister-0.074
Token one
Token ID530
Feature activation+4.17e-02

Pos logit contributions
ets+0.052
 They+0.045
 After+0.043
essing+0.042
lated+0.042
Neg logit contributions
 babys-0.068
 stub-0.061
 salon-0.056
 nowhere-0.054
 poster-0.053
Token is
Token ID318
Feature activation-9.26e-02

Pos logit contributions
ets+0.061
 They+0.052
 textures+0.051
lated+0.049
essing+0.049
Neg logit contributions
 babys-0.086
 stub-0.076
 salon-0.072
ister-0.069
 nowhere-0.068
Token watching
Token ID4964
Feature activation+6.89e-02

Pos logit contributions
 babys+0.152
 stub+0.131
 nowhere+0.118
 salon+0.113
 crying+0.111
Neg logit contributions
ets-0.181
 They-0.157
 textures-0.156
lated-0.153
 After-0.151
Token.
Token ID13
Feature activation+3.53e-02

Pos logit contributions
ets+0.108
 textures+0.090
 sizes+0.087
lated+0.087
 They+0.086
Neg logit contributions
 babys-0.138
 stub-0.116
ister-0.111
 salon-0.109
 nowhere-0.106
Token Taking
Token ID20879
Feature activation+2.32e-01

Pos logit contributions
ets+0.051
 textures+0.041
ly+0.039
 sizes+0.039
le+0.039
Neg logit contributions
 babys-0.078
 stub-0.067
 salon-0.064
ister-0.062
 nowhere-0.061
Token something
Token ID1223
Feature activation+1.58e-03

Pos logit contributions
ets+0.348
 They+0.322
 textures+0.314
lated+0.311
essing+0.308
Neg logit contributions
 babys-0.413
 stub-0.365
 nowhere-0.338
 poster-0.329
 salon-0.324
Token that
Token ID326
Feature activation+8.63e-02

Pos logit contributions
ets+0.003
 textures+0.002
bit+0.002
 They+0.002
 sizes+0.002
Neg logit contributions
 babys-0.003
 stub-0.003
 salon-0.002
ister-0.002
 crying-0.002
Token doesn
Token ID1595
Feature activation-3.50e-02

Pos logit contributions
ets+0.119
 They+0.095
 textures+0.095
essing+0.091
lated+0.090
Neg logit contributions
 babys-0.187
 stub-0.163
 salon-0.155
ister-0.154
 poster-0.149
Token't
Token ID470
Feature activation-2.00e-02

Pos logit contributions
 babys+0.035
 stub+0.025
 salon+0.022
fer+0.019
ister+0.018
Neg logit contributions
ets-0.091
 They-0.084
 until-0.080
 textures-0.080
ly-0.079
Token belong
Token ID5594
Feature activation+3.06e-02

Pos logit contributions
 babys+0.037
 stub+0.032
 nowhere+0.030
 salon+0.028
ister+0.028
Neg logit contributions
ets-0.033
ished-0.028
 After-0.028
 goals-0.028
lated-0.027
Token suggested
Token ID5220
Feature activation-2.07e-02

Pos logit contributions
 babys+0.082
 stub+0.066
 salon+0.061
ister+0.060
 bumped+0.055
Neg logit contributions
ets-0.100
 textures-0.087
 They-0.085
 sizes-0.084
 goals-0.083
Token.
Token ID13
Feature activation+2.72e-02

Pos logit contributions
 babys+0.049
ister+0.040
 stub+0.040
 crying+0.039
 salon+0.039
Neg logit contributions
ets-0.028
 textures-0.022
ws-0.022
bit-0.021
 sizes-0.021
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
ets+0.040
 They+0.036
 After+0.032
 textures+0.032
 until+0.032
Neg logit contributions
 babys-0.058
 stub-0.050
 salon-0.049
ister-0.047
fer-0.045
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
 babys+0.233
 stub+0.197
 salon+0.197
fer+0.180
ister+0.176
Neg logit contributions
ets-0.157
 They-0.148
 After-0.134
 until-0.130
 respect-0.124
TokenWithout
Token ID16249
Feature activation+7.89e-02

Pos logit contributions
 babys+0.180
 stub+0.154
ister+0.146
 salon+0.143
fer+0.137
Neg logit contributions
ets-0.185
 textures-0.159
 They-0.153
ly-0.152
 sizes-0.151
Token wasting
Token ID24430
Feature activation+2.31e-01

Pos logit contributions
ets+0.180
 They+0.157
 textures+0.155
essing+0.153
le+0.151
Neg logit contributions
 babys-0.107
 stub-0.084
 salon-0.075
ister-0.072
 nowhere-0.071
Token any
Token ID597
Feature activation+1.23e-01

Pos logit contributions
ets+0.384
essing+0.310
ly+0.310
 textures+0.308
le+0.304
Neg logit contributions
 babys-0.444
 stub-0.369
ister-0.349
 nowhere-0.348
 salon-0.346
Token time
Token ID640
Feature activation-2.46e-02

Pos logit contributions
ets+0.211
 They+0.183
 textures+0.176
essing+0.173
 sizes+0.171
Neg logit contributions
 babys-0.234
 stub-0.197
 salon-0.186
ister-0.181
 poster-0.174
Token,
Token ID11
Feature activation-5.33e-02

Pos logit contributions
 babys+0.043
 stub+0.036
 nowhere+0.034
ister+0.033
 salon+0.032
Neg logit contributions
ets-0.044
 textures-0.039
essing-0.038
ws-0.037
le-0.037
Token they
Token ID484
Feature activation+5.73e-02

Pos logit contributions
 babys+0.084
 stub+0.072
 nowhere+0.068
ister+0.065
fer+0.064
Neg logit contributions
ets-0.104
 textures-0.088
ly-0.086
le-0.086
essing-0.085
Token went
Token ID1816
Feature activation-2.14e-02

Pos logit contributions
ets+0.095
 They+0.080
 textures+0.079
essing+0.076
 sizes+0.076
Neg logit contributions
 babys-0.113
 stub-0.096
 salon-0.091
ister-0.089
 nowhere-0.085
Token happened
Token ID3022
Feature activation-5.20e-02

Pos logit contributions
 babys+0.042
 stub+0.037
 salon+0.035
ister+0.035
 bumped+0.034
Neg logit contributions
ets-0.020
 After-0.017
 textures-0.017
essing-0.016
 They-0.016
Token.
Token ID13
Feature activation+4.55e-02

Pos logit contributions
 babys+0.124
 stub+0.111
 salon+0.104
 nowhere+0.103
ister+0.102
Neg logit contributions
ets-0.059
 textures-0.049
lated-0.045
 They-0.045
essing-0.043
Token The
Token ID383
Feature activation+1.26e-01

Pos logit contributions
ets+0.068
 textures+0.054
ly+0.052
le+0.052
 sizes+0.051
Neg logit contributions
 babys-0.102
 stub-0.086
 salon-0.082
 nowhere-0.080
ister-0.079
Token fridge
Token ID25772
Feature activation-9.09e-02

Pos logit contributions
ets+0.228
 They+0.193
 textures+0.190
essing+0.185
 sizes+0.183
Neg logit contributions
 babys-0.232
 stub-0.192
 salon-0.182
ister-0.176
 poster-0.168
Token was
Token ID373
Feature activation-9.92e-02

Pos logit contributions
 babys+0.172
 stub+0.144
 salon+0.137
ister+0.134
fer+0.129
Neg logit contributions
ets-0.156
 They-0.133
 textures-0.129
ly-0.126
essing-0.124
Token wasting
Token ID24430
Feature activation+2.31e-01

Pos logit contributions
 babys+0.188
 stub+0.159
 salon+0.153
ister+0.151
fer+0.146
Neg logit contributions
ets-0.169
 They-0.144
 textures-0.140
 until-0.137
 sizes-0.135
Token a
Token ID257
Feature activation+5.20e-04

Pos logit contributions
ets+0.370
essing+0.311
 textures+0.300
 They+0.294
ly+0.292
Neg logit contributions
 babys-0.459
 stub-0.380
 nowhere-0.357
 salon-0.352
ister-0.349
Token lot
Token ID1256
Feature activation+3.85e-02

Pos logit contributions
ets+0.001
 They+0.001
 until+0.001
 textures+0.001
ly+0.001
Neg logit contributions
 babys-0.001
 stub-0.001
 salon-0.001
ister-0.001
fer-0.001
Token of
Token ID286
Feature activation+7.48e-02

Pos logit contributions
ets+0.053
 textures+0.051
essing+0.050
 goals+0.050
bit+0.049
Neg logit contributions
 babys-0.077
ister-0.063
 stub-0.059
 salon-0.059
stand-0.058
Token energy
Token ID2568
Feature activation+5.05e-02

Pos logit contributions
ets+0.134
essing+0.114
bit+0.110
ales+0.110
angles+0.109
Neg logit contributions
 babys-0.141
 stub-0.110
 nowhere-0.102
 crying-0.100
 bumped-0.099
Token and
Token ID290
Feature activation-5.45e-03

Pos logit contributions
ets+0.063
 textures+0.052
essing+0.050
 They+0.050
 After+0.048
Neg logit contributions
 babys-0.117
 stub-0.102
 salon-0.099
ister-0.096
 nowhere-0.093
Token a
Token ID257
Feature activation-7.33e-02

Pos logit contributions
 babys+0.263
 salon+0.226
 stub+0.225
ister+0.223
fer+0.217
Neg logit contributions
ets-0.163
 They-0.154
 textures-0.139
 until-0.137
 After-0.135
Token big
Token ID1263
Feature activation+2.01e-02

Pos logit contributions
 babys+0.165
 stub+0.145
 salon+0.140
ister+0.136
fer+0.134
Neg logit contributions
ets-0.089
 They-0.079
 textures-0.072
 until-0.070
ly-0.069
Token bird
Token ID6512
Feature activation-1.44e-01

Pos logit contributions
ets+0.035
 They+0.030
 textures+0.029
essing+0.028
 sizes+0.028
Neg logit contributions
 babys-0.038
 stub-0.032
 salon-0.030
ister-0.030
fer-0.028
Token called
Token ID1444
Feature activation-7.87e-02

Pos logit contributions
 babys+0.283
 stub+0.245
 salon+0.229
ister+0.224
 nowhere+0.214
Neg logit contributions
ets-0.238
 textures-0.198
 They-0.197
essing-0.189
 sizes-0.189
Token an
Token ID281
Feature activation-7.25e-02

Pos logit contributions
 babys+0.162
 stub+0.139
 salon+0.133
ister+0.129
fer+0.124
Neg logit contributions
ets-0.122
 They-0.104
 textures-0.100
essing-0.096
 sizes-0.095
Token ostr
Token ID42387
Feature activation-1.99e-01

Pos logit contributions
 babys+0.143
 stub+0.123
 salon+0.116
ister+0.113
fer+0.109
Neg logit contributions
ets-0.118
 They-0.100
 textures-0.098
essing-0.094
ly-0.093
Tokenich
Token ID488
Feature activation-1.35e-01

Pos logit contributions
 babys+0.202
 stub+0.144
 salon+0.127
 principal+0.109
 nowhere+0.107
Neg logit contributions
ets-0.486
essing-0.439
 They-0.437
ly-0.433
 until-0.429
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
 babys+0.305
 stub+0.267
ister+0.247
 salon+0.247
 nowhere+0.241
Neg logit contributions
ets-0.192
 textures-0.153
lated-0.145
 sizes-0.143
ws-0.142
Token It
Token ID632
Feature activation+2.44e-02

Pos logit contributions
ets+0.030
le+0.023
ly+0.022
lated+0.021
wed+0.021
Neg logit contributions
 babys-0.049
 stub-0.043
ister-0.040
 salon-0.040
 nowhere-0.039
Token had
Token ID550
Feature activation+1.00e-02

Pos logit contributions
ets+0.033
 They+0.028
 textures+0.027
 sizes+0.025
essing+0.025
Neg logit contributions
 babys-0.055
 stub-0.047
 salon-0.046
ister-0.045
fer-0.043
Token long
Token ID890
Feature activation+1.43e-01

Pos logit contributions
ets+0.014
 They+0.012
 textures+0.012
 respect+0.011
 sizes+0.011
Neg logit contributions
 babys-0.022
 stub-0.019
 salon-0.018
ister-0.018
fer-0.018
Token she
Token ID673
Feature activation+7.79e-02

Pos logit contributions
 babys+0.133
 stub+0.111
 salon+0.104
 nowhere+0.096
ister+0.096
Neg logit contributions
ets-0.143
 textures-0.118
essing-0.117
ales-0.116
 They-0.115
Token left
Token ID1364
Feature activation+7.25e-02

Pos logit contributions
ets+0.119
 They+0.101
ly+0.094
 textures+0.094
essing+0.092
Neg logit contributions
 babys-0.159
 stub-0.134
 salon-0.131
ister-0.131
 poster-0.126
Token Lily
Token ID20037
Feature activation+3.24e-02

Pos logit contributions
ets+0.108
 They+0.100
 until+0.095
 textures+0.090
 After+0.088
Neg logit contributions
 babys-0.144
 stub-0.130
ister-0.123
fer-0.123
 salon-0.123
Token with
Token ID351
Feature activation+4.44e-02

Pos logit contributions
ets+0.050
 They+0.042
 textures+0.041
essing+0.039
ly+0.039
Neg logit contributions
 babys-0.067
 stub-0.057
 salon-0.054
ister-0.054
fer-0.051
Token her
Token ID607
Feature activation-1.50e-02

Pos logit contributions
ets+0.067
 They+0.060
 textures+0.057
 respect+0.055
 until+0.055
Neg logit contributions
 babys-0.088
 stub-0.077
fer-0.076
ister-0.075
 salon-0.074
Token babys
Token ID46711
Feature activation-1.98e-01

Pos logit contributions
 babys+0.030
 stub+0.027
ister+0.026
fer+0.026
 salon+0.025
Neg logit contributions
ets-0.021
 textures-0.019
 They-0.018
 until-0.018
 goals-0.017
Tokenitter
Token ID1967
Feature activation-8.45e-02

Pos logit contributions
 babys+0.305
 stub+0.286
 nowhere+0.260
 poster+0.252
chard+0.245
Neg logit contributions
ets-0.389
ly-0.328
essing-0.326
 They-0.321
 textures-0.305
Token.
Token ID13
Feature activation+1.99e-02

Pos logit contributions
 babys+0.209
 stub+0.183
 salon+0.177
ister+0.173
 poster+0.166
Neg logit contributions
ets-0.098
 They-0.076
 textures-0.074
essing-0.069
 sizes-0.069
Token
Token ID220
Feature activation-1.22e-01

Pos logit contributions
 They+0.026
ets+0.025
 After+0.023
 until+0.021
 But+0.020
Neg logit contributions
 babys-0.043
fer-0.039
 stub-0.039
ister-0.039
 salon-0.038
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
 babys+0.259
 stub+0.225
 salon+0.220
fer+0.216
 poster+0.209
Neg logit contributions
ets-0.176
 They-0.170
 After-0.150
 until-0.146
essing-0.140
Token
Token ID198
Feature activation-9.78e-02

Pos logit contributions
 babys+0.220
 stub+0.187
 salon+0.182
fer+0.179
ister+0.177
Neg logit contributions
ets-0.144
 They-0.138
 After-0.123
 until-0.123
 textures-0.112
Token a
Token ID257
Feature activation-7.13e-02

Pos logit contributions
 babys+0.244
 stub+0.207
 salon+0.205
ister+0.201
fer+0.194
Neg logit contributions
ets-0.171
 They-0.156
 textures-0.145
 until-0.140
 After-0.140
Token big
Token ID1263
Feature activation+2.38e-02

Pos logit contributions
 babys+0.159
 stub+0.139
 salon+0.134
ister+0.130
fer+0.127
Neg logit contributions
ets-0.091
 They-0.079
 textures-0.074
 until-0.071
ly-0.070
Token bird
Token ID6512
Feature activation-1.42e-01

Pos logit contributions
ets+0.041
 They+0.035
 textures+0.034
essing+0.033
 sizes+0.032
Neg logit contributions
 babys-0.045
 stub-0.038
 salon-0.036
ister-0.035
fer-0.034
Token called
Token ID1444
Feature activation-7.56e-02

Pos logit contributions
 babys+0.276
 stub+0.238
 salon+0.222
ister+0.218
 nowhere+0.208
Neg logit contributions
ets-0.239
 textures-0.198
 They-0.198
essing-0.190
 sizes-0.190
Token an
Token ID281
Feature activation-7.13e-02

Pos logit contributions
 babys+0.154
 stub+0.132
 salon+0.125
ister+0.122
fer+0.117
Neg logit contributions
ets-0.120
 They-0.101
 textures-0.098
essing-0.094
 sizes-0.093
Token ostr
Token ID42387
Feature activation-1.98e-01

