TOP ACTIVATIONS
MAX = 0.132

time playing with her or nam ents and making her special
the rest of the or nam ents onto the tree .
she had with her or nam ents . <|endoftext|> Once upon
who liked to collect or nam ents . Everywhere she went
never played with the or nam ents again . They still
went she searched for or nam ents , and the more
All of these lovely or nam ents reminded him of the
to help sort the or nam ents . She picked up
he especially liked the or nam ents he kept around .
to look at the or nam ents on the tree .
take one of the or nam ents outside for a walk
box full of beautiful or nam ents .
many colors . Some or nam ents were round , some
not nice ." Un cle Tom laughed . He
before . " Un ic orn is a rare
a tree with shiny or nam ents hanging from its branches
at all the different or nam ents and adm iring the
a box of shiny or nam ents that spark led in
he noticed some other cater pill ars stretching towards it too
can we have some or nam ents for our snow man

MIN ACTIVATIONS
MIN = -0.135

so beautiful inside and the fringe from the cut shells made
replied with a gentle ' yip '. The little
the cars stopped and the pedestrian light turned green . Then
and books . They see alt ars and offerings and priests
" We are the weapon creators ! We can stop the
into two bowls , then voted for their favourite . Toby
smiled and said , " Church is so nice mom my
the ground that said " short cut ". She thought it
little one 's costume was voted the best ! Everyone cheered
- a shirt and pants combo - and brushed his hair
So , with artificial so aps , they made
yellow and green until the formerly color less walls seemed to
on the airplane said " 747 ". The people were scared
They chase the car - nos aur around the room ,
. " A car - nos aur !" They
making breakfast . They smelled pancakes and syrup . They were
said his mom . " Flags go up there to wave
didn 't know what " nos y " meant , so
?" Mom yells . " YOU ARE MA KING A M
she could help the tea del ive rer by taking the

INTERVAL 0.065 - 0.132
CONTAINS 0.206%

on long car trips to many different places . One day
the handles and g iggle as she went up , up
and tug ged as hard as she could , but the
The b unn ies looked at each other
were burying something from long ago that made them feel sad

INTERVAL -0.002 - 0.065
CONTAINS 51.184%

the king knew that he could always count on the wizard
catch fish . He liked his job . One
beach . Jane looked at Joe , who was jumping up
shining penny and picked it up . She smiled and said
baby 's tears slowly stopped and the baby fell asleep .

INTERVAL -0.069 - -0.002
CONTAINS 48.519%

the top . They found a big bag of flour and
One day , Sara finds a big bottle of oil in
a fork ! From that day Bob knew what a fork
Mia asks . She takes the shovel from Ben and fills
L ily 's mom my was so touched by

INTERVAL -0.135 - -0.069
CONTAINS 0.091%

put on her p aj amas . Mom my read her
share your food and make us happy ." The
. " He is making us scared ." The
her mom , who was sitting on a bench . She
front of him . He tri pped and fell . He
Token time
Token ID640
Feature activation+2.49e-03

Pos logit contributions
age+0.004
est+0.003
+0.003
tted+0.003
 ok+0.003
Neg logit contributions
yles-0.004
 brushes-0.004
 passports-0.004
ries-0.003
outed-0.003
Token playing
Token ID2712
Feature activation-2.38e-02

Pos logit contributions
yles+0.005
outing+0.004
ries+0.004
outed+0.004
ateful+0.004
Neg logit contributions
age-0.004
est-0.004
-0.003
 ok-0.003
ze-0.003
Token with
Token ID351
Feature activation+4.73e-03

Pos logit contributions
age+0.041
est+0.032
 ok+0.030
+0.028
sy+0.026
Neg logit contributions
yles-0.043
ries-0.039
 their-0.038
nam-0.037
 they-0.037
Token her
Token ID607
Feature activation+1.14e-02

Pos logit contributions
yles+0.006
outing+0.006
outed+0.005
ateful+0.005
eling+0.005
Neg logit contributions
age-0.011
est-0.010
-0.009
 ok-0.009
ze-0.008
Token or
Token ID393
Feature activation-1.63e-02

Pos logit contributions
yles+0.020
outing+0.018
ries+0.018
nam+0.017
outed+0.017
Neg logit contributions
age-0.022
est-0.018
-0.016
 ok-0.015
ze-0.015
Tokennam
Token ID7402
Feature activation+1.32e-01

Pos logit contributions
age+0.034
est+0.030
+0.027
 ok+0.026
ze+0.025
Neg logit contributions
yles-0.024
outing-0.023
outed-0.021
ries-0.021
ateful-0.020
Tokenents
Token ID658
Feature activation+5.54e-02

Pos logit contributions
yles+0.123
outing+0.107
eling+0.099
ries+0.096
outed+0.096
Neg logit contributions
age-0.347
est-0.310
-0.293
 ok-0.272
sy-0.267
Token and
Token ID290
Feature activation-1.59e-03

Pos logit contributions
yles+0.123
outing+0.115
outed+0.110
ateful+0.109
ries+0.109
Neg logit contributions
age-0.078
est-0.064
-0.054
 ok-0.049
ze-0.046
Token making
Token ID1642
Feature activation-2.90e-02

Pos logit contributions
age+0.003
est+0.003
+0.003
 ok+0.002
 best+0.002
Neg logit contributions
yles-0.003
outing-0.002
outed-0.002
ateful-0.002
eling-0.002
Token her
Token ID607
Feature activation+9.75e-03

Pos logit contributions
age+0.057
est+0.049
+0.044
 ok+0.042
ze+0.040
Neg logit contributions
yles-0.048
outing-0.044
ries-0.041
outed-0.041
ateful-0.041
Token special
Token ID2041
Feature activation+2.28e-03

Pos logit contributions
yles+0.018
nam+0.016
outing+0.016
outed+0.016
ries+0.016
Neg logit contributions
age-0.017
est-0.014
-0.012
 ok-0.012
sy-0.011
Token the
Token ID262
Feature activation-9.30e-03

Pos logit contributions
yles+0.003
outing+0.003
ries+0.003
outed+0.002
ateful+0.002
Neg logit contributions
age-0.005
est-0.004
-0.004
 ok-0.003
ze-0.003
Token rest
Token ID1334
Feature activation+1.04e-02

Pos logit contributions
age+0.019
est+0.016
 ok+0.014
sy+0.014
nob+0.013
Neg logit contributions
yles-0.013
nam-0.013
outing-0.013
ries-0.012
ateful-0.012
Token of
Token ID286
Feature activation+2.43e-02

Pos logit contributions
yles+0.022
outing+0.020
outed+0.019
ateful+0.019
ries+0.019
Neg logit contributions
age-0.016
est-0.013
-0.011
 ok-0.010
ze-0.010
Token the
Token ID262
Feature activation-9.82e-03

Pos logit contributions
outing+0.043
yles+0.043
outed+0.041
ateful+0.038
eling+0.037
Neg logit contributions
age-0.040
est-0.035
-0.034
 right-0.031
 ok-0.031
Token or
Token ID393
Feature activation-2.00e-02

Pos logit contributions
age+0.019
est+0.017
 ok+0.014
+0.013
sy+0.013
Neg logit contributions
yles-0.015
nam-0.014
outing-0.014
ries-0.014
 spill-0.014
Tokennam
Token ID7402
Feature activation+1.30e-01

Pos logit contributions
age+0.037
est+0.032
+0.030
 ok+0.028
ze+0.027
Neg logit contributions
yles-0.034
outing-0.032
outed-0.030
ries-0.030
ateful-0.029
Tokenents
Token ID658
Feature activation+5.21e-02

Pos logit contributions
yles+0.121
outing+0.103
eling+0.099
ries+0.094
outed+0.094
Neg logit contributions
age-0.339
est-0.299
-0.289
 ok-0.264
ench-0.261
Token onto
Token ID4291
Feature activation+1.52e-02

Pos logit contributions
yles+0.114
outing+0.106
outed+0.102
ateful+0.102
ries+0.101
Neg logit contributions
age-0.075
est-0.062
-0.053
 ok-0.048
ze-0.045
Token the
Token ID262
Feature activation-4.94e-03

Pos logit contributions
yles+0.022
outing+0.020
ries+0.019
ateful+0.019
outed+0.018
Neg logit contributions
age-0.032
est-0.029
-0.025
 ok-0.024
ze-0.024
Token tree
Token ID5509
Feature activation+3.78e-02

Pos logit contributions
age+0.009
est+0.008
 ok+0.007
ench+0.007
iver+0.007
Neg logit contributions
nam-0.007
yles-0.007
 salon-0.007
 brushes-0.006
 spill-0.006
Token.
Token ID13
Feature activation-3.92e-03

Pos logit contributions
yles+0.076
outing+0.072
ries+0.068
outed+0.068
ateful+0.067
Neg logit contributions
age-0.058
est-0.049
-0.041
 ok-0.040
ze-0.037
Token she
Token ID673
Feature activation-1.68e-04

Pos logit contributions
age+0.010
est+0.009
+0.008
 ok+0.008
ze+0.007
Neg logit contributions
yles-0.007
outing-0.007
outed-0.006
ateful-0.006
ries-0.006
Token had
Token ID550
Feature activation-3.78e-03

Pos logit contributions
age+0.000
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.000
outing-0.000
ries-0.000
outed-0.000
ateful-0.000
Token with
Token ID351
Feature activation+9.20e-03

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
ze+0.004
Neg logit contributions
yles-0.007
outing-0.007
outed-0.006
ries-0.006
ateful-0.006
Token her
Token ID607
Feature activation+1.19e-02

Pos logit contributions
yles+0.014
outing+0.013
outed+0.012
ateful+0.012
eling+0.011
Neg logit contributions
age-0.019
est-0.017
-0.016
 ok-0.015
 best-0.015
Token or
Token ID393
Feature activation-1.21e-02

Pos logit contributions
yles+0.023
outing+0.021
ries+0.020
outed+0.020
ateful+0.020
Neg logit contributions
age-0.021
est-0.017
-0.015
 ok-0.014
ze-0.014
Tokennam
Token ID7402
Feature activation+1.28e-01