Pos logit contributions
 babys+0.141
 stub+0.121
 salon+0.115
ister+0.111
fer+0.108
Neg logit contributions
ets-0.115
 They-0.098
 textures-0.097
ly-0.093
essing-0.093
Tokenich
Token ID488
Feature activation-1.33e-01

Pos logit contributions
 babys+0.219
 stub+0.151
 salon+0.136
 principal+0.128
stand+0.119
Neg logit contributions
ets-0.463
essing-0.422
ly-0.414
le-0.413
bit-0.411
Token.
Token ID13
Feature activation+2.77e-02

Pos logit contributions
 babys+0.301
 stub+0.263
ister+0.246
 salon+0.243
 nowhere+0.239
Neg logit contributions
ets-0.191
 textures-0.150
lated-0.142
ws-0.141
 sizes-0.140
Token He
Token ID679
Feature activation+1.43e-01

Pos logit contributions
ets+0.039
le+0.029
ly+0.028
lated+0.027
wed+0.027
Neg logit contributions
 babys-0.063
 stub-0.055
ister-0.052
 salon-0.051
 nowhere-0.050
Token was
Token ID373
Feature activation-1.19e-01

Pos logit contributions
ets+0.142
 They+0.116
 textures+0.107
 sizes+0.098
 likes+0.098
Neg logit contributions
 babys-0.374
 salon-0.326
 stub-0.318
ister-0.316
 principal-0.307
Token very
Token ID845
Feature activation-1.07e-01

Pos logit contributions
 babys+0.227
 salon+0.191
 stub+0.187
ister+0.184
fer+0.180
Neg logit contributions
ets-0.196
 They-0.181
 textures-0.167
 until-0.164
 sizes-0.162
Token and
Token ID290
Feature activation-9.99e-03

Pos logit contributions
ets+0.068
 They+0.050
 until+0.049
ly+0.047
 textures+0.046
Neg logit contributions
 babys-0.150
 stub-0.133
ister-0.125
 salon-0.124
fer-0.123
Token left
Token ID1364
Feature activation+6.64e-02

Pos logit contributions
 babys+0.019
ister+0.017
 stub+0.016
fer+0.015
 salon+0.015
Neg logit contributions
ets-0.016
 They-0.014
 until-0.013
 After-0.013
ly-0.013
Token her
Token ID607
Feature activation-8.56e-03

Pos logit contributions
ets+0.107
 They+0.092
 textures+0.088
 until+0.086
ly+0.084
Neg logit contributions
 babys-0.131
 stub-0.114
 salon-0.107
ister-0.106
fer-0.103
Token with
Token ID351
Feature activation+4.61e-02

Pos logit contributions
 babys+0.016
 stub+0.013
ister+0.013
 salon+0.013
fer+0.012
Neg logit contributions
ets-0.015
 They-0.013
 textures-0.012
essing-0.012
ly-0.012
Token her
Token ID607
Feature activation-1.40e-02

Pos logit contributions
ets+0.071
 They+0.061
 textures+0.060
 until+0.057
 respect+0.057
Neg logit contributions
 babys-0.092
 stub-0.080
ister-0.077
 salon-0.075
fer-0.075
Token babys
Token ID46711
Feature activation-1.97e-01

Pos logit contributions
 babys+0.027
 stub+0.022
 salon+0.021
ister+0.021
 poster+0.020
Neg logit contributions
ets-0.024
 They-0.020
 textures-0.020
essing-0.019
 sizes-0.019
Tokenitter
Token ID1967
Feature activation-8.44e-02

Pos logit contributions
 babys+0.297
 stub+0.271
 nowhere+0.243
 poster+0.231
chard+0.226
Neg logit contributions
ets-0.400
ly-0.339
essing-0.336
 They-0.333
 textures-0.323
Token,
Token ID11
Feature activation-7.82e-02

Pos logit contributions
 babys+0.205
 stub+0.177
 salon+0.173
ister+0.167
 principal+0.161
Neg logit contributions
ets-0.103
 They-0.081
 textures-0.080
essing-0.075
 sizes-0.075
Token Sarah
Token ID10490
Feature activation+2.83e-02

Pos logit contributions
 babys+0.135
 stub+0.113
ister+0.109
 salon+0.107
fer+0.102
Neg logit contributions
ets-0.141
 They-0.126
 until-0.120
 textures-0.119
 After-0.116
Token.
Token ID13
Feature activation+3.56e-02

Pos logit contributions
ets+0.048
 They+0.041
 textures+0.039
ly+0.038
 until+0.038
Neg logit contributions
 babys-0.054
 stub-0.045
 salon-0.043
ister-0.043
 poster-0.041
Token Sarah
Token ID10490
Feature activation+4.52e-02

Pos logit contributions
ets+0.048
 textures+0.038
 They+0.037
le+0.036
 sizes+0.036
Neg logit contributions
 babys-0.082
 stub-0.071
 salon-0.067
ister-0.065
 nowhere-0.063
Token a
Token ID257
Feature activation-6.98e-02

Pos logit contributions
 babys+0.256
 salon+0.220
ister+0.218
 stub+0.216
fer+0.210
Neg logit contributions
ets-0.157
 They-0.148
 until-0.133
 textures-0.132
 After-0.129
Token big
Token ID1263
Feature activation+2.24e-02

Pos logit contributions
 babys+0.158
 stub+0.139
 salon+0.134
ister+0.131
fer+0.128
Neg logit contributions
ets-0.085
 They-0.074
 textures-0.069
 until-0.066
ly-0.065
Token bird
Token ID6512
Feature activation-1.38e-01

Pos logit contributions
ets+0.038
 They+0.032
 textures+0.032
essing+0.030
ly+0.030
Neg logit contributions
 babys-0.043
 stub-0.036
 salon-0.034
ister-0.033
fer-0.032
Token called
Token ID1444
Feature activation-7.54e-02

Pos logit contributions
 babys+0.274
 stub+0.237
 salon+0.222
ister+0.217
 nowhere+0.207
Neg logit contributions
ets-0.228
 They-0.189
 textures-0.189
essing-0.180
 sizes-0.180
Token an
Token ID281
Feature activation-7.38e-02

Pos logit contributions
 babys+0.153
 stub+0.131
 salon+0.125
ister+0.121
fer+0.116
Neg logit contributions
ets-0.119
 They-0.102
 textures-0.098
essing-0.094
 sizes-0.093
Token ostr
Token ID42387
Feature activation-1.96e-01

Pos logit contributions
 babys+0.142
 stub+0.121
 salon+0.115
ister+0.111
fer+0.107
Neg logit contributions
ets-0.123
 They-0.105
 textures-0.104
essing-0.100
ly-0.099
Tokenich
Token ID488
Feature activation-1.35e-01

Pos logit contributions
 babys+0.216
 stub+0.165
 salon+0.134
 nowhere+0.129
Re+0.126
Neg logit contributions
ets-0.449
essing-0.409
ly-0.399
 until-0.398
bit-0.397
Token.
Token ID13
Feature activation+2.36e-02

Pos logit contributions
 babys+0.309
 stub+0.268
ister+0.253
 salon+0.251
 nowhere+0.243
Neg logit contributions
ets-0.190
 textures-0.149
lated-0.140
 sizes-0.139
ws-0.138
Token The
Token ID383
Feature activation+1.04e-01

Pos logit contributions
ets+0.034
le+0.026
ly+0.024
wed+0.024
lated+0.024
Neg logit contributions
 babys-0.053
 stub-0.046
ister-0.044
 salon-0.043
 nowhere-0.042
Token ostr
Token ID42387
Feature activation-1.56e-01

Pos logit contributions
ets+0.158
 They+0.148
 textures+0.141
 until+0.136
 respect+0.136
Neg logit contributions
 babys-0.201
 stub-0.173
 salon-0.170
fer-0.167
ister-0.160
Tokenich
Token ID488
Feature activation-8.48e-02

Pos logit contributions
 babys+0.169
 stub+0.129
 salon+0.104
 nowhere+0.095
 principal+0.094
Neg logit contributions
ets-0.371
essing-0.337
 They-0.334
ires-0.328
 until-0.327
Token a
Token ID257
Feature activation-5.73e-02

Pos logit contributions
 babys+0.117
 stub+0.098
 salon+0.096
ister+0.092
 principal+0.088
Neg logit contributions
ets-0.097
 They-0.085
 textures-0.081
essing-0.078
 until-0.077
Token big
Token ID1263
Feature activation+3.42e-02

Pos logit contributions
 babys+0.127
 stub+0.110
 salon+0.107
ister+0.103
fer+0.101
Neg logit contributions
ets-0.077
 They-0.066
 textures-0.062
ly-0.059
essing-0.059
Token bird
Token ID6512
Feature activation-1.34e-01

Pos logit contributions
ets+0.057
 They+0.051
 textures+0.048
ly+0.047
ness+0.046
Neg logit contributions
 babys-0.063
 stub-0.054
 salon-0.050
fer-0.049
ister-0.048
Token called
Token ID1444
Feature activation-6.81e-02

Pos logit contributions
 babys+0.270
 salon+0.222
 stub+0.220
ister+0.213
 principal+0.208
Neg logit contributions
ets-0.217
 They-0.186
 textures-0.176
le-0.175
ly-0.174
Token an
Token ID281
Feature activation-6.57e-02

Pos logit contributions
 babys+0.146
 stub+0.125
 salon+0.124
ister+0.117
fer+0.114
Neg logit contributions
ets-0.098
 They-0.089
 textures-0.082
 respect-0.079
essing-0.078
Token ostr
Token ID42387
Feature activation-1.96e-01

Pos logit contributions
 babys+0.137
 stub+0.120
 salon+0.114
fer+0.110
ister+0.109
Neg logit contributions
ets-0.096
 textures-0.082
 They-0.081
ly-0.079
essing-0.077
Tokenich
Token ID488
Feature activation-1.33e-01

Pos logit contributions
 babys+0.212
 stub+0.163
 salon+0.139
 principal+0.134
 nowhere+0.131
Neg logit contributions
ets-0.447
essing-0.409
ly-0.403
 They-0.403
le-0.397
Token was
Token ID373
Feature activation-1.50e-01

Pos logit contributions
 babys+0.264
 stub+0.225
 salon+0.214
ister+0.208
fer+0.199
Neg logit contributions
ets-0.216
 They-0.182
 textures-0.178
essing-0.171
 sizes-0.170
Token walking
Token ID6155
Feature activation+5.54e-02

Pos logit contributions
 babys+0.237
 salon+0.193
ister+0.189
 principal+0.184
fer+0.184
Neg logit contributions
ets-0.290
 They-0.265
 for-0.252
 until-0.250
 often-0.245
Token in
Token ID287
Feature activation+5.14e-02

Pos logit contributions
ets+0.111
lated+0.096
 sizes+0.093
essing+0.093
angles+0.092
Neg logit contributions
 babys-0.084
 stub-0.075
 nowhere-0.067
chard-0.063
 crying-0.062
Token the
Token ID262
Feature activation+2.75e-02

Pos logit contributions
ets+0.074
 They+0.064
 textures+0.061
 until+0.058
 sizes+0.058
Neg logit contributions
 babys-0.111
 stub-0.096
 salon-0.092
ister-0.089
fer-0.087
Token a
Token ID257
Feature activation-6.92e-02

Pos logit contributions
 babys+0.243
 stub+0.206
 salon+0.205
ister+0.201
fer+0.195
Neg logit contributions
ets-0.167
 They-0.152
 textures-0.139
 until-0.137
 After-0.135
Token big
Token ID1263
Feature activation+2.27e-02

Pos logit contributions
 babys+0.158
 stub+0.140
 salon+0.135
ister+0.131
 nowhere+0.129
Neg logit contributions
ets-0.082
 They-0.072
 textures-0.066
 until-0.064
ly-0.063
Token bird
Token ID6512
Feature activation-1.40e-01

Pos logit contributions
ets+0.039
 They+0.033
 textures+0.032
essing+0.031
ly+0.031
Neg logit contributions
 babys-0.043
 stub-0.037
 salon-0.034
ister-0.033
fer-0.032
Token called
Token ID1444
Feature activation-7.57e-02

Pos logit contributions
 babys+0.271
 stub+0.232
 salon+0.218
ister+0.213
 nowhere+0.202
Neg logit contributions
ets-0.236
 They-0.198
 textures-0.197
essing-0.188
 sizes-0.188
Token an
Token ID281
Feature activation-7.10e-02

Pos logit contributions
 babys+0.158
 stub+0.136
 salon+0.131
ister+0.126
fer+0.122
Neg logit contributions
ets-0.114
 They-0.099
 textures-0.094
essing-0.090
 until-0.089
Token ostr
Token ID42387
Feature activation-1.96e-01

Pos logit contributions
 babys+0.137
 stub+0.116
 salon+0.110
ister+0.107
fer+0.103
Neg logit contributions
ets-0.119
 They-0.101
 textures-0.100
essing-0.096
ly-0.095
Tokenich
Token ID488
Feature activation-1.33e-01

Pos logit contributions
 babys+0.208
 stub+0.156
 salon+0.128
 nowhere+0.121
 principal+0.119
Neg logit contributions
ets-0.457
essing-0.417
 They-0.409
ly-0.407
 until-0.405
Token.
Token ID13
Feature activation+2.14e-02

Pos logit contributions
 babys+0.293
 stub+0.256
ister+0.237
 salon+0.236
 nowhere+0.229
Neg logit contributions
ets-0.198
 textures-0.160
lated-0.151
 sizes-0.150
essing-0.148
Token The
Token ID383
Feature activation+1.04e-01

Pos logit contributions
ets+0.031
le+0.023
wed+0.022
essing+0.022
lated+0.022
Neg logit contributions
 babys-0.049
 stub-0.042
ister-0.040
 salon-0.039
 nowhere-0.038
Token ostr
Token ID42387
Feature activation-1.56e-01

Pos logit contributions
ets+0.165
 They+0.152
 textures+0.146
 until+0.141
 respect+0.140
Neg logit contributions
 babys-0.195
 stub-0.167
 salon-0.163
fer-0.158
ister-0.154
Tokenich
Token ID488
Feature activation-8.61e-02

Pos logit contributions
 babys+0.164
 stub+0.124
 salon+0.100
 principal+0.090
 nowhere+0.090
Neg logit contributions
ets-0.378
essing-0.343
 They-0.343
 until-0.334
ires-0.332
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
ets+0.044
 They+0.038
 textures+0.037
essing+0.035
 sizes+0.035
Neg logit contributions
 babys-0.053
 stub-0.045
 salon-0.043
ister-0.042
fer-0.040
Token
Token ID198
Feature activation-9.66e-02

Pos logit contributions
 babys+0.223
 salon+0.189
 stub+0.186
fer+0.179
 principal+0.172
Neg logit contributions
ets-0.143
 They-0.137
 until-0.119
 After-0.118
le-0.113
TokenTim
Token ID14967
Feature activation+3.18e-02

Pos logit contributions
 babys+0.166
 stub+0.137
ister+0.130
 salon+0.124
 nowhere+0.117
Neg logit contributions
ets-0.187
 textures-0.157
 goals-0.153
essing-0.153
ly-0.151
Token asked
Token ID1965
Feature activation+6.72e-05

Pos logit contributions
ets+0.062
 textures+0.055
 sizes+0.052
 goals+0.052
lated+0.052
Neg logit contributions
 babys-0.051
 stub-0.044
 salon-0.039
 bumped-0.038
 nowhere-0.038
Token a
Token ID257
Feature activation-8.14e-02

Pos logit contributions
ets+0.000
 They+0.000
 textures+0.000
essing+0.000
 until+0.000
Neg logit contributions
 babys-0.000
 stub-0.000
 salon-0.000
ister-0.000
fer-0.000
Token man
Token ID582
Feature activation-1.93e-01

Pos logit contributions
 babys+0.178
 stub+0.166
 salon+0.162
 nowhere+0.157
fer+0.151
Neg logit contributions
 They-0.093
ets-0.087
 textures-0.079
 respect-0.078
ly-0.071
Token,
Token ID11
Feature activation-1.01e-01

Pos logit contributions
 babys+0.434
 stub+0.369
 salon+0.358
ister+0.351
 poster+0.338
Neg logit contributions
ets-0.270
 textures-0.216
 They-0.209
 sizes-0.206
essing-0.198
Token "
Token ID366
Feature activation-4.49e-02

Pos logit contributions
 babys+0.222
 stub+0.200
 salon+0.195
ister+0.184
fer+0.182
Neg logit contributions
 They-0.126
ets-0.124
 until-0.110
 for-0.108
 respect-0.107
TokenCan
Token ID6090
Feature activation+9.63e-05

Pos logit contributions
 babys+0.088
 stub+0.078
ister+0.071
 salon+0.069
fer+0.067
Neg logit contributions
ets-0.067
 They-0.064
ly-0.059
 respect-0.059
 until-0.058
Token I
Token ID314
Feature activation+1.71e-02