Pos logit contributions
age+0.023
est+0.020
+0.019
 ok+0.018
 best+0.017
Neg logit contributions
yles-0.020
outing-0.019
outed-0.018
ries-0.017
ateful-0.017
Tokenents
Token ID658
Feature activation+5.32e-02

Pos logit contributions
yles+0.112
outing+0.095
eling+0.085
outed+0.085
ries+0.085
Neg logit contributions
age-0.347
est-0.311
-0.295
 ok-0.277
ze-0.271
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
yles+0.112
outing+0.105
outed+0.100
ries+0.100
ateful+0.100
Neg logit contributions
age-0.079
est-0.066
-0.056
 ok-0.052
ze-0.049
Token<|endoftext|>
Token ID50256
Feature activation+3.59e-02

Pos logit contributions
yles+0.008
outing+0.007
outed+0.007
ries+0.007
ateful+0.007
Neg logit contributions
age-0.007
est-0.006
ze-0.005
 ok-0.005
-0.004
TokenOnce
Token ID7454
Feature activation+2.86e-02

Pos logit contributions
yles+0.059
ries+0.051
outing+0.049
ila+0.049
outed+0.048
Neg logit contributions
age-0.069
est-0.060
 ok-0.054
ze-0.052
 biggest-0.048
Token upon
Token ID2402
Feature activation-1.32e-03

Pos logit contributions
yles+0.043
outing+0.038
eling+0.037
ries+0.037
ateful+0.036
Neg logit contributions
age-0.056
est-0.052
-0.049
 ok-0.046
 best-0.046
Token who
Token ID508
Feature activation-1.10e-03

Pos logit contributions
age+0.035
est+0.031
 ok+0.027
+0.026
 biggest+0.025
Neg logit contributions
yles-0.030
outing-0.029
ries-0.027
ateful-0.027
outed-0.027
Token liked
Token ID8288
Feature activation+3.51e-03

Pos logit contributions
age+0.002
est+0.002
+0.002
 ok+0.001
ze+0.001
Neg logit contributions
yles-0.002
outing-0.002
outed-0.002
ateful-0.002
eling-0.002
Token to
Token ID284
Feature activation+2.47e-02

Pos logit contributions
yles+0.008
outing+0.008
eling+0.007
outed+0.007
ateful+0.007
Neg logit contributions
age-0.004
est-0.003
-0.003
ze-0.003
 right-0.003
Token collect
Token ID2824
Feature activation+2.01e-02

Pos logit contributions
yles+0.039
outing+0.035
ries+0.034
ateful+0.034
nam+0.033
Neg logit contributions
age-0.048
est-0.042
-0.037
 ok-0.036
sy-0.034
Token or
Token ID393
Feature activation-1.10e-02

Pos logit contributions
yles+0.034
outing+0.031
ries+0.030
outed+0.029
ateful+0.029
Neg logit contributions
age-0.039
est-0.033
-0.030
 ok-0.029
ze-0.027
Tokennam
Token ID7402
Feature activation+1.28e-01

Pos logit contributions
age+0.030
est+0.028
+0.027
 ok+0.026
 biggest+0.026
Neg logit contributions
yles-0.008
outing-0.007
outed-0.006
ries-0.006
ateful-0.005
Tokenents
Token ID658
Feature activation+5.38e-02

Pos logit contributions
yles+0.118
outing+0.104
eling+0.098
outed+0.094
ateful+0.092
Neg logit contributions
age-0.333
est-0.298
-0.282
 ok-0.259
ench-0.257
Token.
Token ID13
Feature activation-2.18e-03

Pos logit contributions
yles+0.124
outing+0.116
outed+0.112
ateful+0.110
eling+0.109
Neg logit contributions
age-0.073
est-0.059
-0.048
 ok-0.043
ze-0.040
Token Everywhere
Token ID48201
Feature activation-3.12e-02

Pos logit contributions
age+0.004
est+0.003
+0.003
 ok+0.003
ze+0.003
Neg logit contributions
yles-0.004
outing-0.003
outed-0.003
ries-0.003
ateful-0.003
Token she
Token ID673
Feature activation-4.84e-04

Pos logit contributions
age+0.072
est+0.068
+0.065
 best+0.059
 ok+0.058
Neg logit contributions
yles-0.038
outing-0.038
outed-0.032
ateful-0.032
eling-0.031
Token went
Token ID1816
Feature activation+3.44e-03

Pos logit contributions
age+0.001
est+0.001
+0.001
nob+0.001
sy+0.001
Neg logit contributions
yles-0.001
outing-0.001
ries-0.001
ateful-0.001
outed-0.001
Token never
Token ID1239
Feature activation-4.13e-02

Pos logit contributions
age+0.007
+0.005
est+0.005
 ok+0.005
 best+0.004
Neg logit contributions
yles-0.009
outing-0.009
ries-0.008
outed-0.008
eling-0.008
Token played
Token ID2826
Feature activation-1.42e-02

Pos logit contributions
age+0.078
+0.068
est+0.067
 ok+0.060
 right+0.057
Neg logit contributions
yles-0.073
outing-0.067
ries-0.064
outed-0.062
ateful-0.060
Token with
Token ID351
Feature activation+1.51e-03

Pos logit contributions
age+0.024
est+0.020
+0.019
sy+0.016
>+0.015
Neg logit contributions
yles-0.026
ries-0.024
outing-0.022
 their-0.021
 spill-0.021
Token the
Token ID262
Feature activation-6.68e-03

Pos logit contributions
yles+0.002
outing+0.002
outed+0.002
ateful+0.002
eling+0.002
Neg logit contributions
age-0.003
est-0.003
 ok-0.002
-0.002
 best-0.002
Token or
Token ID393
Feature activation-2.35e-02

Pos logit contributions
age+0.014
est+0.012
+0.011
sy+0.010
 ok+0.010
Neg logit contributions
yles-0.009
ries-0.009
outing-0.008
nam-0.008
 brushes-0.008
Tokennam
Token ID7402
Feature activation+1.28e-01

Pos logit contributions
age+0.041
est+0.034
+0.033
 ok+0.031
 back+0.030
Neg logit contributions
yles-0.043
outing-0.040
outed-0.038
ries-0.036
ateful-0.036
Tokenents
Token ID658
Feature activation+5.05e-02

Pos logit contributions
yles+0.113
outing+0.096
eling+0.087
outed+0.086
ries+0.085
Neg logit contributions
age-0.346
est-0.309
-0.291
 ok-0.273
ze-0.268
Token again
Token ID757
Feature activation-1.86e-02

Pos logit contributions
yles+0.121
outing+0.114
outed+0.110
ries+0.109
ateful+0.109
Neg logit contributions
age-0.061
est-0.049
-0.040
 ok-0.036
ze-0.033
Token.
Token ID13
Feature activation-9.93e-04

Pos logit contributions
age+0.025
est+0.021
+0.018
 ok+0.016
ze+0.015
Neg logit contributions
yles-0.042
outing-0.039
outed-0.038
ries-0.037
ateful-0.037
Token They
Token ID1119
Feature activation-1.52e-03

Pos logit contributions
age+0.001
est+0.001
+0.001
 ok+0.001
ze+0.001
Neg logit contributions
yles-0.002
outing-0.002
ries-0.002
outed-0.002
ateful-0.002
Token still
Token ID991
Feature activation+1.47e-02

Pos logit contributions
age+0.003
+0.002
est+0.002
 ok+0.002
 best+0.002
Neg logit contributions
yles-0.003
outing-0.003
ries-0.003
outed-0.003
ateful-0.003
Token went
Token ID1816
Feature activation+3.44e-03

Pos logit contributions
age+0.001
est+0.001
+0.001
nob+0.001
sy+0.001
Neg logit contributions
yles-0.001
outing-0.001
ries-0.001
ateful-0.001
outed-0.001
Token she
Token ID673
Feature activation-3.27e-03

Pos logit contributions
yles+0.007
ries+0.007
outing+0.006
ateful+0.006
nam+0.006
Neg logit contributions
age-0.005
est-0.004
 ok-0.004
ze-0.004
-0.003
Token searched
Token ID16499
Feature activation-1.39e-02

Pos logit contributions
age+0.006
est+0.005
+0.004
ze+0.004
 ok+0.004
Neg logit contributions
yles-0.006
outing-0.006
ries-0.005
ateful-0.005
outed-0.005
Token for
Token ID329
Feature activation-1.67e-02

Pos logit contributions
age+0.018
est+0.016
+0.013
 ok+0.012
 best+0.012
Neg logit contributions
yles-0.032
outing-0.030
outed-0.028
ateful-0.028
ries-0.027
Token or
Token ID393
Feature activation-1.95e-02

Pos logit contributions
age+0.029
est+0.027
+0.022
 ok+0.022
 best+0.021
Neg logit contributions
yles-0.030
outing-0.029
outed-0.027
ateful-0.026
eling-0.025
Tokennam
Token ID7402
Feature activation+1.27e-01

Pos logit contributions
age+0.052
est+0.048
+0.046
 right+0.046
 ok+0.046
Neg logit contributions
yles-0.016
outing-0.012
ries-0.012
outed-0.011
irs-0.010
Tokenents
Token ID658
Feature activation+4.87e-02

Pos logit contributions
yles+0.111
outing+0.095
eling+0.085
outed+0.084
ries+0.083
Neg logit contributions
age-0.342
est-0.307
-0.289
 ok-0.272
ze-0.265
Token,
Token ID11
Feature activation-3.73e-03

Pos logit contributions
yles+0.114
outing+0.106
outed+0.103
ateful+0.102
eling+0.101
Neg logit contributions
age-0.065
est-0.053
-0.042
 ok-0.038
 best-0.035
Token and
Token ID290
Feature activation-2.96e-04

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
 best+0.005
Neg logit contributions
yles-0.007
outing-0.006
outed-0.006
ateful-0.006
ries-0.006
Token the
Token ID262
Feature activation-5.12e-03