Pos logit contributions
ets+0.000
 They+0.000
 respect+0.000
 textures+0.000
ly+0.000
Neg logit contributions
 babys-0.000
 stub-0.000
 salon-0.000
fer-0.000
ister-0.000
Token go
Token ID467
Feature activation-3.98e-02

Pos logit contributions
ets+0.025
 They+0.021
 textures+0.020
essing+0.019
 sizes+0.019
Neg logit contributions
 babys-0.037
 stub-0.032
 salon-0.030
ister-0.030
fer-0.028
Token so
Token ID523
Feature activation-8.57e-02

Pos logit contributions
 babys+0.168
 stub+0.145
 salon+0.139
ister+0.133
 nowhere+0.130
Neg logit contributions
ets-0.128
 textures-0.104
 They-0.102
essing-0.100
lated-0.099
Token they
Token ID484
Feature activation+4.56e-02

Pos logit contributions
 babys+0.137
 stub+0.118
 salon+0.104
ister+0.102
 nowhere+0.100
Neg logit contributions
ets-0.179
ales-0.152
lated-0.149
wed-0.149
essing-0.147
Token asked
Token ID1965
Feature activation-3.40e-03

Pos logit contributions
ets+0.072
 textures+0.061
 They+0.060
 goals+0.059
 sizes+0.059
Neg logit contributions
 babys-0.091
 stub-0.080
 salon-0.074
ister-0.072
 bumped-0.070
Token a
Token ID257
Feature activation-7.76e-02

Pos logit contributions
 babys+0.006
 stub+0.005
 salon+0.005
 nowhere+0.004
ister+0.004
Neg logit contributions
ets-0.006
 sizes-0.005
 textures-0.005
lated-0.005
bit-0.005
Token kind
Token ID1611
Feature activation+2.19e-02

Pos logit contributions
 babys+0.154
 stub+0.141
 salon+0.134
 nowhere+0.133
fer+0.131
Neg logit contributions
ets-0.101
 They-0.099
 respect-0.089
 textures-0.088
 until-0.087
Token man
Token ID582
Feature activation-1.92e-01

Pos logit contributions
ets+0.044
 textures+0.037
 They+0.037
 sizes+0.037
essing+0.036
Neg logit contributions
 babys-0.037
 stub-0.029
 salon-0.028
ister-0.028
 poster-0.026
Token to
Token ID284
Feature activation-1.08e-01

Pos logit contributions
 babys+0.401
 salon+0.328
 stub+0.319
ister+0.307
 principal+0.305
Neg logit contributions
ets-0.289
 textures-0.259
lated-0.250
 sizes-0.241
 goals-0.236
Token help
Token ID1037
Feature activation-5.33e-03

Pos logit contributions
 babys+0.222
 stub+0.189
 salon+0.180
ister+0.176
 poster+0.168
Neg logit contributions
ets-0.170
 They-0.141
 textures-0.139
essing-0.133
 sizes-0.133
Token them
Token ID606
Feature activation-8.66e-02

Pos logit contributions
 babys+0.012
 stub+0.010
ister+0.009
 salon+0.009
 nowhere+0.009
Neg logit contributions
ets-0.008
 textures-0.006
 sizes-0.006
 goals-0.006
lated-0.006
Token.
Token ID13
Feature activation+2.81e-02

Pos logit contributions
 babys+0.184
 stub+0.155
 salon+0.152
ister+0.149
 poster+0.141
Neg logit contributions
ets-0.127
lated-0.103
ly-0.098
 sizes-0.097
 textures-0.095
Token The
Token ID383
Feature activation+1.14e-01

Pos logit contributions
ets+0.054
 textures+0.046
essing+0.044
 sizes+0.044
wed+0.044
Neg logit contributions
 babys-0.050
 stub-0.039
 salon-0.038
 nowhere-0.036
ister-0.035
Token know
Token ID760
Feature activation+2.71e-03

Pos logit contributions
ets+0.139
lated+0.122
essing+0.121
 textures+0.120
ales+0.118
Neg logit contributions
 babys-0.146
 stub-0.126
 salon-0.119
ister-0.115
 bumped-0.111
Token,
Token ID11
Feature activation-6.90e-02

Pos logit contributions
ets+0.004
 They+0.004
 textures+0.004
bit+0.003
essing+0.003
Neg logit contributions
 babys-0.005
 salon-0.005
ister-0.004
 stub-0.004
 nowhere-0.004
Token her
Token ID607
Feature activation-1.09e-02

Pos logit contributions
 babys+0.135
 stub+0.115
 salon+0.113
ister+0.107
 nowhere+0.104
Neg logit contributions
ets-0.113
 textures-0.092
essing-0.092
lated-0.091
le-0.089
Token mum
Token ID25682
Feature activation-1.07e-01

Pos logit contributions
 babys+0.019
 stub+0.016
 salon+0.015
ister+0.015
fer+0.014
Neg logit contributions
ets-0.020
 textures-0.018
 They-0.017
 goals-0.017
 until-0.017
Token was
Token ID373
Feature activation-1.27e-01

Pos logit contributions
 babys+0.189
 stub+0.149
 salon+0.147
ister+0.145
 nowhere+0.135
Neg logit contributions
ets-0.202
 goals-0.171
 textures-0.169
ws-0.169
lated-0.166
Token fore
Token ID1674
Feature activation-1.92e-01

Pos logit contributions
 babys+0.221
 stub+0.184
 salon+0.172
ister+0.168
 poster+0.160
Neg logit contributions
ets-0.237
 They-0.205
 textures-0.200
 until-0.195
essing-0.194
Tokenshadow
Token ID19106
Feature activation+6.76e-02

Pos logit contributions
 babys+0.303
 stub+0.251
 salon+0.230
ister+0.216
 principal+0.215
Neg logit contributions
ets-0.391
ly-0.331
 They-0.326
essing-0.326
 textures-0.322
Tokening
Token ID278
Feature activation+9.72e-02

Pos logit contributions
ets+0.111
 textures+0.097
 They+0.094
 sizes+0.093
ws+0.092
Neg logit contributions
 babys-0.128
 stub-0.107
ister-0.104
 salon-0.102
fer-0.098
Token...
Token ID986
Feature activation+5.67e-04

Pos logit contributions
ets+0.146
 They+0.120
 textures+0.120
essing+0.115
 sizes+0.113
Neg logit contributions
 babys-0.203
 stub-0.172
 salon-0.168
ister-0.166
 poster-0.157
Tokenthe
Token ID1169
Feature activation+8.37e-02

Pos logit contributions
ets+0.001
 They+0.001
 textures+0.001
essing+0.001
 sizes+0.001
Neg logit contributions
 babys-0.001
 stub-0.001
 salon-0.001
ister-0.001
fer-0.001
Token next
Token ID1306
Feature activation+4.42e-02

Pos logit contributions
ets+0.154
 They+0.134
 textures+0.129
essing+0.128
 sizes+0.128
Neg logit contributions
 babys-0.150
 stub-0.125
 salon-0.123
ister-0.117
 poster-0.110
Token,
Token ID11
Feature activation-6.10e-02

Pos logit contributions
ets+0.108
 textures+0.094
ales+0.090
 sizes+0.090
ws+0.088
Neg logit contributions
 babys-0.086
ister-0.068
 stub-0.067
 nowhere-0.065
 poster-0.063
Token Jack
Token ID3619
Feature activation+2.66e-02

Pos logit contributions
 babys+0.117
 stub+0.098
 salon+0.094
ister+0.092
 nowhere+0.089
Neg logit contributions
ets-0.105
 textures-0.086
 They-0.084
essing-0.083
 sizes-0.082
Token asked
Token ID1965
Feature activation-1.69e-03

Pos logit contributions
ets+0.046
 textures+0.040
 They+0.038
 sizes+0.038
essing+0.037
Neg logit contributions
 babys-0.050
 stub-0.043
 salon-0.039
ister-0.038
 nowhere-0.037
Token a
Token ID257
Feature activation-8.18e-02

Pos logit contributions
 babys+0.003
 stub+0.003
ister+0.003
 principal+0.002
 salon+0.002
Neg logit contributions
ets-0.003
 textures-0.003
 sizes-0.002
essing-0.002
 They-0.002
Token wise
Token ID10787
Feature activation+3.06e-02

Pos logit contributions
 babys+0.158
 stub+0.148
 salon+0.141
 nowhere+0.140
fer+0.136
Neg logit contributions
 They-0.106
ets-0.106
 respect-0.095
 textures-0.093
 proper-0.091
Token man
Token ID582
Feature activation-1.92e-01

Pos logit contributions
ets+0.049
 They+0.040
 textures+0.040
 sizes+0.038
essing+0.038
Neg logit contributions
 babys-0.063
 stub-0.053
 salon-0.051
ister-0.050
 poster-0.048
Token,
Token ID11
Feature activation-9.85e-02

Pos logit contributions
 babys+0.420
 stub+0.348
 salon+0.342
ister+0.334
 poster+0.325
Neg logit contributions
ets-0.280
 textures-0.232
 sizes-0.223
 They-0.217
lated-0.215
Token who
Token ID508
Feature activation+9.86e-02

Pos logit contributions
 babys+0.199
 stub+0.171
 salon+0.163
ister+0.158
fer+0.151
Neg logit contributions
ets-0.156
 They-0.135
 textures-0.129
essing-0.124
 until-0.124
Token was
Token ID373
Feature activation-1.16e-01

Pos logit contributions
ets+0.168
 They+0.141
 textures+0.140
essing+0.134
 sizes+0.133
Neg logit contributions
 babys-0.190
 stub-0.161
 salon-0.153
ister-0.149
 nowhere-0.143
Token walking
Token ID6155
Feature activation+7.15e-02

Pos logit contributions
 babys+0.218
 stub+0.191
 salon+0.181
ister+0.180
 poster+0.173
Neg logit contributions
ets-0.170
 They-0.158
 until-0.149
 for-0.147
 respect-0.145
Token by
Token ID416
Feature activation+2.85e-02

Pos logit contributions
ets+0.114
 textures+0.093
essing+0.090
lated+0.089
 sizes+0.089
Neg logit contributions
 babys-0.143
 stub-0.121
 nowhere-0.114
ister-0.113
 salon-0.112
Token they
Token ID484
Feature activation+5.40e-02

Pos logit contributions
ets+0.140
ales+0.120
ws+0.118
 textures+0.118
 sizes+0.116
Neg logit contributions
 babys-0.116
 stub-0.091
 salon-0.087
 nowhere-0.081
 bumped-0.080
Token left
Token ID1364
Feature activation+8.27e-02

Pos logit contributions
ets+0.089
 They+0.075
 textures+0.074
 sizes+0.071
essing+0.071
Neg logit contributions
 babys-0.107
 stub-0.091
 salon-0.086
ister-0.084
 nowhere-0.080
Token her
Token ID607
Feature activation+7.29e-03

Pos logit contributions
ets+0.116
 They+0.097
 textures+0.092
 until+0.091
 respect+0.086
Neg logit contributions
 babys-0.182
 stub-0.160
 salon-0.152
ister-0.149
fer-0.145
Token with
Token ID351
Feature activation+6.13e-02

Pos logit contributions
ets+0.012
 They+0.010
 textures+0.010
essing+0.009
 sizes+0.009
Neg logit contributions
 babys-0.015
 stub-0.012
 salon-0.012
ister-0.012
fer-0.011
Token a
Token ID257
Feature activation-4.44e-02

Pos logit contributions
ets+0.093
 They+0.080
 textures+0.078
 respect+0.074
 until+0.074
Neg logit contributions
 babys-0.126
 stub-0.109
 salon-0.104
ister-0.104
fer-0.101
Token babys
Token ID46711
Feature activation-1.92e-01

Pos logit contributions
 babys+0.085
fer+0.076
ister+0.075
Re+0.072
 principal+0.072
Neg logit contributions
ets-0.057
 proper-0.054
 until-0.053
 respect-0.051
 They-0.048
Tokenitter
Token ID1967
Feature activation-8.38e-02

Pos logit contributions
 babys+0.294
 stub+0.266
 nowhere+0.238
 poster+0.228
 salon+0.228
Neg logit contributions
ets-0.385
ly-0.328
 They-0.326
essing-0.324
 textures-0.308
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
 babys+0.197
 stub+0.167
 salon+0.167
ister+0.160
 nowhere+0.153
Neg logit contributions
ets-0.108
 textures-0.090
 They-0.087
essing-0.084
 sizes-0.083
Token went
Token ID1816
Feature activation-3.81e-02

Pos logit contributions
 babys+0.026
 stub+0.022
ister+0.021
 salon+0.021
fer+0.020
Neg logit contributions
ets-0.025
 They-0.021
 textures-0.021
 until-0.020
ly-0.020
Token to
Token ID284
Feature activation-8.66e-02

Pos logit contributions
 babys+0.071
 stub+0.060
 salon+0.056
ister+0.055
 poster+0.052
Neg logit contributions
ets-0.068
 textures-0.057
 They-0.057
 sizes-0.055
essing-0.055
Token climb
Token ID12080
Feature activation+7.04e-02

Pos logit contributions
 babys+0.192
 stub+0.178
ister+0.170
fer+0.169
 salon+0.166
Neg logit contributions
 They-0.100
ets-0.098
 respect-0.089
 until-0.086
 After-0.085
Token cheering
Token ID29732
Feature activation+2.20e-02

Pos logit contributions
 babys+0.001
 stub+0.001
ister+0.001
 salon+0.001
+0.001
Neg logit contributions
ets-0.002
 They-0.002
 sizes-0.002
 textures-0.002
 until-0.002
Token.
Token ID13
Feature activation+3.01e-02

Pos logit contributions
ets+0.026
wed+0.023
ws+0.023
lated+0.023
 After+0.022
Neg logit contributions
 babys-0.047
 stub-0.039
 nowhere-0.038
ister-0.037
 crying-0.037
Token She
Token ID1375
Feature activation+1.61e-01

Pos logit contributions
ets+0.044
le+0.040
ws+0.039
bit+0.039
wed+0.038
Neg logit contributions
 babys-0.065
 stub-0.054
 salon-0.053
 principal-0.049
 nowhere-0.048
Token asked
Token ID1965
Feature activation-2.58e-04

Pos logit contributions
ets+0.226
 They+0.208
ly+0.180
 textures+0.179
 until+0.178
Neg logit contributions
 babys-0.340
 salon-0.291
 stub-0.284
ister-0.282
-0.273
Token a
Token ID257
Feature activation-7.74e-02

Pos logit contributions
 babys+0.001
 stub+0.000
 salon+0.000
ister+0.000
fer+0.000
Neg logit contributions
ets-0.000
 They-0.000
 textures-0.000
essing-0.000
 sizes-0.000
Token man
Token ID582
Feature activation-1.91e-01

Pos logit contributions
 babys+0.164
 stub+0.152
 salon+0.144
 nowhere+0.140
ister+0.135
Neg logit contributions
ets-0.096
 They-0.095
 textures-0.079
 until-0.078
 respect-0.078
Token,
Token ID11
Feature activation-1.01e-01

Pos logit contributions
 babys+0.435
 stub+0.375
 salon+0.363
ister+0.354
 poster+0.341
Neg logit contributions
ets-0.260
 They-0.207
 textures-0.206
 sizes-0.194
essing-0.193
Token "
Token ID366
Feature activation-5.00e-02

Pos logit contributions
 babys+0.215
 stub+0.191
 salon+0.186
ister+0.180
fer+0.171
Neg logit contributions
ets-0.131
 They-0.128
 until-0.118
 After-0.113
 textures-0.110
TokenWhat
Token ID2061
Feature activation+8.17e-02

Pos logit contributions
 babys+0.098
 stub+0.085
ister+0.079
alo+0.074
 salon+0.073
Neg logit contributions
ets-0.077
 They-0.069
ly-0.065
 until-0.065
le-0.064
Token's
Token ID338
Feature activation+5.71e-03

Pos logit contributions
ets+0.084
 They+0.070
 respect+0.064
 textures+0.063
 likes+0.061
Neg logit contributions
 babys-0.218
 stub-0.189
 salon-0.182
ister-0.175
fer-0.175
Token happening
Token ID5836
Feature activation+8.85e-02

Pos logit contributions
ets+0.008
 They+0.007
essing+0.006
 textures+0.006
 respect+0.006
Neg logit contributions
 babys-0.013
 stub-0.011
 salon-0.010
ister-0.010
fer-0.010
Token,
Token ID11
Feature activation-5.71e-02

Pos logit contributions
 babys+0.159
 stub+0.136
ister+0.125
 salon+0.124
 nowhere+0.120
Neg logit contributions
ets-0.133
 textures-0.109
 They-0.107
 sizes-0.106
essing-0.105
Token he
Token ID339
Feature activation+7.78e-02

Pos logit contributions
 babys+0.104
 stub+0.087
 nowhere+0.081
ister+0.079
 salon+0.079
Neg logit contributions
ets-0.104
 textures-0.085
essing-0.084
 sizes-0.083
 They-0.082
Token asked
Token ID1965
Feature activation+4.01e-05

Pos logit contributions
ets+0.127
 They+0.109
 textures+0.104
essing+0.100
ly+0.100
Neg logit contributions
 babys-0.154
 stub-0.129
 salon-0.126
ister-0.124
 poster-0.117
Token the
Token ID262
Feature activation-2.57e-02

Pos logit contributions
ets+0.000
 sizes+0.000
 textures+0.000
 They+0.000
essing+0.000
Neg logit contributions
 babys-0.000
 stub-0.000
ister-0.000
 principal-0.000
 nowhere-0.000
Token black
Token ID2042
Feature activation+2.66e-02

Pos logit contributions
 babys+0.051
 stub+0.045
 salon+0.043
ister+0.041
fer+0.041
Neg logit contributions
ets-0.039
 They-0.035
 textures-0.034
 respect-0.032
 goals-0.032
Tokensmith
Token ID21453
Feature activation-1.91e-01

Pos logit contributions
ets+0.050
 They+0.044
ly+0.044
 textures+0.043
ness+0.042
Neg logit contributions
 babys-0.044
 stub-0.039
 salon-0.035
 nowhere-0.033
fer-0.033
Token why
Token ID1521
Feature activation+4.89e-03

Pos logit contributions
 babys+0.444
 stub+0.378
 salon+0.373
ister+0.366
 poster+0.351
Neg logit contributions
ets-0.241
 textures-0.193
 They-0.189
 sizes-0.182
lated-0.180
Token he
Token ID339
Feature activation+8.29e-02

Pos logit contributions
ets+0.008
 They+0.007
 textures+0.007
essing+0.007
ly+0.006
Neg logit contributions
 babys-0.009
 stub-0.008
 salon-0.008
ister-0.008
 poster-0.007
Token used
Token ID973
Feature activation+1.55e-01

Pos logit contributions
ets+0.140
 They+0.117
 textures+0.117
essing+0.112
 sizes+0.111
Neg logit contributions
 babys-0.159
 stub-0.137
 salon-0.126
ister-0.124
 nowhere-0.120
Token the
Token ID262
Feature activation+1.63e-02

Pos logit contributions
ets+0.255
 They+0.210
 textures+0.205
essing+0.202
ly+0.199
Neg logit contributions
 babys-0.307
 stub-0.261
 salon-0.245
 nowhere-0.239
ister-0.237
Token scales
Token ID16252
Feature activation-1.69e-03

Pos logit contributions
ets+0.026
 They+0.021
 textures+0.021
essing+0.020
 sizes+0.020
Neg logit contributions
 babys-0.033
 stub-0.028
 salon-0.027
ister-0.026
fer-0.025
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
ets+0.038
 They+0.037
 After+0.034
 until+0.032
 textures+0.032
Neg logit contributions
 babys-0.057
 stub-0.048
 salon-0.046
ister-0.046
fer-0.046
Token
Token ID198
Feature activation-9.91e-02

Pos logit contributions
 babys+0.237
 salon+0.202
 stub+0.199
fer+0.196
 poster+0.187
Neg logit contributions
 They-0.130
ets-0.130
 After-0.116
 until-0.112
 respect-0.108
TokenShe
Token ID3347
Feature activation+1.50e-01

Pos logit contributions
 babys+0.186
 stub+0.156
 salon+0.147
ister+0.143
fer+0.137
Neg logit contributions
ets-0.174
 They-0.149
 textures-0.145
essing-0.141
ly-0.139
Token asked
Token ID1965
Feature activation+1.67e-03

Pos logit contributions
ets+0.279
 textures+0.241
 They+0.238
 sizes+0.236
essing+0.229
Neg logit contributions
 babys-0.265
 stub-0.233
 salon-0.205
 nowhere-0.200
 bumped-0.196
Token a
Token ID257
Feature activation-7.83e-02

Pos logit contributions
ets+0.003
 They+0.003
 textures+0.002
 until+0.002
ly+0.002
Neg logit contributions
 babys-0.003
 stub-0.003
 salon-0.003
ister-0.002
fer-0.002
Token man
Token ID582
Feature activation-1.90e-01

Pos logit contributions
 babys+0.158
 stub+0.144
 salon+0.143
 nowhere+0.136
fer+0.135
Neg logit contributions
 They-0.097
ets-0.094
 textures-0.086
 respect-0.085
ly-0.080
Token for
Token ID329
Feature activation+5.48e-03

Pos logit contributions
 babys+0.416
 stub+0.354
 salon+0.343
ister+0.335
 poster+0.322
Neg logit contributions
ets-0.277
 textures-0.224
 They-0.221
 sizes-0.213
essing-0.209
Token help
Token ID1037
Feature activation-3.01e-03

Pos logit contributions
ets+0.008
 They+0.007
 textures+0.007
 respect+0.007
ly+0.006
Neg logit contributions
 babys-0.011
 stub-0.010
 salon-0.010
ister-0.009
fer-0.009
Token.
Token ID13
Feature activation+2.76e-02

Pos logit contributions
 babys+0.008
 stub+0.007
 salon+0.006
ister+0.006
 nowhere+0.006
Neg logit contributions
ets-0.003
 textures-0.002
 They-0.002
 goals-0.002
 sizes-0.002
Token He
Token ID679
Feature activation+1.45e-01

Pos logit contributions
ets+0.036
 textures+0.027
 sizes+0.026
wed+0.025
essing+0.025
Neg logit contributions
 babys-0.066
 salon-0.056
 stub-0.056
ister-0.055
 poster-0.053
Token was
Token ID373
Feature activation-1.14e-01

Pos logit contributions
ets+0.232
 They+0.204
 textures+0.192
ly+0.191
le+0.190
Neg logit contributions
 babys-0.280
 stub-0.239
 salon-0.232
ister-0.220
fer-0.213
Token
Token ID198
Feature activation-9.78e-02

Pos logit contributions
 babys+0.220
 stub+0.187
 salon+0.182
fer+0.179
ister+0.177
Neg logit contributions
ets-0.144
 They-0.138
 After-0.123
 until-0.123
 textures-0.112
TokenL
Token ID43
Feature activation+3.42e-02

Pos logit contributions
 babys+0.170
 stub+0.144
 salon+0.135
ister+0.127
 nowhere+0.122
Neg logit contributions
ets-0.184
 textures-0.159
 sizes-0.153
essing-0.152
 They-0.152
Tokenily
Token ID813
Feature activation+5.20e-02

Pos logit contributions
ets+0.040
 They+0.032
 textures+0.031
 sizes+0.029
essing+0.028
Neg logit contributions
 babys-0.083
 stub-0.073
 salon-0.071
ister-0.069
 nowhere-0.067
Token and
Token ID290
Feature activation-2.89e-03

Pos logit contributions
ets+0.091
 textures+0.078
 sizes+0.075
 They+0.074
essing+0.073
Neg logit contributions
 babys-0.100
 stub-0.085
 salon-0.080
ister-0.074
 nowhere-0.073
Token her
Token ID607
Feature activation-4.67e-03

Pos logit contributions
 babys+0.006
fer+0.006
 stub+0.006
ister+0.005
 salon+0.005
Neg logit contributions
 They-0.003
 textures-0.003
 each-0.003
ets-0.003
 respect-0.003
Token babys
Token ID46711
Feature activation-1.90e-01

Pos logit contributions
fer+0.009
 stub+0.009
chard+0.009
Re+0.009
ister+0.009
Neg logit contributions
 They-0.005
ets-0.005
 textures-0.005
 for-0.004
 until-0.004
Tokenitter
Token ID1967
Feature activation-7.73e-02

Pos logit contributions
 babys+0.276
 stub+0.251
 nowhere+0.216
 salon+0.215
fer+0.212
Neg logit contributions
ets-0.384
 They-0.346
essing-0.330
ly-0.327
 textures-0.325
Token went
Token ID1816
Feature activation-3.55e-02

Pos logit contributions
 babys+0.147
 salon+0.114
 stub+0.112
ister+0.104
 bumped+0.103
Neg logit contributions
ets-0.138
 goals-0.119
 textures-0.119
bit-0.118
ires-0.117
Token to
Token ID284
Feature activation-8.50e-02

Pos logit contributions
 babys+0.071
 stub+0.063
ister+0.059
 salon+0.058
fer+0.058
Neg logit contributions
ets-0.056
 They-0.049
 until-0.045
 After-0.044
ly-0.044
Token the
Token ID262
Feature activation-5.68e-04

Pos logit contributions
 babys+0.192
 stub+0.185
fer+0.179
ister+0.176
 salon+0.169
Neg logit contributions
 They-0.092
ets-0.084
 respect-0.078
 until-0.077
 After-0.076
Token park
Token ID3952
Feature activation-2.63e-02

Pos logit contributions
 babys+0.001
 stub+0.001
fer+0.001
ister+0.001
 nowhere+0.001
Neg logit contributions
 They-0.001
ets-0.001
 until-0.001
 respect-0.001
 After-0.001
TokenThe
Token ID464
Feature activation+1.01e-01

Pos logit contributions
 babys+0.163
 stub+0.148
ister+0.140
Re+0.136
 salon+0.132
Neg logit contributions
ets-0.179
 textures-0.152
ness-0.149
 sizes-0.148
essing-0.146
Token bird
Token ID6512
Feature activation-1.12e-01

Pos logit contributions
ets+0.161
 textures+0.141
 They+0.141
 goals+0.132
 respect+0.132
Neg logit contributions
 babys-0.198
 stub-0.170
 salon-0.163
ister-0.156
fer-0.152
Token asked
Token ID1965
Feature activation+3.29e-03

Pos logit contributions
 babys+0.145
 stub+0.143
 bumped+0.123
 nowhere+0.118
 salon+0.108
Neg logit contributions
ets-0.232
ires-0.215
 They-0.215
 textures-0.214
 sizes-0.208
Token an
Token ID281
Feature activation-5.38e-02

Pos logit contributions
ets+0.006
 textures+0.005
 sizes+0.005
essing+0.005
lated+0.005
Neg logit contributions
 babys-0.006
 stub-0.005
ister-0.005
 nowhere-0.005
 salon-0.005
Token old
Token ID1468
Feature activation+9.41e-03

Pos logit contributions
 babys+0.103
 stub+0.082
ister+0.080
 salon+0.079
 principal+0.077
Neg logit contributions
ets-0.093
 They-0.079
 After-0.074
essing-0.071
 sizes-0.071
Token man
Token ID582
Feature activation-1.89e-01

Pos logit contributions
ets+0.017
 They+0.015
 textures+0.015
ly+0.014
 respect+0.014
Neg logit contributions
 babys-0.016
 stub-0.014
 salon-0.013
ister-0.012
 nowhere-0.012
Token:
Token ID25
Feature activation-1.39e-01

Pos logit contributions
 babys+0.391
 salon+0.321
 stub+0.320
ister+0.312
 principal+0.301
Neg logit contributions
ets-0.298
 textures-0.248
 sizes-0.236
lated-0.233
 They-0.232
Token "
Token ID366
Feature activation-3.94e-02

Pos logit contributions
 babys+0.309
 stub+0.274
 salon+0.262
ister+0.247
fer+0.241
Neg logit contributions
 They-0.173
ets-0.155
 until-0.153
 After-0.152
 respect-0.137
TokenWhat
Token ID2061
Feature activation+8.68e-02

Pos logit contributions
 babys+0.070
 stub+0.058
 salon+0.054
ister+0.053
 principal+0.050
Neg logit contributions
ets-0.070
 textures-0.061
 They-0.061
le-0.060
 respect-0.060
Token was
Token ID373
Feature activation-7.51e-02

Pos logit contributions
ets+0.110
 They+0.089
 textures+0.086
essing+0.082
 respect+0.081
Neg logit contributions
 babys-0.206
 stub-0.179
 salon-0.172
ister-0.167
fer-0.162
Token that
Token ID326
Feature activation+7.12e-02

Pos logit contributions
 babys+0.177
 stub+0.154
 salon+0.148
ister+0.141
fer+0.139
Neg logit contributions
ets-0.097
 They-0.075
ly-0.073
 textures-0.073
 until-0.073
Token very
Token ID845
Feature activation-9.68e-02

Pos logit contributions
 babys+0.032
 stub+0.026
 salon+0.026
ister+0.025
fer+0.024
Neg logit contributions
ets-0.034
 They-0.030
 textures-0.029
 until-0.028
 respect-0.028
Token polite
Token ID23507
Feature activation+8.27e-02

Pos logit contributions
 babys+0.136
 stub+0.116
ister+0.093
 crying+0.089
 salon+0.085
Neg logit contributions
ets-0.217
 sizes-0.191
 textures-0.188
ales-0.187
 They-0.183
Token and
Token ID290
Feature activation-2.71e-02

Pos logit contributions
ets+0.113
 textures+0.095
lated+0.094
 sizes+0.090
 They+0.090
Neg logit contributions
 babys-0.178
 stub-0.157
 nowhere-0.149
 salon-0.147
 crying-0.141
Token asked
Token ID1965
Feature activation-5.88e-03

Pos logit contributions
 babys+0.050
 stub+0.044
 salon+0.038
 nowhere+0.037
ister+0.037
Neg logit contributions
ets-0.048
 textures-0.039
essing-0.039
le-0.038
ales-0.038
Token the
Token ID262
Feature activation-2.88e-02

Pos logit contributions
 babys+0.011
 stub+0.009
 salon+0.008
ister+0.008
 nowhere+0.008
Neg logit contributions
ets-0.011
 textures-0.009
 They-0.009
 sizes-0.009
essing-0.009
Token man
Token ID582
Feature activation-1.89e-01

Pos logit contributions
 babys+0.057
fer+0.056
 stub+0.052
chard+0.050
ister+0.050
Neg logit contributions
 They-0.035
 respect-0.034
 textures-0.032
ets-0.032
 likes-0.031
Token who
Token ID508
Feature activation+9.13e-02

Pos logit contributions
 babys+0.397
 salon+0.322
 stub+0.318
ister+0.304
 principal+0.304
Neg logit contributions
ets-0.301
 textures-0.241
 sizes-0.231
lated-0.231
 They-0.223
Token owned
Token ID6898
Feature activation+9.39e-02

Pos logit contributions
ets+0.152
 They+0.127
 textures+0.125
essing+0.120
 sizes+0.119
Neg logit contributions
 babys-0.180
 stub-0.153
 salon-0.145
ister-0.142
 nowhere-0.135
Token the
Token ID262
Feature activation+1.94e-02

Pos logit contributions
ets+0.142
 They+0.123
 textures+0.118
ly+0.112
 sizes+0.111
Neg logit contributions
 babys-0.196
 stub-0.168
 salon-0.163
ister-0.159
fer-0.153
Token bird
Token ID6512
Feature activation-1.05e-01

Pos logit contributions
ets+0.028
 respect+0.024
 textures+0.024
 until+0.023
 They+0.023
Neg logit contributions
 babys-0.039
ister-0.034
fer-0.034
 stub-0.033
 salon-0.032
Token if
Token ID611
Feature activation+6.79e-02

Pos logit contributions
 babys+0.245
 stub+0.216
 salon+0.202
 nowhere+0.198
ister+0.194
Neg logit contributions
ets-0.136
 textures-0.107
 They-0.105
lated-0.104
essing-0.100
Token So
Token ID1406
Feature activation+5.82e-02

Pos logit contributions
ets+0.034
le+0.025
 textures+0.025
ly+0.024
wed+0.024
Neg logit contributions
 babys-0.063
 stub-0.055
 salon-0.052
 nowhere-0.051
ister-0.050
Token the
Token ID262
Feature activation+1.01e-02

Pos logit contributions
ets+0.133
ws+0.112
ales+0.111
wed+0.110
ished+0.110
Neg logit contributions
 babys-0.085
 stub-0.067
 nowhere-0.065
 salon-0.061
 bumped-0.061
Token car
Token ID1097
Feature activation-4.00e-02

Pos logit contributions
ets+0.016
 They+0.014
 textures+0.013
 sizes+0.013
essing+0.013
Neg logit contributions
 babys-0.020
 stub-0.018
 salon-0.017
ister-0.016
fer-0.016
Token asked
Token ID1965
Feature activation+2.82e-06

Pos logit contributions
 babys+0.070
 stub+0.059
 salon+0.054
ister+0.052
 bumped+0.052
Neg logit contributions
ets-0.075
 textures-0.066
 They-0.063
 sizes-0.062
essing-0.062
Token a
Token ID257
Feature activation-7.82e-02

Feature not active on prev token;
no predictions were affected.
Token man
Token ID582
Feature activation-1.89e-01

Pos logit contributions
 babys+0.162
 stub+0.144
 salon+0.137
ister+0.133
fer+0.131
Neg logit contributions
ets-0.110
 They-0.099
 textures-0.093
 respect-0.088
 until-0.088
Token for
Token ID329
Feature activation+6.79e-04