Pos logit contributions
age+0.001
est+0.000
+0.000
 best+0.000
 ok+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.000
ateful-0.000
eling-0.000
Token more
Token ID517
Feature activation+9.46e-03

Pos logit contributions
age+0.010
est+0.008
+0.008
sy+0.007
ze+0.007
Neg logit contributions
nam-0.008
yles-0.008
outing-0.007
ries-0.007
ateful-0.007
Token All
Token ID1439
Feature activation+4.47e-02

Pos logit contributions
age+0.004
est+0.003
ze+0.003
 ok+0.003
sy+0.003
Neg logit contributions
yles-0.004
outing-0.004
outed-0.004
ries-0.003
ateful-0.003
Token of
Token ID286
Feature activation+2.53e-02

Pos logit contributions
yles+0.094
outing+0.088
outed+0.082
nam+0.082
ateful+0.082
Neg logit contributions
age-0.068
est-0.062
-0.053
 ok-0.045
 best-0.044
Token these
Token ID777
Feature activation-1.72e-02

Pos logit contributions
outing+0.051
yles+0.051
outed+0.049
ateful+0.044
ours+0.044
Neg logit contributions
age-0.036
est-0.033
-0.030
 ok-0.027
 best-0.027
Token lovely
Token ID14081
Feature activation-1.37e-02

Pos logit contributions
age+0.032
est+0.030
+0.025
 ok+0.025
 best+0.025
Neg logit contributions
yles-0.029
outing-0.027
ateful-0.024
outed-0.024
ries-0.024
Token or
Token ID393
Feature activation-1.77e-02

Pos logit contributions
age+0.026
est+0.022
+0.020
 ok+0.019
ze+0.018
Neg logit contributions
yles-0.024
outing-0.022
ries-0.021
outed-0.021
ateful-0.020
Tokennam
Token ID7402
Feature activation+1.26e-01

Pos logit contributions
age+0.043
est+0.041
+0.039
 ok+0.037
 best+0.036
Neg logit contributions
yles-0.018
outing-0.016
outed-0.015
ries-0.013
ateful-0.013
Tokenents
Token ID658
Feature activation+5.13e-02

Pos logit contributions
yles+0.118
outing+0.102
eling+0.096
outed+0.093
ateful+0.092
Neg logit contributions
age-0.331
est-0.293
-0.279
 ok-0.255
sy-0.254
Token reminded
Token ID14516
Feature activation-3.16e-02

Pos logit contributions
yles+0.092
outing+0.084
ateful+0.080
outed+0.080
nam+0.078
Neg logit contributions
age-0.096
est-0.084
-0.073
 ok-0.067
ze-0.065
Token him
Token ID683
Feature activation-1.13e-02

Pos logit contributions
age+0.066
est+0.059
+0.053
 ok+0.051
ze+0.048
Neg logit contributions
yles-0.048
outing-0.044
outed-0.041
ateful-0.040
ries-0.040
Token of
Token ID286
Feature activation+2.87e-02

Pos logit contributions
age+0.022
est+0.019
+0.017
 ok+0.016
ze+0.016
Neg logit contributions
yles-0.018
outing-0.017
ries-0.016
outed-0.015
ateful-0.015
Token the
Token ID262
Feature activation-6.38e-03

Pos logit contributions
yles+0.050
outing+0.049
outed+0.046
ateful+0.042
ries+0.042
Neg logit contributions
age-0.050
est-0.046
-0.041
 ok-0.041
 best-0.039
Token to
Token ID284
Feature activation+1.64e-02

Pos logit contributions
yles+0.051
outing+0.047
ries+0.045
outed+0.044
ateful+0.044
Neg logit contributions
age-0.048
est-0.041
-0.035
 ok-0.033
ze-0.032
Token help
Token ID1037
Feature activation+6.53e-03

Pos logit contributions
yles+0.025
ateful+0.022
outing+0.022
 spill+0.021
ila+0.021
Neg logit contributions
age-0.030
est-0.028
 ok-0.023
-0.023
sy-0.023
Token sort
Token ID3297
Feature activation-3.10e-03

Pos logit contributions
yles+0.009
outing+0.008
ries+0.008
ateful+0.008
nam+0.008
Neg logit contributions
age-0.014
est-0.012
-0.011
 ok-0.011
ze-0.010
Token the
Token ID262
Feature activation-8.58e-03

Pos logit contributions
age+0.007
est+0.006
+0.006
 ok+0.006
ze+0.005
Neg logit contributions
yles-0.004
outing-0.004
ries-0.003
ateful-0.003
outed-0.003
Token or
Token ID393
Feature activation-2.15e-02

Pos logit contributions
age+0.019
est+0.015
+0.013
 ok+0.013
ze+0.013
Neg logit contributions
yles-0.013
outing-0.012
nam-0.012
ries-0.012
outed-0.011
Tokennam
Token ID7402
Feature activation+1.26e-01

Pos logit contributions
age+0.046
est+0.042
+0.040
 ok+0.039
 right+0.037
Neg logit contributions
yles-0.029
outing-0.026
ries-0.025
outed-0.024
ateful-0.023
Tokenents
Token ID658
Feature activation+5.01e-02

Pos logit contributions
yles+0.116
outing+0.100
eling+0.091
outed+0.090
ries+0.089
Neg logit contributions
age-0.333
est-0.300
-0.283
 ok-0.264
ze-0.257
Token.
Token ID13
Feature activation-4.13e-03

Pos logit contributions
yles+0.109
outing+0.102
outed+0.098
ateful+0.097
ries+0.097
Neg logit contributions
age-0.072
est-0.060
-0.051
 ok-0.046
ze-0.043
Token She
Token ID1375
Feature activation-1.59e-02

Pos logit contributions
age+0.008
est+0.007
ze+0.006
 ok+0.006
+0.006
Neg logit contributions
yles-0.007
outing-0.006
outed-0.006
ries-0.006
nam-0.006
Token picked
Token ID6497
Feature activation+1.07e-02

Pos logit contributions
age+0.034
est+0.030
+0.027
 ok+0.026
ze+0.025
Neg logit contributions
yles-0.024
outing-0.022
ries-0.020
outed-0.020
ateful-0.020
Token up
Token ID510
Feature activation+7.30e-03

Pos logit contributions
yles+0.021
outing+0.020
ries+0.019
outed+0.019
ateful+0.019
Neg logit contributions
age-0.018
est-0.015
-0.013
 ok-0.012
ze-0.012
Token he
Token ID339
Feature activation+1.63e-02

Pos logit contributions
age+0.006
est+0.005
+0.005
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.009
outing-0.009
ries-0.008
outed-0.008
ateful-0.008
Token especially
Token ID2592
Feature activation-5.17e-02

Pos logit contributions
yles+0.027
outing+0.024
outed+0.023
ateful+0.023
ries+0.023
Neg logit contributions
age-0.031
est-0.027
-0.024
 ok-0.023
ze-0.022
Token liked
Token ID8288
Feature activation-3.21e-03

Pos logit contributions
age+0.092
est+0.082
+0.073
 ok+0.070
ze+0.067
Neg logit contributions
yles-0.095
outing-0.087
ries-0.084
irs-0.084
ateful-0.079
Token the
Token ID262
Feature activation-9.43e-03

Pos logit contributions
age+0.006
est+0.005
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.006
outing-0.005
outed-0.005
ries-0.005
ateful-0.005
Token or
Token ID393
Feature activation-1.78e-02

Pos logit contributions
age+0.017
est+0.014
+0.013
ze+0.012
sy+0.012
Neg logit contributions
yles-0.015
nam-0.014
outing-0.014
 passports-0.014
 brushes-0.014
Tokennam
Token ID7402
Feature activation+1.26e-01

Pos logit contributions
age+0.036
est+0.032
+0.029
 ok+0.028
ze+0.026
Neg logit contributions
yles-0.028
outing-0.026
outed-0.024
ries-0.024
ateful-0.023
Tokenents
Token ID658
Feature activation+5.23e-02

Pos logit contributions
yles+0.117
outing+0.100
eling+0.092
outed+0.091
ries+0.090
Neg logit contributions
age-0.333
est-0.298
-0.281
 ok-0.261
ze-0.257
Token he
Token ID339
Feature activation+2.03e-02

Pos logit contributions
yles+0.115
outing+0.107
outed+0.103
ateful+0.102
ries+0.102
Neg logit contributions
age-0.075
est-0.062
-0.053
 ok-0.048
ze-0.045
Token kept
Token ID4030
Feature activation+4.91e-03

Pos logit contributions
yles+0.034
outing+0.031
ries+0.029
ateful+0.029
outed+0.029
Neg logit contributions
age-0.040
est-0.035
-0.032
 ok-0.030
ze-0.029
Token around
Token ID1088
Feature activation+1.67e-02

Pos logit contributions
yles+0.009
outing+0.009
ries+0.008
ateful+0.008
outed+0.008
Neg logit contributions
age-0.008
est-0.007
-0.006
 ok-0.006
ze-0.005
Token.
Token ID13
Feature activation-2.15e-03

Pos logit contributions
yles+0.029
nam+0.026
ries+0.026
outing+0.026
ateful+0.025
Neg logit contributions
age-0.032
est-0.026
-0.022
 ok-0.021
ench-0.021
Token to
Token ID284
Feature activation+1.68e-02

Pos logit contributions
age+0.006
est+0.005
 back+0.005
+0.005
 right+0.005
Neg logit contributions
outing-0.010
outed-0.009
yles-0.009
eling-0.009
ateful-0.009
Token look
Token ID804
Feature activation+2.01e-02

Pos logit contributions
yles+0.033
outing+0.032
outed+0.030
ateful+0.029
ries+0.029
Neg logit contributions
age-0.028
est-0.024
-0.022
 ok-0.019
ze-0.019
Token at
Token ID379
Feature activation+2.58e-02

Pos logit contributions
yles+0.028
outing+0.026
ries+0.025
outed+0.025
nam+0.024
Neg logit contributions
age-0.048
est-0.038
-0.035
nob-0.034
ze-0.034
Token the
Token ID262
Feature activation-3.66e-03