Pos logit contributions
 babys+0.394
 salon+0.318
 stub+0.311
ister+0.306
 principal+0.299
Neg logit contributions
ets-0.299
 textures-0.256
lated-0.243
 sizes-0.242
 goals-0.235
Token help
Token ID1037
Feature activation-2.46e-03

Pos logit contributions
ets+0.001
 They+0.001
 textures+0.001
essing+0.001
 sizes+0.001
Neg logit contributions
 babys-0.001
 stub-0.001
 salon-0.001
ister-0.001
 nowhere-0.001
Token.
Token ID13
Feature activation+2.21e-02

Pos logit contributions
 babys+0.006
 stub+0.005
ister+0.005
 salon+0.005
 crying+0.005
Neg logit contributions
ets-0.003
 textures-0.002
 goals-0.002
lated-0.002
 sizes-0.002
Token The
Token ID383
Feature activation+1.11e-01

Pos logit contributions
ets+0.033
 textures+0.026
le+0.025
essing+0.025
 sizes+0.024
Neg logit contributions
 babys-0.048
 stub-0.040
 salon-0.039
ister-0.039
 poster-0.038
Token man
Token ID582
Feature activation-1.41e-01

Pos logit contributions
ets+0.177
 They+0.159
 textures+0.154
 respect+0.150
ly+0.149
Neg logit contributions
 babys-0.205
 stub-0.185
 salon-0.163
ister-0.162
fer-0.161
Token top
Token ID1353
Feature activation-1.26e-03

Pos logit contributions
 babys+0.004
 stub+0.003
 salon+0.003
ister+0.003
 nowhere+0.003
Neg logit contributions
ets-0.003
 They-0.003
essing-0.003
 textures-0.003
le-0.003
Token.
Token ID13
Feature activation+2.63e-02

Pos logit contributions
 babys+0.003
 salon+0.003
 stub+0.002
ister+0.002
 poster+0.002
Neg logit contributions
ets-0.002
 textures-0.001
 They-0.001
 respect-0.001
essing-0.001
Token They
Token ID1119
Feature activation+1.49e-01

Pos logit contributions
ets+0.048
 textures+0.038
le+0.038
wed+0.038
ws+0.038
Neg logit contributions
 babys-0.050
 stub-0.041
 salon-0.037
-0.037
ister-0.036
Token asked
Token ID1965
Feature activation-1.38e-03

Pos logit contributions
ets+0.271
 textures+0.224
essing+0.220
 They+0.217
lated+0.215
Neg logit contributions
 babys-0.275
 stub-0.231
 salon-0.217
ister-0.208
 nowhere-0.205
Token a
Token ID257
Feature activation-7.65e-02

Pos logit contributions
 babys+0.003
 stub+0.002
ister+0.002
 nowhere+0.002
 salon+0.002
Neg logit contributions
ets-0.003
 textures-0.002
 sizes-0.002
lated-0.002
essing-0.002
Token man
Token ID582
Feature activation-1.89e-01

Pos logit contributions
 babys+0.154
 stub+0.138
 salon+0.128
ister+0.125
fer+0.125
Neg logit contributions
ets-0.101
 They-0.095
 textures-0.090
 until-0.088
 respect-0.085
Token who
Token ID508
Feature activation+9.46e-02

Pos logit contributions
 babys+0.399
 salon+0.327
 stub+0.323
ister+0.318
 poster+0.302
Neg logit contributions
ets-0.299
 textures-0.249
 sizes-0.234
lated-0.228
 goals-0.228
Token was
Token ID373
Feature activation-1.15e-01

Pos logit contributions
ets+0.159
 They+0.133
 textures+0.131
essing+0.126
 sizes+0.125
Neg logit contributions
 babys-0.184
 stub-0.156
 salon-0.148
ister-0.145
 nowhere-0.138
Token bald
Token ID28273
Feature activation+4.08e-02

Pos logit contributions
 babys+0.208
 stub+0.186
 salon+0.160
ister+0.159
+0.156
Neg logit contributions
ets-0.165
 until-0.161
 They-0.157
 for-0.155
 like-0.153
Token to
Token ID284
Feature activation-1.05e-01

Pos logit contributions
ets+0.056
ws+0.045
wed+0.045
 They+0.044
lated+0.043
Neg logit contributions
 babys-0.093
 salon-0.080
ister-0.078
 stub-0.078
fer-0.076
Token tell
Token ID1560
Feature activation+1.87e-02

Pos logit contributions
 babys+0.218
 stub+0.189
 salon+0.177
ister+0.173
fer+0.166
Neg logit contributions
ets-0.160
 They-0.135
 textures-0.133
 respect-0.129
 sizes-0.125
Token saw
Token ID2497
Feature activation-6.31e-03

Pos logit contributions
ets+0.040
 textures+0.035
 They+0.034
 sizes+0.033
essing+0.033
Neg logit contributions
 babys-0.038
 stub-0.033
 salon-0.030
ister-0.029
 nowhere-0.028
Token a
Token ID257
Feature activation-5.71e-02

Pos logit contributions
 babys+0.013
 stub+0.011
 salon+0.010
ister+0.010
fer+0.010
Neg logit contributions
ets-0.010
 They-0.008
 textures-0.008
essing-0.008
 sizes-0.008
Token pretty
Token ID2495
Feature activation+8.03e-02

Pos logit contributions
 babys+0.113
 stub+0.102
ister+0.097
fer+0.093
 salon+0.093
Neg logit contributions
ets-0.071
 textures-0.065
 They-0.065
 until-0.064
 proper-0.061
Token toy
Token ID13373
Feature activation-2.80e-02

Pos logit contributions
ets+0.147
 They+0.127
 textures+0.126
ly+0.121
essing+0.120
Neg logit contributions
 babys-0.140
 stub-0.117
 salon-0.109
ister-0.108
fer-0.102
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
 babys+0.057
 stub+0.048
 salon+0.047
ister+0.045
 poster+0.044
Neg logit contributions
ets-0.046
 textures-0.038
 They-0.037
essing-0.036
 sizes-0.036
Token She
Token ID1375
Feature activation+1.63e-01

Pos logit contributions
ets+0.041
 They+0.031
 textures+0.031
essing+0.029
 sizes+0.028
Neg logit contributions
 babys-0.091
 stub-0.080
 salon-0.077
ister-0.076
 poster-0.073
Token wanted
Token ID2227
Feature activation+1.03e-02

Pos logit contributions
ets+0.242
 They+0.208
 textures+0.199
ly+0.190
essing+0.188
Neg logit contributions
 babys-0.345
 stub-0.292
 salon-0.284
ister-0.282
fer-0.266
Token to
Token ID284
Feature activation-9.94e-02

Pos logit contributions
ets+0.019
 They+0.016
 textures+0.016
essing+0.015
 sizes+0.015
Neg logit contributions
 babys-0.019
 stub-0.015
 salon-0.015
ister-0.014
 nowhere-0.013
Token give
Token ID1577
Feature activation+7.56e-04

Pos logit contributions
 babys+0.208
 stub+0.178
 salon+0.168
ister+0.164
 poster+0.157
Neg logit contributions
ets-0.158
 They-0.124
 textures-0.123
essing-0.123
 sizes-0.122
Token it
Token ID340
Feature activation-7.96e-02

Pos logit contributions
ets+0.001
 textures+0.001
 sizes+0.001
 They+0.001
essing+0.001
Neg logit contributions
 babys-0.001
 stub-0.001
 salon-0.001
ister-0.001
 nowhere-0.001
Token to
Token ID284
Feature activation-9.62e-02

Pos logit contributions
 babys+0.126
 stub+0.098
 salon+0.090
 nowhere+0.090
ister+0.088
Neg logit contributions
ets-0.158
 sizes-0.137
 textures-0.136
 They-0.135
essing-0.133
Token out
Token ID503
Feature activation-1.28e-02

Pos logit contributions
ets+0.170
 textures+0.157
 sizes+0.155
 They+0.149
essing+0.146
Neg logit contributions
 babys-0.146
 stub-0.128
 nowhere-0.116
ister-0.110
 bumped-0.107
Token from
Token ID422
Feature activation-1.52e-02

Pos logit contributions
 babys+0.020
 nowhere+0.016
 stub+0.016
ister+0.016
 crying+0.015
Neg logit contributions
ets-0.024
essing-0.021
ws-0.021
wed-0.021
osaurs-0.020
Token the
Token ID262
Feature activation+2.32e-02

Pos logit contributions
 babys+0.027
 nowhere+0.023
 stub+0.023
 salon+0.021
chard+0.021
Neg logit contributions
ets-0.028
essing-0.023
 They-0.022
 sizes-0.022
 textures-0.022
Token pile
Token ID14540
Feature activation-1.90e-02

Pos logit contributions
ets+0.043
 They+0.036
essing+0.035
le+0.035
 textures+0.035
Neg logit contributions
 babys-0.043
 stub-0.035
 salon-0.035
 poster-0.032
 principal-0.031
Token.
Token ID13
Feature activation+3.62e-02

Pos logit contributions
 babys+0.043
 salon+0.037
 stub+0.037
ister+0.037
 nowhere+0.035
Neg logit contributions
ets-0.024
 textures-0.020
ws-0.019
essing-0.019
 proper-0.019
Token She
Token ID1375
Feature activation+1.64e-01

Pos logit contributions
 They+0.030
ets+0.030
 After+0.024
 until+0.020
 textures+0.020
Neg logit contributions
 babys-0.098
 stub-0.086
ister-0.086
 salon-0.086
fer-0.085
Token went
Token ID1816
Feature activation-2.45e-02

Pos logit contributions
ets+0.247
 They+0.219
 textures+0.206
ly+0.203
 until+0.200
Neg logit contributions
 babys-0.338
ister-0.281
 salon-0.281
 stub-0.274
 poster-0.263
Token closer
Token ID5699
Feature activation+5.06e-02

Pos logit contributions
 babys+0.054
 stub+0.048
 salon+0.046
ister+0.046
fer+0.045
Neg logit contributions
ets-0.032
 They-0.027
 until-0.027
 After-0.024
ly-0.024
Token to
Token ID284
Feature activation-5.63e-02

Pos logit contributions
ets+0.082
 textures+0.068
 sizes+0.066
 They+0.066
essing+0.065
Neg logit contributions
 babys-0.098
 stub-0.085
 salon-0.081
ister-0.079
 nowhere-0.077
Token look
Token ID804
Feature activation-2.12e-02

Pos logit contributions
 babys+0.122
 stub+0.105
ister+0.101
 salon+0.101
fer+0.096
Neg logit contributions
ets-0.080
 They-0.069
 textures-0.066
 respect-0.064
 until-0.064
Token and
Token ID290
Feature activation-1.17e-02

Pos logit contributions
 babys+0.039
 stub+0.033
 nowhere+0.033
 crying+0.032
 bumped+0.031
Neg logit contributions
ets-0.032
bit-0.031
 sizes-0.031
 textures-0.031
essing-0.028
Token create
Token ID2251
Feature activation+7.52e-02

Pos logit contributions
 babys+0.170
 stub+0.144
 salon+0.136
ister+0.128
 poster+0.126
Neg logit contributions
ets-0.146
 They-0.115
essing-0.114
ly-0.114
 textures-0.114
Token something
Token ID1223
Feature activation-2.44e-02

Pos logit contributions
ets+0.156
ales+0.137
essing+0.135
rated+0.135
wed+0.134
Neg logit contributions
 babys-0.098
 nowhere-0.073
 stub-0.073
 crying-0.070
 principal-0.069
Token new
Token ID649
Feature activation+9.87e-02

Pos logit contributions
 babys+0.045
 stub+0.037
 salon+0.035
ister+0.034
 crying+0.034
Neg logit contributions
ets-0.042
bit-0.035
ales-0.035
wed-0.035
ws-0.035
Token.
Token ID13
Feature activation+3.29e-02

Pos logit contributions
ets+0.121
lated+0.098
 They+0.092
 textures+0.092
bit+0.091
Neg logit contributions
 babys-0.226
 stub-0.195
 salon-0.192
 nowhere-0.188
fer-0.187
Token He
Token ID679
Feature activation+1.53e-01

Pos logit contributions
ets+0.046
le+0.041
 textures+0.034
ales+0.033
 sizes+0.033
Neg logit contributions
 babys-0.078
 stub-0.068
 salon-0.060
-0.060
 nowhere-0.059
Token used
Token ID973
Feature activation+1.49e-01

Pos logit contributions
ets+0.257
 They+0.217
 textures+0.215
ly+0.207
essing+0.206
Neg logit contributions
 babys-0.297
 stub-0.263
 salon-0.243
 nowhere-0.229
ister-0.224
Token his
Token ID465
Feature activation+1.79e-02

Pos logit contributions
ets+0.227
 They+0.182
essing+0.180
 textures+0.180
ly+0.173
Neg logit contributions
 babys-0.313
 stub-0.270
 salon-0.252
 nowhere-0.247
ister-0.242
Token creative
Token ID7325
Feature activation+1.23e-01

Pos logit contributions
ets+0.027
 They+0.023
 textures+0.022
 sizes+0.021
 until+0.021
Neg logit contributions
 babys-0.037
 stub-0.032
 salon-0.032
ister-0.031
fer-0.029
Token mind
Token ID2000
Feature activation+2.54e-02

Pos logit contributions
ets+0.198
 They+0.167
 textures+0.161
essing+0.159
lated+0.157
Neg logit contributions
 babys-0.245
 stub-0.208
 salon-0.188
ister-0.183
 nowhere-0.183
Token to
Token ID284
Feature activation-7.08e-02

Pos logit contributions
ets+0.054
lated+0.048
 textures+0.047
le+0.047
essing+0.047
Neg logit contributions
 babys-0.035
 stub-0.028
 salon-0.026
 nowhere-0.025
ister-0.024
Token make
Token ID787
Feature activation+2.23e-02

Pos logit contributions
 babys+0.134
 stub+0.114
 salon+0.106
 poster+0.104
ister+0.103
Neg logit contributions
ets-0.115
ly-0.095
ished-0.092
essing-0.091
 After-0.091
Token table
Token ID3084
Feature activation-3.91e-02

Pos logit contributions
ets+0.050
 They+0.044
lated+0.042
essing+0.042
 textures+0.041
Neg logit contributions
 babys-0.048
 stub-0.039
 salon-0.039
 poster-0.036
ister-0.035
Token and
Token ID290
Feature activation+3.56e-03

Pos logit contributions
 babys+0.076
 salon+0.070
ister+0.067
 poster+0.063
 stub+0.061
Neg logit contributions
ets-0.055
 textures-0.047
lated-0.047
 They-0.046
essing-0.045
Token it
Token ID340
Feature activation-3.92e-02

Pos logit contributions
ets+0.006
essing+0.005
lated+0.005
 They+0.005
 textures+0.005
Neg logit contributions
 babys-0.007
 stub-0.006
 salon-0.006
 poster-0.005
ister-0.005
Token is
Token ID318
Feature activation-1.04e-01

Pos logit contributions
 babys+0.063
 salon+0.060
 poster+0.057
 stub+0.056
 bumped+0.055
Neg logit contributions
ets-0.059
lated-0.054
 textures-0.052
ales-0.052
 respect-0.051
Token very
Token ID845
Feature activation-9.55e-02

Pos logit contributions
 babys+0.168
 nowhere+0.139
 stub+0.137
 salon+0.132
chard+0.130
Neg logit contributions
ets-0.196
ly-0.171
le-0.168
 They-0.160
essing-0.158
Token long
Token ID890
Feature activation+1.45e-01

Pos logit contributions
 babys+0.140
chard+0.119
ister+0.118
 stub+0.111
nam+0.106
Neg logit contributions
ets-0.187
en-0.167
le-0.165
ales-0.156
ness-0.156
Token".
Token ID1911
Feature activation-3.06e-02

Pos logit contributions
ets+0.193
lated+0.175
 They+0.163
essing+0.162
angles+0.157
Neg logit contributions
 babys-0.300
 stub-0.259
 salon-0.254
 nowhere-0.245
ister-0.239
Token
Token ID198
Feature activation-1.04e-01

Pos logit contributions
 babys+0.069
 stub+0.060
 salon+0.057
ister+0.056
fer+0.054
Neg logit contributions
ets-0.042
 textures-0.034
 They-0.034
essing-0.032
 sizes-0.032
TokenThen
Token ID6423
Feature activation+8.40e-02

Pos logit contributions
 babys+0.205
 stub+0.175
 salon+0.168
ister+0.158
 poster+0.158
Neg logit contributions
ets-0.164
 They-0.148
 After-0.137
 until-0.135
 textures-0.134
Token he
Token ID339
Feature activation+7.91e-02

Pos logit contributions
ets+0.151
 textures+0.124
essing+0.122
 They+0.119
lated+0.119
Neg logit contributions
 babys-0.160
 stub-0.132
 salon-0.125
ister-0.122
fer-0.117
Token started
Token ID2067
Feature activation+7.78e-03