Pos logit contributions
outing+0.049
yles+0.048
outed+0.045
eling+0.043
ateful+0.041
Neg logit contributions
age-0.039
est-0.038
-0.031
 biggest-0.031
 best-0.030
Token or
Token ID393
Feature activation-1.60e-02

Pos logit contributions
age+0.008
est+0.006
 ok+0.006
+0.006
ze+0.005
Neg logit contributions
yles-0.006
outing-0.005
ries-0.005
ateful-0.005
nam-0.005
Tokennam
Token ID7402
Feature activation+1.26e-01

Pos logit contributions
age+0.037
est+0.033
+0.033
 ok+0.031
 right+0.030
Neg logit contributions
yles-0.018
outing-0.017
ries-0.016
outed-0.015
ateful-0.014
Tokenents
Token ID658
Feature activation+5.12e-02

Pos logit contributions
yles+0.119
outing+0.101
eling+0.099
ries+0.094
outed+0.093
Neg logit contributions
age-0.326
est-0.288
-0.277
ench-0.252
 ok-0.251
Token on
Token ID319
Feature activation-6.37e-03

Pos logit contributions
yles+0.116
outing+0.109
outed+0.106
ateful+0.104
ries+0.103
Neg logit contributions
age-0.069
est-0.057
-0.047
 ok-0.042
ze-0.041
Token the
Token ID262
Feature activation-1.60e-03

Pos logit contributions
age+0.012
est+0.011
+0.010
 ok+0.009
ze+0.009
Neg logit contributions
yles-0.011
outing-0.010
outed-0.010
ateful-0.009
eling-0.009
Token tree
Token ID5509
Feature activation+3.81e-02

Pos logit contributions
age+0.003
 ok+0.003
est+0.003
ench+0.003
tted+0.002
Neg logit contributions
nam-0.002
 salon-0.002
ries-0.002
 brushes-0.002
yles-0.002
Token.
Token ID13
Feature activation+3.00e-03

Pos logit contributions
yles+0.086
outing+0.080
outed+0.077
ateful+0.077
ries+0.076
Neg logit contributions
age-0.053
est-0.042
-0.037
 ok-0.031
ze-0.030
Token take
Token ID1011
Feature activation-1.15e-03

Pos logit contributions
yles+0.031
ateful+0.028
outing+0.028
eling+0.028
ries+0.028
Neg logit contributions
age-0.040
est-0.036
 ok-0.030
-0.029
sy-0.029
Token one
Token ID530
Feature activation-1.36e-02

Pos logit contributions
age+0.002
est+0.002
+0.001
 ok+0.001
ze+0.001
Neg logit contributions
yles-0.002
ries-0.002
outing-0.002
ateful-0.002
nam-0.002
Token of
Token ID286
Feature activation+2.89e-02

Pos logit contributions
age+0.024
est+0.020
ze+0.019
 ok+0.019
sy+0.018
Neg logit contributions
yles-0.021
ries-0.021
outing-0.021
nam-0.020
 salon-0.020
Token the
Token ID262
Feature activation-7.27e-03

Pos logit contributions
yles+0.049
outing+0.047
outed+0.044
ateful+0.042
ries+0.041
Neg logit contributions
age-0.055
est-0.048
-0.044
 ok-0.042
 best-0.039
Token or
Token ID393
Feature activation-1.49e-02

Pos logit contributions
age+0.014
est+0.011
+0.011
ze+0.010
sy+0.010
Neg logit contributions
yles-0.012
nam-0.012
ries-0.011
outing-0.011
ateful-0.010
Tokennam
Token ID7402
Feature activation+1.26e-01

Pos logit contributions
age+0.035
est+0.031
+0.029
 ok+0.028
ze+0.027
Neg logit contributions
yles-0.019
outing-0.017
outed-0.015
ries-0.015
ateful-0.015
Tokenents
Token ID658
Feature activation+5.09e-02

Pos logit contributions
yles+0.113
outing+0.096
eling+0.088
outed+0.087
ries+0.086
Neg logit contributions
age-0.336
est-0.300
-0.285
 ok-0.265
ze-0.260
Token outside
Token ID2354
Feature activation+1.62e-02

Pos logit contributions
yles+0.105
outing+0.098
ries+0.093
outed+0.093
ateful+0.093
Neg logit contributions
age-0.078
est-0.065
-0.056
 ok-0.052
ze-0.049
Token for
Token ID329
Feature activation-1.70e-02

Pos logit contributions
yles+0.031
outing+0.029
ries+0.027
ateful+0.027
outed+0.027
Neg logit contributions
age-0.027
est-0.022
-0.019
 ok-0.019
ze-0.018
Token a
Token ID257
Feature activation-3.25e-03

Pos logit contributions
age+0.025
est+0.020
+0.018
 ok+0.017
ze+0.016
Neg logit contributions
yles-0.036
outing-0.035
outed-0.034
ateful-0.032
ries-0.032
Token walk
Token ID2513
Feature activation+2.91e-02

Pos logit contributions
age+0.006
est+0.005
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.005
outing-0.005
nam-0.005
 spill-0.004
 salon-0.004
Token box
Token ID3091
Feature activation-2.05e-02

Pos logit contributions
age+0.046
est+0.036
 ok+0.034
ze+0.033
tted+0.033
Neg logit contributions
ries-0.033
yles-0.033
nam-0.032
 spill-0.032
 passports-0.031
Token full
Token ID1336
Feature activation-2.48e-03

Pos logit contributions
age+0.032
est+0.028
 ok+0.023
+0.023
ze+0.022
Neg logit contributions
yles-0.039
outing-0.038
ries-0.036
outed-0.036
nam-0.035
Token of
Token ID286
Feature activation+2.86e-02

Pos logit contributions
age+0.005
est+0.004
ze+0.004
 ok+0.004
sy+0.004
Neg logit contributions
outing-0.003
yles-0.003
ries-0.003
nam-0.003
outed-0.003
Token beautiful
Token ID4950
Feature activation-3.29e-03

Pos logit contributions
yles+0.046
outing+0.042
ries+0.040
outed+0.039
ateful+0.039
Neg logit contributions
age-0.058
est-0.050
-0.045
 ok-0.043
ze-0.041
Token or
Token ID393
Feature activation-1.53e-02

Pos logit contributions
age+0.007
est+0.006
 ok+0.006
+0.005
ze+0.005
Neg logit contributions
yles-0.005
ries-0.005
outing-0.004
 brushes-0.004
nam-0.004
Tokennam
Token ID7402
Feature activation+1.25e-01

Pos logit contributions
age+0.044
est+0.041
+0.039
 ok+0.038
 biggest+0.037
Neg logit contributions
yles-0.010
outing-0.008
outed-0.007
ries-0.006
eling-0.006
Tokenents
Token ID658
Feature activation+5.01e-02

Pos logit contributions
yles+0.112
outing+0.096
eling+0.087
outed+0.086
ries+0.085
Neg logit contributions
age-0.334
est-0.300
-0.284
 ok-0.265
sy-0.260
Token.
Token ID13
Feature activation+5.79e-04

Pos logit contributions
yles+0.116
outing+0.108
outed+0.105
ateful+0.104
ries+0.101
Neg logit contributions
age-0.067
est-0.054
-0.046
 ok-0.040
ze-0.038
Token
Token ID220
Feature activation+3.57e-02

Pos logit contributions
yles+0.001
outing+0.001
outed+0.001
nam+0.001
ries+0.001
Neg logit contributions
age-0.001
est-0.001
 ok-0.001
ze-0.001
-0.001
Token
Token ID198
Feature activation-9.45e-03

Pos logit contributions
yles+0.073
outing+0.068
outed+0.065
ries+0.064
ateful+0.063
Neg logit contributions
age-0.055
est-0.048
-0.038
ze-0.037
 ok-0.037
Token
Token ID198
Feature activation-9.96e-03

Pos logit contributions
age+0.016
est+0.014
 ok+0.011
ze+0.011
+0.011
Neg logit contributions
yles-0.018
outing-0.016
outed-0.016
ries-0.015
nam-0.015
Token many
Token ID867
Feature activation+6.99e-02

Pos logit contributions
age+0.016
est+0.014
+0.012
 ok+0.012
ze+0.011
Neg logit contributions
yles-0.017
outing-0.016
outed-0.015
ries-0.015
ateful-0.015
Token colors
Token ID7577
Feature activation+1.44e-02

Pos logit contributions
yles+0.106
outing+0.096
ries+0.092
outed+0.090
ateful+0.089
Neg logit contributions
age-0.146
est-0.127
-0.116
 ok-0.110
ze-0.107
Token.
Token ID13
Feature activation+1.34e-03

Pos logit contributions
yles+0.032
outing+0.030
outed+0.028
ateful+0.028
eling+0.028
Neg logit contributions
age-0.020
est-0.017
-0.014
 ok-0.013
ze-0.012
Token Some
Token ID2773
Feature activation+2.98e-02

Pos logit contributions
yles+0.003
outing+0.002
outed+0.002
ries+0.002
ateful+0.002
Neg logit contributions
age-0.002
est-0.002
ze-0.002
-0.001
 ok-0.001
Token or
Token ID393
Feature activation-1.79e-02

Pos logit contributions
yles+0.049
outing+0.045
ateful+0.041
outed+0.041
eling+0.040
Neg logit contributions
age-0.060
est-0.055
-0.048
 ok-0.044
 best-0.043
Tokennam
Token ID7402
Feature activation+1.25e-01

Pos logit contributions
age+0.040
est+0.038
+0.036
 ok+0.033
 best+0.033
Neg logit contributions
yles-0.022
outing-0.020
outed-0.019
ateful-0.018
eling-0.017
Tokenents
Token ID658
Feature activation+5.00e-02

Pos logit contributions
yles+0.122
outing+0.106
eling+0.105
outed+0.098
ateful+0.097
Neg logit contributions
age-0.321
est-0.283
-0.269
sy-0.244
ench-0.244
Token were
Token ID547
Feature activation+2.47e-02