Pos logit contributions
ets+0.141
 They+0.121
 textures+0.119
essing+0.114
 sizes+0.114
Neg logit contributions
 babys-0.145
 stub-0.122
 salon-0.115
ister-0.112
fer-0.106
Token find
Token ID1064
Feature activation+3.41e-03

Pos logit contributions
 babys+0.067
 stub+0.056
 salon+0.055
ister+0.053
 poster+0.052
Neg logit contributions
ets-0.048
 They-0.040
 textures-0.039
le-0.038
ly-0.038
Token his
Token ID465
Feature activation-9.26e-03

Pos logit contributions
ets+0.006
 They+0.005
 textures+0.005
essing+0.005
 sizes+0.005
Neg logit contributions
 babys-0.007
 stub-0.006
 salon-0.005
 nowhere-0.005
ister-0.005
Token favorite
Token ID4004
Feature activation+1.02e-02

Pos logit contributions
 babys+0.020
 stub+0.018
ister+0.017
 salon+0.017
fer+0.017
Neg logit contributions
ets-0.012
 textures-0.010
 They-0.010
 sizes-0.010
 goals-0.009
Token folder
Token ID9483
Feature activation-7.45e-02

Pos logit contributions
ets+0.011
 textures+0.010
 They+0.009
ly+0.009
 sizes+0.009
Neg logit contributions
 babys-0.024
ister-0.022
 stub-0.021
 salon-0.021
fer-0.021
Token.
Token ID13
Feature activation+2.10e-02

Pos logit contributions
 babys+0.193
 stub+0.171
 salon+0.164
ister+0.161
 nowhere+0.160
Neg logit contributions
ets-0.074
 They-0.056
 textures-0.056
essing-0.052
 sizes-0.051
Token He
Token ID679
Feature activation+1.45e-01

Pos logit contributions
ets+0.026
le+0.019
ly+0.017
 respect+0.017
wed+0.017
Neg logit contributions
 babys-0.053
 stub-0.046
 salon-0.044
ister-0.042
 nowhere-0.042
Token searched
Token ID16499
Feature activation+1.68e-02

Pos logit contributions
ets+0.272
 textures+0.229
 sizes+0.226
 They+0.225
ires+0.223
Neg logit contributions
 babys-0.261
 stub-0.236
 salon-0.200
 bumped-0.200
 nowhere-0.198
Token high
Token ID1029
Feature activation+8.45e-02

Pos logit contributions
ets+0.026
 textures+0.022
essing+0.022
der+0.022
 respect+0.021
Neg logit contributions
 babys-0.032
 stub-0.028
 nowhere-0.027
 salon-0.025
ister-0.025
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
ets+0.125
 respect+0.107
 textures+0.106
 They+0.104
 sizes+0.103
Neg logit contributions
 babys-0.165
 stub-0.145
 nowhere-0.144
 salon-0.138
ister-0.137
Token low
Token ID1877
Feature activation+8.75e-02

Pos logit contributions
 babys+0.029
 stub+0.024
 salon+0.023
ister+0.022
fer+0.021
Neg logit contributions
ets-0.032
 They-0.028
 textures-0.027
essing-0.026
 sizes-0.026
Token,
Token ID11
Feature activation-6.74e-02

Pos logit contributions
ets+0.132
bit+0.112
wed+0.111
essing+0.109
 textures+0.109
Neg logit contributions
 babys-0.170
 stub-0.140
 salon-0.140
 crying-0.136
 nowhere-0.133
Token toys
Token ID14958
Feature activation-2.47e-02

Pos logit contributions
 babys+0.036
 stub+0.033
ister+0.033
fer+0.033
 salon+0.032
Neg logit contributions
ets-0.015
 textures-0.014
 They-0.014
 until-0.013
 sizes-0.012
Token and
Token ID290
Feature activation-5.11e-03

Pos logit contributions
 babys+0.058
 salon+0.050
 stub+0.050
ister+0.047
 nowhere+0.047
Neg logit contributions
ets-0.031
 textures-0.024
 They-0.024
essing-0.024
 sizes-0.023
Token run
Token ID1057
Feature activation+4.54e-02

Pos logit contributions
 babys+0.011
 stub+0.009
ister+0.009
 salon+0.009
fer+0.008
Neg logit contributions
ets-0.008
 They-0.007
 textures-0.007
 sizes-0.006
 until-0.006
Token around
Token ID1088
Feature activation+2.51e-02

Pos logit contributions
ets+0.053
 textures+0.047
essing+0.045
 sizes+0.044
 respect+0.043
Neg logit contributions
 babys-0.103
 stub-0.092
 salon-0.084
 bumped-0.083
 nowhere-0.083
Token outside
Token ID2354
Feature activation+2.52e-02

Pos logit contributions
ets+0.034
 They+0.029
 until+0.027
 textures+0.027
 After+0.026
Neg logit contributions
 babys-0.057
 stub-0.049
ister-0.047
 salon-0.047
fer-0.045
Token.
Token ID13
Feature activation+3.05e-02

Pos logit contributions
ets+0.034
lated+0.025
wed+0.025
essing+0.024
ws+0.024
Neg logit contributions
 babys-0.060
 stub-0.052
 salon-0.050
ister-0.048
 poster-0.047
Token One
Token ID1881
Feature activation+1.54e-01

Pos logit contributions
ets+0.037
 textures+0.028
ly+0.027
le+0.026
 sizes+0.026
Neg logit contributions
 babys-0.075
 stub-0.065
 salon-0.063
ister-0.059
 nowhere-0.058
Token day
Token ID1110
Feature activation-6.62e-02

Pos logit contributions
ets+0.204
 They+0.170
 textures+0.166
essing+0.155
ly+0.154
Neg logit contributions
 babys-0.350
 stub-0.303
 salon-0.294
ister-0.286
fer-0.284
Token,
Token ID11
Feature activation-4.83e-02

Pos logit contributions
 babys+0.166
 salon+0.149
fer+0.147
 stub+0.146
ister+0.145
Neg logit contributions
ets-0.066
 They-0.059
 until-0.057
ly-0.053
 After-0.050
Token Lily
Token ID20037
Feature activation+4.02e-02

Pos logit contributions
 babys+0.103
ister+0.092
fer+0.090
 stub+0.089
 salon+0.086
Neg logit contributions
ets-0.064
 They-0.062
 until-0.060
ly-0.055
 After-0.055
Token's
Token ID338
Feature activation-2.61e-02

Pos logit contributions
ets+0.056
 They+0.046
 textures+0.044
ly+0.042
essing+0.042
Neg logit contributions
 babys-0.089
 stub-0.076
 salon-0.074
ister-0.074
 poster-0.071
Token
Token ID198
Feature activation-9.74e-02

Pos logit contributions
 babys+0.171
 stub+0.144
ister+0.132
 salon+0.130
 nowhere+0.124
Neg logit contributions
ets-0.200
 textures-0.172
essing-0.166
 sizes-0.165
ly-0.164
Token"
Token ID1
Feature activation-4.72e-02

Pos logit contributions
 babys+0.155
 stub+0.134
ister+0.127
 salon+0.125
Re+0.123
Neg logit contributions
ets-0.189
 textures-0.167
essing-0.160
wed-0.155
 sizes-0.155
TokenI
Token ID40
Feature activation+5.85e-02

Pos logit contributions
 babys+0.094
 stub+0.081
 salon+0.075
ister+0.073
 nowhere+0.070
Neg logit contributions
ets-0.073
 They-0.070
 textures-0.066
 sizes-0.063
 respect-0.062
Token am
Token ID716
Feature activation-1.17e-01

Pos logit contributions
ets+0.116
 They+0.101
 textures+0.099
essing+0.096
 sizes+0.096
Neg logit contributions
 babys-0.096
 stub-0.079
 salon-0.074
ister-0.072
fer-0.067
Token Ben
Token ID3932
Feature activation+1.25e-02

Pos logit contributions
 babys+0.232
 stub+0.200
 salon+0.192
ister+0.184
fer+0.178
Neg logit contributions
ets-0.186
 They-0.163
 until-0.151
 textures-0.148
 respect-0.148
Token.
Token ID13
Feature activation+5.97e-02

Pos logit contributions
ets+0.019
lated+0.015
 textures+0.015
 After+0.015
wed+0.015
Neg logit contributions
 babys-0.027
ister-0.022
 stub-0.022
 crying-0.022
 salon-0.022
Token I
Token ID314
Feature activation+3.67e-02

Pos logit contributions
ets+0.120
wed+0.105
lated+0.103
le+0.100
 textures+0.099
Neg logit contributions
 babys-0.100
 stub-0.082
 principal-0.074
 salon-0.072
ister-0.072
Token like
Token ID588
Feature activation+1.24e-01

Pos logit contributions
ets+0.075
 textures+0.068
lated+0.066
 They+0.066
ly+0.065
Neg logit contributions
 babys-0.057
 stub-0.047
 salon-0.041
ister-0.040
 bumped-0.039
Token to
Token ID284
Feature activation-6.62e-02

Pos logit contributions
ets+0.188
 They+0.160
 textures+0.156
 sizes+0.148
 respect+0.147
Neg logit contributions
 babys-0.260
 stub-0.223
 salon-0.212
ister-0.209
fer-0.202
Token study
Token ID2050
Feature activation+9.31e-02

Pos logit contributions
 babys+0.125
 stub+0.106
 salon+0.100
ister+0.098
 poster+0.093
Neg logit contributions
ets-0.115
 They-0.097
 textures-0.096
essing-0.092
 sizes-0.092
Token the
Token ID262
Feature activation+2.62e-02

Pos logit contributions
ets+0.124
wed+0.100
 textures+0.099
essing+0.098
 They+0.097
Neg logit contributions
 babys-0.201
ister-0.171
 salon-0.170
 stub-0.167
 poster-0.167
Token who
Token ID508
Feature activation+1.09e-01

Pos logit contributions
 babys+0.137
 stub+0.116
 salon+0.110
ister+0.107
 nowhere+0.103
Neg logit contributions
ets-0.113
 They-0.093
 textures-0.093
essing-0.090
ly-0.088
Token were
Token ID547
Feature activation-9.91e-02

Pos logit contributions
ets+0.177
lated+0.153
ly+0.147
essing+0.146
 goals+0.146
Neg logit contributions
 babys-0.219
 stub-0.180
 salon-0.172
ister-0.167
 bumped-0.164
Token always
Token ID1464
Feature activation+1.05e-01

Pos logit contributions
 babys+0.179
 stub+0.151
 salon+0.142
ister+0.138
fer+0.131
Neg logit contributions
ets-0.180
 They-0.154
 textures-0.151
essing-0.146
 sizes-0.145
Token happy
Token ID3772
Feature activation+4.81e-02

Pos logit contributions
ets+0.204
 They+0.184
 textures+0.178
 sizes+0.176
 until+0.173
Neg logit contributions
 babys-0.169
 stub-0.141
 salon-0.132
ister-0.131
 poster-0.121
Token to
Token ID284
Feature activation-6.27e-02

Pos logit contributions
ets+0.073
lated+0.065
le+0.058
essing+0.058
bit+0.058
Neg logit contributions
 babys-0.101
 stub-0.084
 salon-0.080
 nowhere-0.077
ister-0.076
Token play
Token ID711
Feature activation+4.80e-02

Pos logit contributions
 babys+0.130
 stub+0.110
 salon+0.104
ister+0.103
 poster+0.098
Neg logit contributions
ets-0.100
 textures-0.081
 They-0.080
 sizes-0.078
essing-0.078
Token together
Token ID1978
Feature activation+1.00e-01

Pos logit contributions
ets+0.067
 textures+0.055
 They+0.052
 sizes+0.052
essing+0.051
Neg logit contributions
 babys-0.105
 stub-0.091
 salon-0.086
ister-0.086
 nowhere-0.084
Token.
Token ID13
Feature activation+2.67e-02

Pos logit contributions
ets+0.122
lated+0.097
 textures+0.097
essing+0.093
 They+0.093
Neg logit contributions
 babys-0.228
 stub-0.199
 salon-0.198
 nowhere-0.193
ister-0.190
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
ets+0.038
le+0.029
ly+0.029
wed+0.028
 textures+0.028
Neg logit contributions
 babys-0.062
 stub-0.052
 salon-0.051
 nowhere-0.049
ister-0.048
Token
Token ID198
Feature activation-9.92e-02

Pos logit contributions
 babys+0.236
 stub+0.203
 salon+0.201
fer+0.194
 principal+0.186
Neg logit contributions
 They-0.132
ets-0.123
 After-0.113
 until-0.111
 Every-0.100
TokenBut
Token ID1537
Feature activation+5.09e-02

Pos logit contributions
 babys+0.195
 stub+0.165
 salon+0.159
ister+0.155
 nowhere+0.150
Neg logit contributions
ets-0.170
 textures-0.137
ly-0.135
ness-0.134
essing-0.132
Token Tim
Token ID5045
Feature activation-8.83e-03

Pos logit contributions
 babys+0.099
 stub+0.083
ister+0.075
chard+0.074
 nowhere+0.073
Neg logit contributions
ets-0.105
 goals-0.083
le-0.083
 textures-0.082
ness-0.081
Token.
Token ID13
Feature activation+2.36e-02

Pos logit contributions
 babys+0.014
 stub+0.012
 nowhere+0.011
 crying+0.011
 salon+0.010
Neg logit contributions
ets-0.017
 textures-0.015
 goals-0.015
lated-0.014
 sizes-0.014
Token Tim
Token ID5045
Feature activation+1.02e-02

Pos logit contributions
ets+0.042
le+0.036
ly+0.033
essing+0.031
 respect+0.031
Neg logit contributions
 babys-0.045
 stub-0.037
-0.036
ister-0.035
 nowhere-0.034
Token was
Token ID373
Feature activation-1.25e-01

Pos logit contributions
ets+0.019
 textures+0.015
der+0.015
ales+0.015
ires+0.015
Neg logit contributions
 babys-0.018
 stub-0.017
 nowhere-0.015
 bumped-0.014
 crying-0.014
Token feeling
Token ID4203
Feature activation-5.51e-03

Pos logit contributions
 babys+0.253
ister+0.229
fer+0.222
 salon+0.220
 stub+0.219
Neg logit contributions
 They-0.166
ets-0.154
 until-0.145
 After-0.142
 for-0.139
Token sad
Token ID6507
Feature activation+6.68e-02

Pos logit contributions
 babys+0.009
 stub+0.008
 salon+0.007
ister+0.007
fer+0.007
Neg logit contributions
ets-0.011
 They-0.009
 textures-0.009
essing-0.009
 sizes-0.009
Token.
Token ID13
Feature activation+2.59e-02

Pos logit contributions
ets+0.113
bit+0.110
wed+0.104
ws+0.103
lated+0.101
Neg logit contributions
 babys-0.121
 crying-0.100
 stub-0.098
 nowhere-0.094
 salon-0.092
Token He
Token ID679
Feature activation+1.46e-01

Pos logit contributions
ets+0.023
 textures+0.015
 They+0.015
essing+0.014
ly+0.014
Neg logit contributions
 babys-0.071
 stub-0.064
 salon-0.061
ister-0.060
 nowhere-0.059
Token didn
Token ID1422
Feature activation-6.11e-02

Pos logit contributions
ets+0.271
 textures+0.232
ales+0.230
 sizes+0.228
 They+0.223
Neg logit contributions
 babys-0.258
 stub-0.241
 bumped-0.201
 nowhere-0.199
 salon-0.191
Token't
Token ID470
Feature activation-3.38e-02

Pos logit contributions
 babys+0.083
fer+0.066
 stub+0.066
chard+0.064
 salon+0.063
Neg logit contributions
 They-0.128
ets-0.120
 After-0.117
 Every-0.115
 He-0.110
Token know
Token ID760
Feature activation+8.35e-03

Pos logit contributions
 babys+0.066
 stub+0.062
 crying+0.052
 bumped+0.051
 salon+0.051
Neg logit contributions
ets-0.050
lated-0.043
ires-0.043
erve-0.042
 goals-0.042
Token she
Token ID673
Feature activation+7.77e-02

Pos logit contributions
 babys+0.061
 salon+0.052
ister+0.051
 stub+0.049
 nowhere+0.048
Neg logit contributions
ets-0.068
 textures-0.055
ws-0.055
 sizes-0.055
bit-0.054
Token would
Token ID561
Feature activation-4.90e-02

Pos logit contributions
ets+0.146
 textures+0.129
ales+0.129
lated+0.126
 They+0.125
Neg logit contributions
 babys-0.123
 stub-0.109
 nowhere-0.102
 bumped-0.095
 salon-0.095
Token always
Token ID1464
Feature activation+1.23e-01

Pos logit contributions
 babys+0.091
 stub+0.079
ister+0.077
 salon+0.076
 poster+0.068
Neg logit contributions
ets-0.084
ished-0.074
ly-0.072
lated-0.072
 textures-0.071
Token remember
Token ID3505
Feature activation+1.35e-01

Pos logit contributions
ets+0.195
lated+0.166
 After+0.161
 They+0.161
 textures+0.160
Neg logit contributions
 babys-0.239
 stub-0.205
 salon-0.195
ister-0.194
fer-0.188
Token it
Token ID340
Feature activation-4.24e-02

Pos logit contributions
ets+0.234
 They+0.194
 textures+0.193
essing+0.189
lated+0.187
Neg logit contributions
 babys-0.255
 stub-0.214
 salon-0.205
ister-0.200
 nowhere-0.198
Token.
Token ID13
Feature activation+4.00e-02

Pos logit contributions
 babys+0.088
 nowhere+0.077
 stub+0.076
ister+0.075
 salon+0.072
Neg logit contributions
ets-0.055
 textures-0.047
lated-0.047
ws-0.046
 They-0.045
Token<|endoftext|>
Token ID50256
Feature activation-9.93e-02

Pos logit contributions
ets+0.076
 textures+0.065
le+0.064
ly+0.063
essing+0.062
Neg logit contributions
 babys-0.071
 stub-0.058
 salon-0.055
ister-0.053
 principal-0.052
TokenOnce
Token ID7454
Feature activation-4.67e-02

Pos logit contributions
 babys+0.190
 stub+0.158
 salon+0.156
ister+0.147
fer+0.142
Neg logit contributions
ets-0.167
 They-0.153
 textures-0.138
 After-0.137
 until-0.137
Token upon
Token ID2402
Feature activation+2.20e-02

Pos logit contributions
 babys+0.085
 stub+0.070
 salon+0.067
fer+0.067
 principal+0.064
Neg logit contributions
ets-0.081
 They-0.074
 until-0.069
 textures-0.067
 After-0.067
Token a
Token ID257
Feature activation-3.23e-02

Pos logit contributions
ets+0.031
 They+0.028
 textures+0.026
 until+0.025
 respect+0.025
Neg logit contributions
 babys-0.049
 stub-0.041
 salon-0.041
ister-0.040
fer-0.039
Token time
Token ID640
Feature activation-5.45e-02

Pos logit contributions
 babys+0.072
 stub+0.062
 salon+0.059
ister+0.058
fer+0.056
Neg logit contributions
ets-0.045
 They-0.037
 textures-0.036
essing-0.034
 sizes-0.034
Token"
Token ID1
Feature activation-5.11e-02

Pos logit contributions
 babys+0.123
 stub+0.095
 salon+0.091
ister+0.090
Re+0.090
Neg logit contributions
ets-0.247
 textures-0.217
ness-0.216
 sizes-0.212
essing-0.211
TokenWow
Token ID22017
Feature activation+4.21e-02

Pos logit contributions
 babys+0.105
 stub+0.088
 salon+0.084
ister+0.082
 principal+0.079
Neg logit contributions
ets-0.073
 They-0.072
 textures-0.069
 sizes-0.065
 respect-0.064
Token,
Token ID11
Feature activation-3.91e-02

Pos logit contributions
ets+0.086
wed+0.079
 textures+0.078
 sizes+0.076
 After+0.074
Neg logit contributions
 babys-0.058
ister-0.051
 stub-0.047
 poster-0.046
 crying-0.043
Token Bob
Token ID5811
Feature activation+1.28e-02

Pos logit contributions
 babys+0.073
 stub+0.059
 salon+0.058
ister+0.057
 poster+0.055
Neg logit contributions
ets-0.070
 textures-0.057
wed-0.056
 They-0.056
 sizes-0.056
Tokeno
Token ID78
Feature activation-4.11e-02

Pos logit contributions
ets+0.031
 textures+0.028
 goals+0.027
 After+0.027
lated+0.027
Neg logit contributions
 babys-0.015
ister-0.012
 stub-0.011
 salon-0.009
 poster-0.009
Token,
Token ID11
Feature activation-4.16e-02

Pos logit contributions
 babys+0.072
ister+0.064
 stub+0.062
 poster+0.060
 bumped+0.057
Neg logit contributions
ets-0.070
 textures-0.066
ires-0.061
 sizes-0.060
lated-0.060
Token you
Token ID345
Feature activation+8.97e-03

Pos logit contributions
 babys+0.077
 stub+0.065
 salon+0.063
ister+0.061
 poster+0.059
Neg logit contributions
ets-0.073
 They-0.061
 textures-0.060
essing-0.059
 sizes-0.058
Token are
Token ID389
Feature activation-9.23e-02

Pos logit contributions
ets+0.014
 textures+0.013
 After+0.012
 They+0.012
lated+0.012
Neg logit contributions
 babys-0.017
 stub-0.014
ister-0.013
 poster-0.013
 bumped-0.013
Token very
Token ID845
Feature activation-9.78e-02

Pos logit contributions
 babys+0.161
 stub+0.133
 salon+0.123
ister+0.121
 nowhere+0.118
Neg logit contributions
ets-0.174
 They-0.147
 textures-0.147
ly-0.142
essing-0.142
Token brave
Token ID14802
Feature activation+7.39e-02

Pos logit contributions
 babys+0.184
 stub+0.152
ister+0.148
 salon+0.140
 poster+0.137
Neg logit contributions
ets-0.174
 textures-0.147
wed-0.142
 They-0.140
essing-0.140
Token,"
Token ID553
Feature activation-9.31e-02

Pos logit contributions
ets+0.118
lated+0.108
essing+0.102
wed+0.101
 After+0.100
Neg logit contributions
 babys-0.138
 stub-0.120
 nowhere-0.111
ister-0.110
 crying-0.107
Token"
Token ID1
Feature activation-4.26e-02

Pos logit contributions
 babys+0.154
 stub+0.130
 salon+0.124
ister+0.119
 poster+0.115
Neg logit contributions
ets-0.137
 They-0.120
 textures-0.113
 After-0.110
essing-0.109
TokenO
Token ID46
Feature activation-1.68e-02

Pos logit contributions
 babys+0.082
 stub+0.070
ister+0.065
 salon+0.064
 poster+0.061
Neg logit contributions
ets-0.065
 They-0.062
 textures-0.058
 respect-0.058
 After-0.055
Tokenw
Token ID86
Feature activation-2.87e-02

Pos logit contributions
 babys+0.013
ister+0.011
 stub+0.010
 salon+0.009
fer+0.007
Neg logit contributions
ets-0.047
 They-0.043
 textures-0.043
 sizes-0.042
 goals-0.041
Token,
Token ID11
Feature activation-7.43e-02

Pos logit contributions
 babys+0.066
 stub+0.057
 salon+0.057
 poster+0.053
 principal+0.053
Neg logit contributions
ets-0.037
 They-0.030
ly-0.029
 textures-0.029
le-0.029
Token ow
Token ID12334
Feature activation-3.02e-02

Pos logit contributions
 babys+0.145
 stub+0.126
 salon+0.124
fer+0.118
 nowhere+0.116
Neg logit contributions
ets-0.104
 They-0.101
 respect-0.092
ly-0.091
 until-0.090
Token,
Token ID11
Feature activation-7.09e-02

Pos logit contributions
 babys+0.057
 stub+0.050
ister+0.047
 salon+0.045
 bumped+0.042
Neg logit contributions
ets-0.052
 They-0.044
 textures-0.043
essing-0.042
 sizes-0.042
Token ow
Token ID12334
Feature activation-3.49e-02

Pos logit contributions
 babys+0.136
 stub+0.115
 salon+0.112
ister+0.105
fer+0.105
Neg logit contributions
ets-0.114
 They-0.103
 textures-0.096
ly-0.096
 respect-0.095
Token!
Token ID0
Feature activation+4.33e-02

Pos logit contributions
 babys+0.067
 stub+0.060
ister+0.059
 salon+0.053
 bumped+0.052
Neg logit contributions
ets-0.057
 They-0.047
 textures-0.047
essing-0.046
 After-0.046
Token It
Token ID632
Feature activation+5.16e-02

Pos logit contributions
ets+0.057
 They+0.051
 textures+0.046
essing+0.045
 respect+0.044
Neg logit contributions
 babys-0.096
 stub-0.084
 salon-0.081
ister-0.078
 nowhere-0.076
Token hurts
Token ID20406
Feature activation+1.45e-02

Pos logit contributions
ets+0.084
 They+0.070
 textures+0.069
essing+0.066
 sizes+0.066
Neg logit contributions
 babys-0.103
 stub-0.088
 salon-0.083
ister-0.081
fer-0.078
Token,
Token ID11
Feature activation-7.50e-02

Pos logit contributions
ets+0.022
 textures+0.017
essing+0.017
 goals+0.017
 sizes+0.017
Neg logit contributions
 babys-0.030
 stub-0.026
ister-0.025
 nowhere-0.024
 salon-0.023
Token with
Token ID351
Feature activation+4.02e-02

Pos logit contributions
ets+0.137
 textures+0.117
 They+0.115
lated+0.113
essing+0.110
Neg logit contributions
 babys-0.209
 stub-0.187
 salon-0.183
 nowhere-0.179
ister-0.178
Token a
Token ID257
Feature activation-7.44e-02

Pos logit contributions
ets+0.067
essing+0.056
lated+0.054
 They+0.054
 textures+0.053
Neg logit contributions
 babys-0.077
 stub-0.064
 salon-0.062
 nowhere-0.061
ister-0.059
Token shovel
Token ID33677
Feature activation-5.89e-02

Pos logit contributions
 babys+0.144
 stub+0.121
ister+0.117
 salon+0.116
fer+0.111
Neg logit contributions
ets-0.118
 They-0.103
 textures-0.100
 until-0.099
 goals-0.097
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
 babys+0.131
 stub+0.112
 salon+0.111
ister+0.107
 nowhere+0.105
Neg logit contributions
ets-0.078
 After-0.064
lated-0.063
essing-0.063
 textures-0.062
Token But
Token ID887
Feature activation+5.74e-02

Pos logit contributions
ets+0.032
 textures+0.024
le+0.024
lated+0.023
essing+0.023
Neg logit contributions
 babys-0.057
 stub-0.049
 salon-0.047
ister-0.045
 nowhere-0.045
Token his
Token ID465
Feature activation+1.28e-02

Pos logit contributions
ets+0.097
 textures+0.077
 They+0.077
essing+0.075
 sizes+0.075
Neg logit contributions
 babys-0.114
 stub-0.098
 salon-0.094
ister-0.089
 nowhere-0.088
Token daddy
Token ID35822
Feature activation-1.05e-01

Pos logit contributions
ets+0.025
 They+0.021
 textures+0.020
le+0.020
essing+0.020
Neg logit contributions
 babys-0.022
 stub-0.019
 salon-0.017
ister-0.016
 nowhere-0.016
Token said
Token ID531
Feature activation-1.01e-01

Pos logit contributions
 babys+0.185
 stub+0.155
ister+0.147
 salon+0.147
 bumped+0.140
Neg logit contributions
ets-0.191
 textures-0.174
 They-0.160
 sizes-0.160
 goals-0.160
Token no
Token ID645
Feature activation-1.00e-02

Pos logit contributions
 babys+0.194
 stub+0.164
 salon+0.155
ister+0.151
 nowhere+0.144
Neg logit contributions
ets-0.175
 textures-0.144
 They-0.144
essing-0.139
 sizes-0.138
Token because
Token ID780
Feature activation+5.30e-02

Pos logit contributions
 babys+0.020
 salon+0.016
ister+0.016
 crying+0.015
 stub+0.015
Neg logit contributions
ets-0.016
ws-0.014
wed-0.014
lated-0.014
angles-0.014
Token the
Token ID262
Feature activation+2.39e-02

Pos logit contributions
ets+0.099
essing+0.080
 textures+0.079
lated+0.079
 They+0.079
Neg logit contributions
 babys-0.096
 stub-0.081
 salon-0.077
 nowhere-0.075
ister-0.074
TokenWhen
Token ID2215
Feature activation+7.33e-02

Pos logit contributions
 babys+0.199
 stub+0.171
 salon+0.162
ister+0.158
fer+0.151
Neg logit contributions
ets-0.158
 textures-0.129
 They-0.129
essing-0.123
 sizes-0.123
Token they
Token ID484
Feature activation+7.13e-02

Pos logit contributions
ets+0.127
 textures+0.105
 They+0.105
essing+0.101
 sizes+0.101
Neg logit contributions
 babys-0.142
 stub-0.120
 salon-0.113
ister-0.111
 poster-0.105
Token arrived
Token ID5284
Feature activation-8.48e-02

Pos logit contributions
ets+0.128
 They+0.118
 until+0.107
 After+0.103
ly+0.103
Neg logit contributions
 babys-0.127
ister-0.109
fer-0.108
 stub-0.108
 salon-0.106
Token at
Token ID379
Feature activation+4.33e-02

Pos logit contributions
 babys+0.173
 stub+0.144
 salon+0.140
ister+0.138
 nowhere+0.131
Neg logit contributions
ets-0.139
 sizes-0.118
 textures-0.117
 They-0.109
bit-0.107
Token the
Token ID262
Feature activation+2.69e-02

Pos logit contributions
ets+0.055
 They+0.050
 textures+0.047
 until+0.044
 respect+0.044
Neg logit contributions
 babys-0.097
 stub-0.086
ister-0.082
 salon-0.080
fer-0.079
Token park
Token ID3952
Feature activation-7.49e-03

Pos logit contributions
ets+0.053
 They+0.046
 textures+0.046
essing+0.044
 sizes+0.044
Neg logit contributions
 babys-0.045
 stub-0.037
 salon-0.034
ister-0.033
fer-0.031
Token,
Token ID11
Feature activation-5.36e-02

Pos logit contributions
 babys+0.013
 salon+0.010
 stub+0.010
ister+0.010
 nowhere+0.009
Neg logit contributions
ets-0.015
 textures-0.013
ws-0.013
bit-0.012
wed-0.012
Token they
Token ID484
Feature activation+5.36e-02

Pos logit contributions
 babys+0.104
 stub+0.088
 salon+0.084
ister+0.081
 nowhere+0.078
Neg logit contributions
ets-0.091
 They-0.075
 textures-0.075
essing-0.072
 sizes-0.072
Token saw
Token ID2497
Feature activation-6.89e-03

Pos logit contributions
ets+0.081
 They+0.072
 until+0.068
 each+0.065
 often+0.064
Neg logit contributions
 babys-0.109
ister-0.093
 stub-0.089
 salon-0.088
fer-0.087
Token that
Token ID326
Feature activation+6.09e-02

Pos logit contributions
 babys+0.013
 stub+0.011
 salon+0.010
ister+0.010
 nowhere+0.010
Neg logit contributions
ets-0.012
 They-0.010
 textures-0.010
essing-0.010
 sizes-0.009
Token all
Token ID477
Feature activation+1.05e-01

Pos logit contributions
ets+0.101
 They+0.085
 textures+0.084
essing+0.080
 sizes+0.080
Neg logit contributions
 babys-0.120
 stub-0.102
 salon-0.097
ister-0.094
fer-0.090
Token<|endoftext|>
Token ID50256
Feature activation-9.36e-02

Pos logit contributions
ets+0.060
 textures+0.051
le+0.049
ly+0.049
essing+0.049
Neg logit contributions
 babys-0.054
 stub-0.045
ister-0.041
 salon-0.040
 nowhere-0.038
TokenOnce
Token ID7454
Feature activation-5.04e-02

Pos logit contributions
 babys+0.157
 stub+0.127
 salon+0.124
ister+0.116
fer+0.111
Neg logit contributions
ets-0.180
 They-0.165
 textures-0.153
 After-0.151
 until-0.150
Token upon
Token ID2402
Feature activation+1.52e-02

Pos logit contributions
 babys+0.086
 stub+0.070
 salon+0.067
ister+0.064
fer+0.063
Neg logit contributions
ets-0.094
 They-0.083
 textures-0.079
 until-0.079
essing-0.078
Token a
Token ID257
Feature activation-2.94e-02

Pos logit contributions
ets+0.024
 They+0.021
 textures+0.020
 until+0.019
 respect+0.019
Neg logit contributions
 babys-0.031
 stub-0.026
 salon-0.026
ister-0.025
 poster-0.024
Token time
Token ID640
Feature activation-5.20e-02

Pos logit contributions
 babys+0.062
 stub+0.054
 salon+0.050
ister+0.050
 nowhere+0.048
Neg logit contributions
ets-0.044
 They-0.037
 textures-0.036
 sizes-0.035
essing-0.034
Token,
Token ID11
Feature activation-6.34e-02

Pos logit contributions
 babys+0.146
 salon+0.132
 principal+0.130
 stub+0.130
fer+0.126
Neg logit contributions
 until-0.036
 They-0.036
ets-0.027
 for-0.026
 But-0.021
Token there
Token ID612
Feature activation+4.25e-02