Pos logit contributions
yles+0.097
outing+0.089
outed+0.085
ateful+0.084
nam+0.084
Neg logit contributions
age-0.086
est-0.074
-0.064
 back-0.058
 ok-0.057
Token round
Token ID2835
Feature activation-3.21e-04

Pos logit contributions
yles+0.049
outing+0.045
outed+0.042
eling+0.042
ries+0.042
Neg logit contributions
age-0.040
est-0.033
-0.030
 ok-0.028
 best-0.027
Token,
Token ID11
Feature activation-6.48e-06

Pos logit contributions
age+0.000
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.001
outing-0.001
ries-0.001
outed-0.001
ateful-0.001
Token some
Token ID617
Feature activation+4.29e-02

Feature not active on prev token;
no predictions were affected.
Token not
Token ID407
Feature activation-1.28e-04

Pos logit contributions
yles+0.028
outing+0.027
ries+0.025
outed+0.025
ateful+0.025
Neg logit contributions
age-0.031
est-0.028
-0.023
 ok-0.021
ze-0.021
Token nice
Token ID3621
Feature activation-1.78e-02

Pos logit contributions
age+0.000
est+0.000
+0.000
 ok+0.000
 best+0.000
Neg logit contributions
yles-0.000
outing-0.000
outed-0.000
ries-0.000
ateful-0.000
Token."
Token ID526
Feature activation+7.82e-03

Pos logit contributions
age+0.030
est+0.024
+0.022
sy+0.021
 ok+0.021
Neg logit contributions
yles-0.032
ries-0.031
outing-0.030
ateful-0.030
outed-0.029
Token
Token ID198
Feature activation-1.27e-03

Pos logit contributions
yles+0.016
outing+0.015
eling+0.014
ries+0.014
ateful+0.014
Neg logit contributions
age-0.012
est-0.010
-0.010
 ok-0.009
ze-0.008
Token
Token ID198
Feature activation-2.79e-03

Pos logit contributions
age+0.002
est+0.002
+0.001
 ok+0.001
ze+0.001
Neg logit contributions
yles-0.003
outing-0.003
outed-0.002
ries-0.002
ateful-0.002
TokenUn
Token ID3118
Feature activation+1.24e-01

Pos logit contributions
age+0.005
est+0.004
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.005
outing-0.004
ries-0.004
outed-0.004
ateful-0.004
Tokencle
Token ID2375
Feature activation+3.37e-02

Pos logit contributions
yles+0.225
outing+0.198
outed+0.191
ries+0.190
eling+0.189
Neg logit contributions
age-0.236
est-0.193
-0.178
 ok-0.162
sy-0.154
Token Tom
Token ID4186
Feature activation+4.43e-02

Pos logit contributions
yles+0.033
outing+0.029
ries+0.026
outed+0.026
ateful+0.025
Neg logit contributions
age-0.089
est-0.080
-0.073
 ok-0.071
ze-0.070
Token laughed
Token ID13818
Feature activation-7.40e-03

Pos logit contributions
yles+0.084
outing+0.077
ateful+0.073
ries+0.073
outed+0.072
Neg logit contributions
age-0.076
est-0.065
-0.059
 ok-0.055
ze-0.052
Token.
Token ID13
Feature activation+4.71e-04

Pos logit contributions
age+0.015
est+0.012
sy+0.011
nob+0.011
ench+0.010
Neg logit contributions
outing-0.011
yles-0.011
outed-0.011
ries-0.010
ateful-0.010
Token He
Token ID679
Feature activation-1.52e-03

Pos logit contributions
yles+0.001
outing+0.001
eling+0.001
ries+0.001
ateful+0.001
Neg logit contributions
age-0.001
est-0.000
-0.000
 ok-0.000
 right-0.000
Token before
Token ID878
Feature activation+2.86e-02

Pos logit contributions
yles+0.041
outing+0.037
ries+0.035
ateful+0.034
nam+0.034
Neg logit contributions
age-0.031
est-0.026
-0.023
 ok-0.022
ench-0.021
Token.
Token ID13
Feature activation+5.82e-03

Pos logit contributions
yles+0.064
outing+0.060
outed+0.058
ateful+0.057
ries+0.057
Neg logit contributions
age-0.039
est-0.032
-0.028
 ok-0.025
ze-0.024
Token
Token ID198
Feature activation-3.20e-03

Pos logit contributions
yles+0.012
outing+0.011
ries+0.010
eling+0.010
ateful+0.010
Neg logit contributions
age-0.009
est-0.008
-0.007
 ok-0.007
ze-0.006
Token
Token ID198
Feature activation-4.48e-03

Pos logit contributions
age+0.005
est+0.004
+0.003
 ok+0.003
ze+0.003
Neg logit contributions
yles-0.007
outing-0.007
outed-0.006
ries-0.006
ateful-0.006
Token"
Token ID1
Feature activation+1.64e-02

Pos logit contributions
age+0.008
est+0.007
+0.006
 ok+0.006
ze+0.005
Neg logit contributions
yles-0.008
outing-0.008
ries-0.007
outed-0.007
ateful-0.007
TokenUn
Token ID3118
Feature activation+1.24e-01

Pos logit contributions
yles+0.033
eling+0.032
outing+0.032
ries+0.031
outed+0.030
Neg logit contributions
age-0.024
-0.020
est-0.019
ze-0.016
 right-0.016
Tokenic
Token ID291
Feature activation-6.92e-03

Pos logit contributions
yles+0.212
outing+0.196
outed+0.186
ries+0.184
ateful+0.182
Neg logit contributions
age-0.239
est-0.205
-0.185
 ok-0.172
ze-0.166
Tokenorn
Token ID1211
Feature activation+4.72e-02

Pos logit contributions
age+0.009
est+0.007
+0.007
 ok+0.007
 biggest+0.006
Neg logit contributions
eling-0.014
yles-0.014
outing-0.014
ries-0.014
ateful-0.013
Token is
Token ID318
Feature activation+2.54e-02

Pos logit contributions
yles+0.089
outing+0.084
ries+0.082
eling+0.081
outed+0.079
Neg logit contributions
age-0.075
est-0.061
-0.054
 ok-0.052
ench-0.050
Token a
Token ID257
Feature activation-8.27e-03

Pos logit contributions
yles+0.045
outing+0.041
outed+0.039
nam+0.039
ateful+0.039
Neg logit contributions
age-0.047
est-0.040
-0.033
ench-0.032
nob-0.030
Token rare
Token ID4071
Feature activation-1.02e-02

Pos logit contributions
age+0.016
est+0.014
ench+0.013
+0.013
 ok+0.012
Neg logit contributions
yles-0.012
nam-0.010
outing-0.010
ateful-0.010
 passports-0.010
Token a
Token ID257
Feature activation-4.78e-03

Pos logit contributions
age+0.018
est+0.015
+0.012
 biggest+0.011
 best+0.011
Neg logit contributions
yles-0.038
outing-0.037
eling-0.035
outed-0.034
ateful-0.034
Token tree
Token ID5509
Feature activation+4.38e-02

Pos logit contributions
age+0.008
est+0.007
+0.006
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.009
outing-0.008
outed-0.008
ries-0.008
ateful-0.008
Token with
Token ID351
Feature activation+8.50e-03

Pos logit contributions
yles+0.099
outing+0.095
ries+0.091
outed+0.091
ateful+0.089
Neg logit contributions
age-0.056
est-0.046
 ok-0.037
-0.036
ze-0.033
Token shiny
Token ID22441
Feature activation+1.20e-02

Pos logit contributions
yles+0.018
outing+0.017
eling+0.016
outed+0.016
ateful+0.016
Neg logit contributions
age-0.013
est-0.011
-0.009
 biggest-0.009
 middle-0.008
Token or
Token ID393
Feature activation-1.13e-02

Pos logit contributions
yles+0.021
outing+0.019
ries+0.018
outed+0.018
ateful+0.018
Neg logit contributions
age-0.022
est-0.019
-0.017
 ok-0.016
ze-0.016
Tokennam
Token ID7402
Feature activation+1.24e-01

Pos logit contributions
age+0.026
est+0.024
+0.023
 ok+0.021
 biggest+0.021
Neg logit contributions
yles-0.014
outing-0.013
outed-0.012
ries-0.011
eling-0.011
Tokenents
Token ID658
Feature activation+5.22e-02

Pos logit contributions
yles+0.110
outing+0.093
eling+0.085
outed+0.083
ries+0.082
Neg logit contributions
age-0.333
est-0.300
-0.282
 ok-0.264
ze-0.258
Token hanging
Token ID10938
Feature activation-1.83e-02

Pos logit contributions
yles+0.132
outing+0.122
ateful+0.119
outed+0.119
eling+0.117
Neg logit contributions
age-0.060
est-0.047
-0.036
 right-0.031
 back-0.030
Token from
Token ID422
Feature activation+6.03e-03

Pos logit contributions
age+0.030
est+0.025
+0.022
 ok+0.021
ze+0.020
Neg logit contributions
yles-0.036
outing-0.034
ries-0.033
outed-0.032
ateful-0.032
Token its
Token ID663
Feature activation+3.47e-02

Pos logit contributions
yles+0.011
outing+0.010
ries+0.010
outed+0.010
ateful+0.010
Neg logit contributions
age-0.011
est-0.009
-0.008
 ok-0.008
ze-0.007
Token branches
Token ID13737
Feature activation+2.17e-02

Pos logit contributions
nam+0.060
yles+0.058
ries+0.058
 brushes+0.056
outing+0.056
Neg logit contributions
age-0.056
est-0.050
-0.045
 ok-0.044
ze-0.041
Token at
Token ID379
Feature activation+2.05e-02

Pos logit contributions
age+0.031
est+0.024
+0.023
nob+0.022
ze+0.021
Neg logit contributions
yles-0.028
outing-0.027
outed-0.027
ries-0.025
ateful-0.025
Token all
Token ID477
Feature activation+5.50e-02

Pos logit contributions
outing+0.037
yles+0.036
outed+0.033
eling+0.032
ateful+0.032
Neg logit contributions
age-0.032
est-0.031
-0.027
 best-0.027
 biggest-0.026
Token the
Token ID262
Feature activation-1.28e-02