Pos logit contributions
 babys+0.088
 stub+0.072
 salon+0.064
ister+0.062
 nowhere+0.061
Neg logit contributions
ets-0.143
 textures-0.123
 They-0.122
 sizes-0.120
essing-0.118
Token was
Token ID373
Feature activation-1.23e-01

Pos logit contributions
ets+0.050
 They+0.048
 textures+0.043
 until+0.042
 After+0.040
Neg logit contributions
 babys-0.100
 stub-0.084
 salon-0.084
ister-0.081
fer-0.081
Token a
Token ID257
Feature activation-7.39e-02

Pos logit contributions
 babys+0.261
 salon+0.220
 stub+0.218
ister+0.215
fer+0.206
Neg logit contributions
ets-0.183
 They-0.166
 textures-0.153
 until-0.151
 After-0.148
Token clever
Token ID14169
Feature activation+7.75e-02

Pos logit contributions
 babys+0.166
 stub+0.145
 salon+0.141
ister+0.137
fer+0.133
Neg logit contributions
ets-0.093
 They-0.080
 textures-0.075
 until-0.072
ly-0.071
Token boy
Token ID2933
Feature activation-1.28e-01

Pos logit contributions
ets+0.143
 They+0.119
 textures+0.118
 sizes+0.117
essing+0.116
Neg logit contributions
 babys-0.141
 stub-0.116
 salon-0.110
ister-0.109
 poster-0.104
Token said
Token ID531
Feature activation-9.36e-02

Pos logit contributions
 babys+0.010
 stub+0.008
 salon+0.008
ister+0.008
fer+0.007
Neg logit contributions
ets-0.010
 They-0.008
 textures-0.008
essing-0.008
 sizes-0.008
Token.
Token ID13
Feature activation+3.45e-02

Pos logit contributions
 babys+0.231
 stub+0.203
ister+0.191
 salon+0.191
fer+0.183
Neg logit contributions
ets-0.111
 textures-0.085
 sizes-0.082
 They-0.078
essing-0.077
Token "
Token ID366
Feature activation-3.32e-02

Pos logit contributions
ets+0.052
 They+0.044
 textures+0.042
essing+0.040
 until+0.040
Neg logit contributions
 babys-0.073
 stub-0.063
 salon-0.060
ister-0.059
fer-0.056
TokenI
Token ID40
Feature activation+5.51e-02

Pos logit contributions
 babys+0.064
 stub+0.052
 salon+0.050
ister+0.050
 poster+0.046
Neg logit contributions
ets-0.057
 They-0.050
 textures-0.048
 until-0.047
 respect-0.047
Token want
Token ID765
Feature activation+2.52e-02

Pos logit contributions
ets+0.083
 textures+0.072
 They+0.069
 sizes+0.069
ly+0.067
Neg logit contributions
 babys-0.115
 stub-0.101
 salon-0.092
ister-0.092
 bumped-0.089
Token to
Token ID284
Feature activation-8.91e-02

Pos logit contributions
ets+0.043
 They+0.038
 textures+0.037
 respect+0.035
ly+0.035
Neg logit contributions
 babys-0.048
 stub-0.040
 salon-0.039
ister-0.038
fer-0.036
Token play
Token ID711
Feature activation+4.17e-02

Pos logit contributions
 babys+0.184
 stub+0.157
 salon+0.150
ister+0.146
fer+0.140
Neg logit contributions
ets-0.139
 They-0.116
 textures-0.114
essing-0.109
 sizes-0.108
Token with
Token ID351
Feature activation+5.12e-02

Pos logit contributions
ets+0.066
 textures+0.056
 They+0.054
 sizes+0.054
essing+0.052
Neg logit contributions
 babys-0.083
 stub-0.072
ister-0.068
 salon-0.068
 nowhere-0.066
Token you
Token ID345
Feature activation+1.03e-03

Pos logit contributions
ets+0.090
 textures+0.075
 They+0.075
 sizes+0.073
essing+0.072
Neg logit contributions
 babys-0.097
 stub-0.082
ister-0.077
 salon-0.077
 nowhere-0.074
Token."
Token ID526
Feature activation-3.64e-02

Pos logit contributions
ets+0.001
lated+0.001
 textures+0.001
 They+0.001
 After+0.001
Neg logit contributions
 babys-0.002
 stub-0.002
 salon-0.002
ister-0.002
 nowhere-0.002
Token
Token ID198
Feature activation-1.05e-01

Pos logit contributions
 babys+0.068
 stub+0.058
 salon+0.054
ister+0.053
fer+0.050
Neg logit contributions
ets-0.064
 They-0.055
 textures-0.054
essing-0.052
 sizes-0.051
Token with
Token ID351
Feature activation+6.83e-02

Pos logit contributions
ets+0.096
 They+0.079
 until+0.074
le+0.073
ly+0.073
Neg logit contributions
 babys-0.156
 stub-0.134
 salon-0.128
ister-0.126
 principal-0.121
Token me
Token ID502
Feature activation-7.46e-02

Pos logit contributions
ets+0.087
 They+0.069
 textures+0.067
 respect+0.064
ly+0.064
Neg logit contributions
 babys-0.161
 stub-0.140
 salon-0.135
ister-0.131
fer-0.129
Token and
Token ID290
Feature activation-7.88e-03

Pos logit contributions
 babys+0.127
 stub+0.105
 salon+0.099
ister+0.096
 nowhere+0.091
Neg logit contributions
ets-0.142
 They-0.123
 textures-0.121
essing-0.117
 sizes-0.117
Token my
Token ID616
Feature activation+4.09e-02

Pos logit contributions
 babys+0.017
 stub+0.015
ister+0.014
 salon+0.014
fer+0.014
Neg logit contributions
ets-0.011
 They-0.009
 textures-0.009
 respect-0.009
 until-0.008
Token mom
Token ID1995
Feature activation-1.19e-01

Pos logit contributions
ets+0.062
 textures+0.054
 They+0.054
 goals+0.051
 sizes+0.051
Neg logit contributions
 babys-0.081
 stub-0.071
ister-0.067
 salon-0.067
fer-0.065
Token?"
Token ID1701
Feature activation-1.29e-01

Pos logit contributions
 babys+0.195
 stub+0.160
 salon+0.149
ister+0.145
fer+0.137
Neg logit contributions
ets-0.236
 They-0.205
 textures-0.201
essing-0.195
 sizes-0.194
Token she
Token ID673
Feature activation+5.46e-02

Pos logit contributions
 babys+0.266
 stub+0.226
 salon+0.218
ister+0.214
fer+0.206
Neg logit contributions
ets-0.194
 They-0.174
 textures-0.160
 until-0.154
 After-0.154
Token says
Token ID1139
Feature activation-9.79e-02

Pos logit contributions
ets+0.068
 They+0.056
 textures+0.053
ly+0.050
le+0.050
Neg logit contributions
 babys-0.129
 stub-0.113
 salon-0.109
ister-0.108
fer-0.104
Token.
Token ID13
Feature activation+2.96e-02

Pos logit contributions
 babys+0.260
 stub+0.230
 salon+0.221
ister+0.218
fer+0.211
Neg logit contributions
ets-0.095
 textures-0.068
 They-0.066
 sizes-0.064
essing-0.062
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
 They+0.039
ets+0.032
 After+0.030
 He+0.030
 But+0.029
Neg logit contributions
 babys-0.070
 salon-0.063
fer-0.060
 stub-0.059
ister-0.059
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
 babys+0.220
 stub+0.187
 salon+0.182
fer+0.171
ister+0.169
Neg logit contributions
ets-0.165
 They-0.152
 until-0.135
 After-0.134
 textures-0.132
Token.
Token ID13
Feature activation+3.48e-02

Pos logit contributions
 babys+0.021
 stub+0.018
 salon+0.018
ister+0.017
 nowhere+0.017
Neg logit contributions
ets-0.011
 They-0.009
 textures-0.009
essing-0.008
 sizes-0.008
Token
Token ID198
Feature activation-9.84e-02

Pos logit contributions
ets+0.050
 They+0.045
 textures+0.040
 After+0.040
essing+0.039
Neg logit contributions
 babys-0.076
 stub-0.066
 salon-0.062
ister-0.061
fer-0.060
Token
Token ID198
Feature activation-9.53e-02

Pos logit contributions
 babys+0.220
 stub+0.189
 salon+0.181
fer+0.178
chard+0.170
Neg logit contributions
ets-0.136
 They-0.132
 After-0.114
 until-0.112
 respect-0.105
TokenTom
Token ID13787
Feature activation+1.96e-03

Pos logit contributions
 babys+0.163
 stub+0.135
 salon+0.127
ister+0.123
fer+0.116
Neg logit contributions
ets-0.183
 They-0.159
 textures-0.156
essing-0.150
 sizes-0.150
Token said
Token ID531
Feature activation-8.76e-02

Pos logit contributions
ets+0.003
 textures+0.003
lated+0.003
 goals+0.003
 sizes+0.003
Neg logit contributions
 babys-0.004
 stub-0.003
 salon-0.003
ister-0.003
 nowhere-0.003
Token,
Token ID11
Feature activation-8.75e-02

Pos logit contributions
 babys+0.197
 stub+0.171
 salon+0.166
ister+0.159
 nowhere+0.157
Neg logit contributions
ets-0.115
 They-0.104
ly-0.096
 until-0.094
 textures-0.090
Token "
Token ID366
Feature activation-3.60e-02

Pos logit contributions
 babys+0.184
 stub+0.160
 salon+0.155
ister+0.149
fer+0.143
Neg logit contributions
ets-0.126
 They-0.118
 until-0.106
 textures-0.104
 After-0.103
TokenLet
Token ID5756
Feature activation+5.35e-02

Pos logit contributions
 babys+0.062
 stub+0.053
 salon+0.049
ister+0.047
 nowhere+0.045
Neg logit contributions
ets-0.069
 textures-0.057
 They-0.056
essing-0.056
ly-0.055
Token's
Token ID338
Feature activation-1.39e-02

Pos logit contributions
ets+0.056
 They+0.046
ly+0.042
le+0.040
essing+0.039
Neg logit contributions
 babys-0.137
 stub-0.120
 salon-0.118
fer-0.114
ister-0.114
Token go
Token ID467
Feature activation-3.47e-02

Pos logit contributions
 babys+0.027
 stub+0.022
 salon+0.021
ister+0.021
+0.020
Neg logit contributions
ets-0.024
ly-0.020
 textures-0.019
lated-0.019
 sizes-0.019
Token for
Token ID329
Feature activation+3.34e-02

Pos logit contributions
 babys+0.065
 stub+0.054
 salon+0.050
ister+0.050
 poster+0.048
Neg logit contributions
ets-0.060
 textures-0.053
 sizes-0.051
 goals-0.050
essing-0.050
Token box
Token ID3091
Feature activation-8.29e-02

Pos logit contributions
ets+0.053
 textures+0.051
 respect+0.050
 They+0.049
 sizes+0.048
Neg logit contributions
 babys-0.029
 stub-0.026
fer-0.024
ister-0.024
 salon-0.023
Token and
Token ID290
Feature activation+2.03e-04

Pos logit contributions
 babys+0.145
 salon+0.135
 nowhere+0.120
ister+0.120
 poster+0.118
Neg logit contributions
ets-0.118
bit-0.114
 After-0.114
 textures-0.114
ws-0.111
Token we
Token ID356
Feature activation+1.03e-02

Pos logit contributions
ets+0.000
 They+0.000
 textures+0.000
 sizes+0.000
 respect+0.000
Neg logit contributions
 babys-0.000
 stub-0.000
 salon-0.000
ister-0.000
fer-0.000
Token found
Token ID1043
Feature activation-1.09e-02

Pos logit contributions
ets+0.018
ires+0.018
lated+0.018
 After+0.017
ales+0.017
Neg logit contributions
 babys-0.017
 stub-0.015
 bumped-0.014
 pin-0.012
 salon-0.012
Token this
Token ID428
Feature activation+1.93e-02

Pos logit contributions
 babys+0.017
 nowhere+0.014
 stub+0.014
 poster+0.013
 salon+0.013
Neg logit contributions
ets-0.021
 textures-0.018
 sizes-0.018
lated-0.018
 They-0.018
Token photo
Token ID4590
Feature activation-9.33e-02

Pos logit contributions
ets+0.033
 They+0.028
 textures+0.027
 sizes+0.026
 until+0.026
Neg logit contributions
 babys-0.037
 stub-0.031
 salon-0.029
ister-0.029
fer-0.028
Token.
Token ID13
Feature activation+5.47e-02

Pos logit contributions
 babys+0.222
 salon+0.193
 stub+0.192
ister+0.187
 nowhere+0.183
Neg logit contributions
ets-0.102
 textures-0.087
 After-0.081
lated-0.080
 They-0.079
Token We
Token ID775
Feature activation+6.92e-02

Pos logit contributions
ets+0.078
 textures+0.061
ly+0.060
le+0.059
wed+0.058
Neg logit contributions
 babys-0.121
 stub-0.104
 salon-0.097
ister-0.097
 poster-0.096
Token wanted
Token ID2227
Feature activation+2.24e-02

Pos logit contributions
ets+0.124
lated+0.110
 textures+0.109
ires+0.109
 After+0.109
Neg logit contributions
 babys-0.123
 stub-0.108
 bumped-0.098
 salon-0.088
 nowhere-0.087
Token to
Token ID284
Feature activation-9.30e-02

Pos logit contributions
ets+0.039
 They+0.032
 textures+0.032
essing+0.031
 sizes+0.031
Neg logit contributions
 babys-0.043
 stub-0.036
 salon-0.034
ister-0.033
 nowhere-0.032
Token see
Token ID766
Feature activation+1.27e-02

Pos logit contributions
 babys+0.197
 stub+0.170
 salon+0.162
ister+0.158
fer+0.152
Neg logit contributions
ets-0.140
 They-0.116
 textures-0.113
essing-0.108
 sizes-0.107
Token to
Token ID284
Feature activation-1.02e-01

Pos logit contributions
ets+0.022
 They+0.019
 textures+0.019
ly+0.018
 respect+0.018
Neg logit contributions
 babys-0.024
 stub-0.020
 salon-0.019
ister-0.019
fer-0.018
Token come
Token ID1282
Feature activation-9.26e-02

Pos logit contributions
 babys+0.217
 stub+0.187
 salon+0.179
ister+0.174
 nowhere+0.167
Neg logit contributions
ets-0.151
 They-0.126
 textures-0.123
essing-0.116
 respect-0.116
Token with
Token ID351
Feature activation+4.11e-02

Pos logit contributions
 babys+0.188
 stub+0.161
ister+0.149
 salon+0.148
 poster+0.144
Neg logit contributions
ets-0.149
 textures-0.123
 sizes-0.118
 They-0.117
lated-0.116
Token you
Token ID345
Feature activation-1.23e-02

Pos logit contributions
ets+0.055
 They+0.045
 textures+0.042
ly+0.041
 until+0.041
Neg logit contributions
 babys-0.095
 stub-0.082
 salon-0.079
ister-0.077
fer-0.075
Token!"
Token ID2474
Feature activation-7.58e-02

Pos logit contributions
 babys+0.029
 stub+0.025
ister+0.025
 salon+0.025
 poster+0.024
Neg logit contributions
ets-0.015
 textures-0.012
lated-0.011
wed-0.011
 They-0.011
Token
Token ID198
Feature activation-1.16e-01

Pos logit contributions
 babys+0.149
 stub+0.119
 salon+0.116
ister+0.115
 poster+0.111
Neg logit contributions
ets-0.127
 textures-0.106
lated-0.103
essing-0.103
le-0.102
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
 babys+0.248
 stub+0.211
 salon+0.209
fer+0.197
ister+0.191
Neg logit contributions
ets-0.165
 They-0.155
 After-0.140
 until-0.138
 textures-0.131
TokenSo
Token ID2396
Feature activation+4.76e-02

Pos logit contributions
 babys+0.191
 stub+0.161
 salon+0.156
ister+0.156
fer+0.145
Neg logit contributions
ets-0.198
 textures-0.161
ly-0.160
essing-0.159
ness-0.158
Token,
Token ID11
Feature activation-6.74e-02

Pos logit contributions
ets+0.115
ws+0.101
ales+0.099
wed+0.098
 textures+0.098
Neg logit contributions
 babys-0.057
ister-0.043
 stub-0.042
lyss-0.039
 poster-0.038
Token the
Token ID262
Feature activation+1.31e-03

Pos logit contributions
 babys+0.124
 stub+0.103
 salon+0.097
ister+0.095
 nowhere+0.093
Neg logit contributions
ets-0.125
essing-0.101
 textures-0.101
wed-0.098
 sizes-0.098
Token p
Token ID279
Feature activation-6.95e-02

Pos logit contributions
ets+0.002
 They+0.002
 textures+0.001
 until+0.001
ly+0.001
Neg logit contributions
 babys-0.003
 stub-0.002
 salon-0.002
ister-0.002
fer-0.002