Pos logit contributions
yles+0.095
outing+0.086
outed+0.081
ateful+0.079
nam+0.077
Neg logit contributions
age-0.104
est-0.097
-0.086
 ok-0.077
 best-0.076
Token different
Token ID1180
Feature activation-5.45e-03

Pos logit contributions
age+0.025
est+0.021
+0.019
 ok+0.018
ze+0.018
Neg logit contributions
yles-0.021
outing-0.020
ries-0.019
ateful-0.018
outed-0.018
Token or
Token ID393
Feature activation-1.90e-02

Pos logit contributions
age+0.011
est+0.009
+0.008
 ok+0.008
ze+0.008
Neg logit contributions
yles-0.009
outing-0.008
ries-0.008
ateful-0.008
outed-0.008
Tokennam
Token ID7402
Feature activation+1.24e-01

Pos logit contributions
age+0.042
est+0.040
+0.039
 ok+0.038
 best+0.037
Neg logit contributions
yles-0.020
outing-0.018
outed-0.017
ries-0.016
ila-0.016
Tokenents
Token ID658
Feature activation+4.77e-02

Pos logit contributions
yles+0.115
outing+0.097
eling+0.094
outed+0.089
ries+0.089
Neg logit contributions
age-0.324
est-0.288
-0.275
 ok-0.252
sy-0.251
Token and
Token ID290
Feature activation-7.36e-04

Pos logit contributions
yles+0.109
outing+0.101
outed+0.098
ateful+0.097
ries+0.095
Neg logit contributions
age-0.065
est-0.054
-0.045
 ok-0.039
ze-0.038
Token adm
Token ID6178
Feature activation-2.73e-03

Pos logit contributions
age+0.001
est+0.001
+0.001
 ok+0.001
 best+0.001
Neg logit contributions
yles-0.001
outing-0.001
outed-0.001
ateful-0.001
eling-0.001
Tokeniring
Token ID3428
Feature activation+2.49e-02

Pos logit contributions
age+0.006
est+0.005
+0.004
 ok+0.004
 best+0.004
Neg logit contributions
yles-0.004
outing-0.004
eling-0.003
ries-0.003
nam-0.003
Token the
Token ID262
Feature activation-8.81e-03

Pos logit contributions
yles+0.040
outing+0.038
outed+0.036
ateful+0.034
eling+0.034
Neg logit contributions
age-0.046
est-0.043
-0.039
 ok-0.037
 best-0.035
Token a
Token ID257
Feature activation-1.23e-02

Pos logit contributions
age+0.030
est+0.025
+0.023
 ok+0.021
ze+0.020
Neg logit contributions
yles-0.034
outing-0.032
ateful-0.030
outed-0.030
ries-0.030
Token box
Token ID3091
Feature activation-2.57e-02

Pos logit contributions
age+0.025
est+0.022
nob+0.018
+0.018
ze+0.017
Neg logit contributions
yles-0.018
nam-0.017
 brushes-0.017
outing-0.017
 passports-0.017
Token of
Token ID286
Feature activation+2.06e-02

Pos logit contributions
age+0.046
est+0.042
+0.037
 ok+0.036
ze+0.036
Neg logit contributions
outing-0.039
yles-0.036
outed-0.035
ries-0.035
 brushes-0.035
Token shiny
Token ID22441
Feature activation+5.69e-03

Pos logit contributions
yles+0.030
outing+0.027
ries+0.026
nam+0.026
outed+0.025
Neg logit contributions
age-0.044
est-0.038
-0.035
 ok-0.034
ze-0.033
Token or
Token ID393
Feature activation-2.19e-02

Pos logit contributions
yles+0.008
ries+0.007
outing+0.007
nam+0.006
outed+0.006
Neg logit contributions
age-0.013
est-0.011
-0.010
 ok-0.010
ze-0.010
Tokennam
Token ID7402
Feature activation+1.23e-01

Pos logit contributions
age+0.052
est+0.048
+0.046
 ok+0.043
 best+0.042
Neg logit contributions
yles-0.025
outing-0.023
outed-0.021
eling-0.020
ateful-0.020
Tokenents
Token ID658
Feature activation+4.87e-02

Pos logit contributions
yles+0.109
outing+0.094
eling+0.085
outed+0.083
ries+0.082
Neg logit contributions
age-0.331
est-0.297
-0.281
 ok-0.262
ze-0.256
Token that
Token ID326
Feature activation+1.02e-02

Pos logit contributions
yles+0.107
outing+0.100
outed+0.096
ries+0.095
ateful+0.095
Neg logit contributions
age-0.069
est-0.057
-0.048
 ok-0.044
ze-0.041
Token spark
Token ID9009
Feature activation+3.72e-02

Pos logit contributions
yles+0.013
outing+0.012
outed+0.011
ateful+0.011
ries+0.011
Neg logit contributions
age-0.024
est-0.021
-0.020
 ok-0.019
ze-0.018
Tokenled
Token ID992
Feature activation+3.85e-02

Pos logit contributions
yles+0.060
outing+0.056
nam+0.054
ateful+0.053
outed+0.051
Neg logit contributions
age-0.074
est-0.071
-0.057
ze-0.053
 best-0.052
Token in
Token ID287
Feature activation-1.45e-02

Pos logit contributions
yles+0.071
outing+0.068
ries+0.066
nam+0.065
outed+0.064
Neg logit contributions
age-0.068
est-0.052
-0.044
ze-0.043
ench-0.043
Token he
Token ID339
Feature activation+1.34e-02

Pos logit contributions
yles+0.002
outing+0.002
ries+0.001
outed+0.001
ateful+0.001
Neg logit contributions
age-0.003
est-0.002
-0.002
 ok-0.002
ze-0.002
Token noticed
Token ID6810
Feature activation-5.11e-02

Pos logit contributions
yles+0.020
outing+0.018
outed+0.017
ries+0.016
eling+0.016
Neg logit contributions
age-0.029
est-0.025
-0.022
 ok-0.022
ze-0.021
Token some
Token ID617
Feature activation+4.31e-02

Pos logit contributions
age+0.092
est+0.080
+0.071
 ok+0.067
ze+0.064
Neg logit contributions
yles-0.092
outing-0.085
outed-0.081
ries-0.080
ateful-0.080
Token other
Token ID584
Feature activation+3.48e-02

Pos logit contributions
yles+0.080
outing+0.074
outed+0.070
ries+0.070
ateful+0.069
Neg logit contributions
age-0.075
est-0.065
-0.057
 ok-0.054
ze-0.052
Token cater
Token ID20825
Feature activation+1.89e-02

Pos logit contributions
yles+0.052
outing+0.046
ries+0.046
ateful+0.044
eling+0.043
Neg logit contributions
age-0.076
est-0.062
-0.057
 ok-0.056
ze-0.054
Tokenpill
Token ID27215
Feature activation+1.23e-01

Pos logit contributions
yles+0.019
outing+0.016
ries+0.014
eling+0.014
outed+0.013
Neg logit contributions
age-0.050
est-0.045
-0.041
 ok-0.041
ze-0.039
Tokenars
Token ID945
Feature activation+4.81e-02

Pos logit contributions
yles+0.241
outing+0.232
eling+0.220
outed+0.214
ateful+0.210
Neg logit contributions
age-0.180
est-0.164
 ok-0.131
-0.127
ze-0.120
Token stretching
Token ID20880
Feature activation-5.55e-03

Pos logit contributions
yles+0.101
outing+0.093
outed+0.090
ateful+0.090
ries+0.089
Neg logit contributions
age-0.072
est-0.061
-0.054
 ok-0.049
ze-0.047
Token towards
Token ID3371
Feature activation+1.62e-03

Pos logit contributions
age+0.009
est+0.008
+0.007
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.010
outing-0.010
ries-0.009
outed-0.009
ateful-0.009
Token it
Token ID340
Feature activation+9.92e-04

Pos logit contributions
yles+0.002
outing+0.002
outed+0.002
ries+0.002
ateful+0.002
Neg logit contributions
age-0.004
est-0.003
-0.003
 ok-0.003
ze-0.003
Token too
Token ID1165
Feature activation+4.29e-02

Pos logit contributions
yles+0.002
outing+0.002
ries+0.002
outed+0.001
eling+0.001
Neg logit contributions
age-0.002
est-0.001
 ok-0.001
>-0.001
ze-0.001
Token can
Token ID460
Feature activation+1.94e-02

Pos logit contributions
age+0.010
est+0.009
+0.007
ze+0.007
 ok+0.007
Neg logit contributions
yles-0.008
outing-0.007
ries-0.007
nam-0.007
ateful-0.007
Token we
Token ID356
Feature activation-4.09e-03

Pos logit contributions
yles+0.038
outing+0.036
outed+0.034
ateful+0.034
ries+0.034
Neg logit contributions
age-0.032
est-0.027
-0.024
 ok-0.022
ze-0.021
Token have
Token ID423
Feature activation+2.17e-02

Pos logit contributions
age+0.008
est+0.007
 ok+0.006
+0.006
ze+0.006
Neg logit contributions
yles-0.007
outing-0.006
nam-0.006
ries-0.006
ateful-0.006
Token some
Token ID617
Feature activation+4.22e-02

Pos logit contributions
yles+0.043
outing+0.042
outed+0.039
ateful+0.039
ries+0.038
Neg logit contributions
age-0.034
est-0.029
-0.026
 ok-0.024
ze-0.022
Token or
Token ID393
Feature activation-1.82e-02

Pos logit contributions
yles+0.069
ries+0.065
outing+0.062
nam+0.062
ateful+0.060
Neg logit contributions
age-0.084
est-0.069
-0.061
ze-0.060
sy-0.059
Tokennam
Token ID7402
Feature activation+1.23e-01

Pos logit contributions
age+0.039
est+0.034
+0.033
 ok+0.031
 best+0.029
Neg logit contributions
yles-0.025
outing-0.024
outed-0.022
eling-0.021
ateful-0.021
Tokenents
Token ID658
Feature activation+4.90e-02

Pos logit contributions
yles+0.109
outing+0.094
eling+0.086
outed+0.085
ateful+0.083
Neg logit contributions
age-0.326
est-0.292
-0.277
 ok-0.258
ze-0.253
Token for
Token ID329
Feature activation-1.91e-02

Pos logit contributions
yles+0.102
outing+0.096
ries+0.093
outed+0.092
ateful+0.091
Neg logit contributions
age-0.072
est-0.060
-0.051
 ok-0.048
ze-0.046
Token our
Token ID674
Feature activation-2.25e-02

Pos logit contributions
age+0.030
est+0.026
+0.025
 ok+0.023
ze+0.022
Neg logit contributions
yles-0.036
outing-0.035
outed-0.033
ateful-0.032
eling-0.030
Token snow
Token ID6729
Feature activation+6.86e-03

Pos logit contributions
age+0.046
est+0.039
+0.035
 ok+0.033
sy+0.033
Neg logit contributions
yles-0.036
ries-0.032
outing-0.032
nam-0.032
ateful-0.031
Tokenman
Token ID805
Feature activation-1.42e-02

Pos logit contributions
yles+0.014
ries+0.013
 salon+0.012
outing+0.012
outed+0.012
Neg logit contributions
age-0.009
est-0.008
-0.008
 ok-0.007
sy-0.007
Token so
Token ID523
Feature activation+1.34e-02

Pos logit contributions
yles+0.048
outing+0.045
ries+0.043
outed+0.043
ateful+0.042
Neg logit contributions
age-0.039
est-0.033
-0.028
 ok-0.026
ze-0.025
Token beautiful
Token ID4950
Feature activation-3.31e-03

Pos logit contributions
yles+0.029
outing+0.026
ries+0.026
eling+0.025
ateful+0.025
Neg logit contributions
age-0.019
est-0.016
-0.016
 ok-0.013
sy-0.013
Token inside
Token ID2641
Feature activation+1.74e-02

Pos logit contributions
age+0.005
est+0.004
+0.003
 ok+0.003
ze+0.003
Neg logit contributions
yles-0.007
outing-0.007
ries-0.006
outed-0.006
ateful-0.006
Token and
Token ID290
Feature activation-8.73e-04

Pos logit contributions
yles+0.031
outing+0.029
outed+0.027
ateful+0.027
nam+0.026
Neg logit contributions
age-0.031
est-0.028
-0.025
 ok-0.023
 best-0.022
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
age+0.002
est+0.001
+0.001
 ok+0.001
 best+0.001
Neg logit contributions
yles-0.001
outing-0.001
ateful-0.001
outed-0.001
eling-0.001
Token fringe
Token ID26821
Feature activation-1.35e-01

Pos logit contributions
age+0.022
est+0.018
+0.016
 ok+0.015
ze+0.015
Neg logit contributions
yles-0.018
outing-0.017
outed-0.016
ries-0.016
ateful-0.016
Token from
Token ID422
Feature activation+3.93e-04

Pos logit contributions
age+0.220
est+0.185
+0.161
 ok+0.151
ze+0.144
Neg logit contributions
yles-0.267
outing-0.250
ries-0.237
outed-0.237
ateful-0.235
Token the
Token ID262
Feature activation-1.01e-02

Pos logit contributions
yles+0.001
outing+0.001
outed+0.001
ateful+0.001
eling+0.001
Neg logit contributions
age-0.001
est-0.001
-0.001
 ok-0.000
 biggest-0.000
Token cut
Token ID2005
Feature activation-1.25e-02

Pos logit contributions
age+0.022
est+0.018
+0.016
 ok+0.016
house+0.015
Neg logit contributions
yles-0.015
outing-0.014
outed-0.013
eling-0.013
ries-0.013
Token shells
Token ID19679
Feature activation+1.46e-02

Pos logit contributions
age+0.022
est+0.018
+0.016
 ok+0.015
ze+0.015
Neg logit contributions
yles-0.023
outing-0.022
ries-0.021
outed-0.020
ateful-0.020
Token made
Token ID925
Feature activation-3.44e-02

Pos logit contributions
yles+0.031
outing+0.029
outed+0.028
ateful+0.028
ries+0.028
Neg logit contributions
age-0.021
est-0.018
-0.016
 ok-0.014
ze-0.013
Token replied
Token ID8712
Feature activation-3.98e-03

Pos logit contributions
age+0.028
est+0.025
+0.022
 ok+0.021
ze+0.020
Neg logit contributions
yles-0.017
outing-0.015
outed-0.015
ries-0.014
eling-0.014
Token with
Token ID351
Feature activation+1.88e-03

Pos logit contributions
age+0.007
est+0.005
 entire+0.005
iver+0.005
+0.005
Neg logit contributions
outing-0.007
 they-0.007
yles-0.006
 their-0.006
outed-0.006
Token a
Token ID257
Feature activation-1.03e-02

Pos logit contributions
yles+0.004
outing+0.003
ateful+0.003
outed+0.003
ries+0.003
Neg logit contributions
age-0.003
est-0.003
-0.002
 ok-0.002
ze-0.002
Token gentle
Token ID10296
Feature activation+2.01e-02

Pos logit contributions
age+0.020
est+0.018
+0.015
nob+0.015
ze+0.015
Neg logit contributions
yles-0.015
outing-0.015
outed-0.014
nam-0.014
ateful-0.013
Token '
Token ID705
Feature activation+1.84e-02

Pos logit contributions
yles+0.025
outing+0.025
outed+0.024
 frowned+0.023
 passports+0.022
Neg logit contributions
age-0.040
est-0.034
-0.033
 ok-0.031
 biggest-0.031
Tokenyip
Token ID39666
Feature activation-1.31e-01

Pos logit contributions
yles+0.033
outing+0.032
outed+0.030
ateful+0.030
ries+0.030
Neg logit contributions
age-0.033
est-0.028
-0.026
 ok-0.022
sy-0.021
Token'.
Token ID4458
Feature activation-2.90e-02

Pos logit contributions
age+0.166
est+0.123
 biggest+0.110
nob+0.108
 middle+0.104
Neg logit contributions
outing-0.261
yles-0.249
ries-0.241
ateful-0.237
outed-0.234
Token
Token ID198
Feature activation-9.28e-03

Pos logit contributions
age+0.047
est+0.041
ze+0.033
+0.033
 ok+0.032
Neg logit contributions
yles-0.056
outing-0.052
outed-0.051
ries-0.049
nam-0.049
Token
Token ID198
Feature activation-9.99e-03

Pos logit contributions
est+0.019
age+0.018
 ok+0.015
 biggest+0.014
ze+0.014
Neg logit contributions
yles-0.013
outing-0.012
ila-0.012
outed-0.011
irs-0.011
TokenThe
Token ID464
Feature activation-9.93e-03

Pos logit contributions
est+0.018
age+0.017
 ok+0.014
 best+0.014
 biggest+0.014
Neg logit contributions
outing-0.016
yles-0.015
outed-0.014
ateful-0.014
ila-0.014
Token little
Token ID1310
Feature activation+1.93e-02

Pos logit contributions
age+0.019
est+0.016
+0.014
 ok+0.014
nob+0.013
Neg logit contributions
yles-0.016
outing-0.015
outed-0.015
nam-0.014
ateful-0.014
Token the
Token ID262
Feature activation-1.85e-02

Pos logit contributions
yles+0.038
outing+0.035
outed+0.033
ateful+0.032
ries+0.032
Neg logit contributions
age-0.045
est-0.039
-0.037
 ok-0.035
ze-0.033
Token cars
Token ID5006
Feature activation-2.37e-02

Pos logit contributions
age+0.034
est+0.030
+0.026
 ok+0.025
ze+0.024
Neg logit contributions
yles-0.031
outing-0.029
outed-0.028
ries-0.027
ateful-0.027
Token stopped
Token ID5025
Feature activation+2.88e-03

Pos logit contributions
age+0.048
est+0.041
+0.038
 ok+0.035
ze+0.034
Neg logit contributions
yles-0.039
outing-0.036
ateful-0.034
ries-0.033
nam-0.033
Token and
Token ID290
Feature activation-6.77e-03

Pos logit contributions
yles+0.006
outing+0.005
ries+0.005
outed+0.005
ateful+0.005
Neg logit contributions
age-0.005
est-0.004
-0.003
 ok-0.003
ze-0.003
Token the
Token ID262
Feature activation-1.54e-02

Pos logit contributions
age+0.013
est+0.011
+0.011
 ok+0.010
 right+0.010
Neg logit contributions
yles-0.011
outing-0.011
ateful-0.010
outed-0.010
ries-0.010
Token pedestrian
Token ID22382
Feature activation-1.30e-01

Pos logit contributions
age+0.029
est+0.025
+0.022
 ok+0.021
ench+0.021
Neg logit contributions
yles-0.024
outing-0.023
nam-0.022
outed-0.022
 passports-0.022
Token light
Token ID1657
Feature activation+3.96e-02

Pos logit contributions
age+0.208
est+0.151
+0.146
ze+0.142
 ok+0.141
Neg logit contributions
outing-0.224
yles-0.217
outed-0.211
ries-0.205
 brushes-0.201
Token turned
Token ID2900
Feature activation+2.00e-02

Pos logit contributions
yles+0.080
outing+0.074
ateful+0.071
outed+0.070
nam+0.070
Neg logit contributions
age-0.064
est-0.055
-0.047
 ok-0.043
ze-0.042
Token green
Token ID4077
Feature activation-9.13e-03

Pos logit contributions
yles+0.038
outing+0.035
outed+0.033
ries+0.033
ateful+0.033
Neg logit contributions
age-0.034
est-0.030
-0.026
 ok-0.024
ze-0.023
Token.
Token ID13
Feature activation-7.53e-03

Pos logit contributions
age+0.017
est+0.015
+0.013
 ok+0.012
ze+0.012
Neg logit contributions
yles-0.016
outing-0.015
outed-0.014
ries-0.014
ateful-0.014
Token Then
Token ID3244
Feature activation+1.44e-02

Pos logit contributions
age+0.014
est+0.012
ze+0.010
 ok+0.009
sy+0.009
Neg logit contributions
yles-0.014
outed-0.012
outing-0.012
nam-0.011
ries-0.011
Token and
Token ID290
Feature activation-6.18e-03

Pos logit contributions
age+0.020
est+0.017
+0.014
 ok+0.013
ze+0.012
Neg logit contributions
yles-0.029
outing-0.027
ries-0.026
outed-0.026
ateful-0.025
Token books
Token ID3835
Feature activation-4.91e-02

Pos logit contributions
age+0.011
est+0.010
+0.009
 middle+0.008
ze+0.008
Neg logit contributions
outing-0.011
yles-0.011
outed-0.010
ries-0.010
eling-0.009
Token.
Token ID13
Feature activation-2.70e-03

Pos logit contributions
age+0.058
est+0.046
+0.042
 right+0.032
 ok+0.031
Neg logit contributions
yles-0.119
outing-0.113
outed-0.112
ateful-0.109
nam-0.108
Token They
Token ID1119
Feature activation-5.45e-03

Pos logit contributions
age+0.006
est+0.005
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.004
outing-0.004
outed-0.004
ateful-0.004
ries-0.004
Token see
Token ID766
Feature activation-4.43e-03

Pos logit contributions
age+0.008
+0.007
est+0.007
 ok+0.006
 right+0.006
Neg logit contributions
yles-0.011
outing-0.010
outed-0.010
ries-0.010
ateful-0.009
Token alt
Token ID5988
Feature activation-1.27e-01

Pos logit contributions
age+0.008
est+0.007
+0.006
 ok+0.006
 best+0.006
Neg logit contributions
yles-0.008
outing-0.007
outed-0.007
eling-0.007
ries-0.007
Tokenars
Token ID945
Feature activation+3.25e-02

Pos logit contributions
age+0.159
est+0.112
+0.102
ze+0.080
 ok+0.080
Neg logit contributions
yles-0.310
ries-0.286
outing-0.282
ateful-0.280
nam-0.280
Token and
Token ID290
Feature activation-6.69e-03

Pos logit contributions
yles+0.074
outing+0.069
outed+0.067
ries+0.066
ateful+0.066
Neg logit contributions
age-0.043
est-0.035
-0.030
 ok-0.027
ze-0.025
Token offerings
Token ID18369
Feature activation-2.77e-02

Pos logit contributions
age+0.012
est+0.010
+0.010
 middle+0.009
ze+0.009
Neg logit contributions
yles-0.012
outing-0.011
outed-0.011
ries-0.010
ateful-0.010
Token and
Token ID290
Feature activation-7.24e-03

Pos logit contributions
age+0.026
est+0.022
+0.018
 best+0.014
 right+0.013
Neg logit contributions
yles-0.072
outing-0.067
outed-0.067
nam-0.067
eling-0.066
Token priests
Token ID17345
Feature activation-3.18e-02

Pos logit contributions
age+0.013
est+0.011
+0.011
 ok+0.009
ze+0.009
Neg logit contributions
yles-0.013
outing-0.013
outed-0.012
ries-0.011
ateful-0.011
Token "
Token ID366
Feature activation+6.18e-03

Pos logit contributions
age+0.006
est+0.005
+0.005
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.009
outing-0.008
ries-0.008
ateful-0.008
outed-0.008
TokenWe
Token ID1135
Feature activation-3.24e-02

Pos logit contributions
yles+0.011
outing+0.010
ateful+0.009
ries+0.009
outed+0.009
Neg logit contributions
age-0.011
est-0.010
 ok-0.009
-0.008
ench-0.008
Token are
Token ID389
Feature activation+3.86e-02

Pos logit contributions
age+0.070
est+0.062
 ok+0.052
+0.052
nob+0.051
Neg logit contributions
yles-0.044
ateful-0.038
outing-0.038
eling-0.037
outed-0.036
Token the
Token ID262
Feature activation-8.04e-03

Pos logit contributions
yles+0.053
nam+0.045
ateful+0.044
ries+0.042
eling+0.041
Neg logit contributions
age-0.093
est-0.083
nob-0.067
ench-0.066
-0.064
Token weapon
Token ID4282
Feature activation+3.01e-02

Pos logit contributions
age+0.012
est+0.009
+0.007
nob+0.007
ench+0.007
Neg logit contributions
yles-0.017
ateful-0.016
outing-0.016
nam-0.016
 salon-0.015
Token creators
Token ID16294
Feature activation-1.24e-01

Pos logit contributions
yles+0.054
outing+0.051
ries+0.050
 they+0.049
 spill+0.048
Neg logit contributions
age-0.046
est-0.037
ench-0.034
 ok-0.033
 middle-0.032
Token!
Token ID0
Feature activation-8.43e-03

Pos logit contributions
age+0.173
est+0.136
 ok+0.117
+0.114
 biggest+0.112
Neg logit contributions
yles-0.256
outing-0.234
ateful-0.227
ries-0.225
eling-0.223
Token We
Token ID775
Feature activation+6.52e-03

Pos logit contributions
age+0.015
est+0.014
ench+0.012
sy+0.011
 ok+0.011
Neg logit contributions
yles-0.014
ateful-0.012
outing-0.011
ila-0.011
 they-0.011
Token can
Token ID460
Feature activation+2.06e-02

Pos logit contributions
yles+0.009
outing+0.008
eling+0.008
ateful+0.008
outed+0.008
Neg logit contributions
age-0.013
est-0.012
 ok-0.010
-0.010
ze-0.010
Token stop
Token ID2245
Feature activation+1.42e-02

Pos logit contributions
yles+0.032
outing+0.028
 spill+0.027
eling+0.027
ateful+0.027
Neg logit contributions
age-0.040
est-0.038
 ok-0.031
sy-0.029
-0.029
Token the
Token ID262
Feature activation-9.45e-03

Pos logit contributions
yles+0.021
outing+0.018
ries+0.017
eling+0.017
ateful+0.017
Neg logit contributions
age-0.033
est-0.028
sy-0.024
nob-0.024
tted-0.023
Token into
Token ID656
Feature activation+2.85e-03

Pos logit contributions
age+0.051
est+0.043
 ok+0.037
+0.036
ze+0.035
Neg logit contributions
yles-0.058
outing-0.055
ries-0.054
outed-0.052
ateful-0.051
Token two
Token ID734
Feature activation+2.08e-02

Pos logit contributions
yles+0.005
outing+0.005
outed+0.005
ries+0.005
ateful+0.005
Neg logit contributions
age-0.005
est-0.004
-0.004
 ok-0.003
ze-0.003
Token bowls
Token ID34796
Feature activation-4.04e-02

Pos logit contributions
yles+0.037
outing+0.034
ries+0.033
eling+0.032
outed+0.032
Neg logit contributions
age-0.039
est-0.032
 ok-0.027
-0.026
ze-0.026
Token,
Token ID11
Feature activation-3.12e-03

Pos logit contributions
age+0.067
est+0.056
 ok+0.047
ze+0.046
+0.046
Neg logit contributions
yles-0.077
outing-0.074
ries-0.072
outed-0.069
ateful-0.067
Token then
Token ID788
Feature activation+1.64e-02

Pos logit contributions
age+0.006
est+0.005
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.005
outing-0.005
ries-0.005
nam-0.005
outed-0.005
Token voted
Token ID7052
Feature activation-1.12e-01

Pos logit contributions
yles+0.024
outing+0.022
ries+0.021
outed+0.020
ateful+0.020
Neg logit contributions
age-0.035
est-0.031
-0.027
 ok-0.026
ze-0.026
Token for
Token ID329
Feature activation-1.77e-02

Pos logit contributions
age+0.190
est+0.152
+0.128
ze+0.121
 ok+0.119
Neg logit contributions
yles-0.218
outing-0.207
ries-0.199
outed-0.195
ateful-0.193
Token their
Token ID511
Feature activation+2.26e-02

Pos logit contributions
age+0.035
est+0.032
+0.030
 ok+0.028
 best+0.027
Neg logit contributions
yles-0.027
outing-0.025
outed-0.024
ateful-0.023
eling-0.022
Token favourite
Token ID12507
Feature activation-3.26e-02

Pos logit contributions
yles+0.040
outing+0.038
ries+0.037
outed+0.037
ateful+0.036
Neg logit contributions
age-0.042
est-0.034
-0.029
nob-0.027
sy-0.027
Token.
Token ID13
Feature activation+2.13e-03

Pos logit contributions
age+0.063
est+0.050
+0.045
 ok+0.045
sy+0.043
Neg logit contributions
yles-0.054
ries-0.050
outing-0.049
eling-0.047
outed-0.046
Token Toby
Token ID37578
Feature activation+8.50e-03

Pos logit contributions
yles+0.004
outing+0.003
outed+0.003
ries+0.003
ateful+0.003
Neg logit contributions
age-0.004
est-0.003
ze-0.003
 ok-0.003
-0.003
Token smiled
Token ID13541
Feature activation+4.17e-03

Pos logit contributions
age+0.054
est+0.046
+0.040
 ok+0.038
ze+0.036
Neg logit contributions
yles-0.059
outing-0.054
outed-0.052
ries-0.051
ateful-0.051
Token and
Token ID290
Feature activation-1.66e-03

Pos logit contributions
yles+0.008
outing+0.007
outed+0.007
ateful+0.007
nam+0.007
Neg logit contributions
age-0.007
est-0.006
-0.005
nob-0.005
 ok-0.005
Token said
Token ID531
Feature activation-8.54e-03

Pos logit contributions
age+0.003
+0.003
est+0.003
 ok+0.003
 back+0.002
Neg logit contributions
outing-0.003
yles-0.003
ries-0.003
ateful-0.002
irs-0.002
Token,
Token ID11
Feature activation-2.34e-03

Pos logit contributions
age+0.014
est+0.011
+0.009
nob+0.009
 ok+0.009
Neg logit contributions
yles-0.017
outing-0.016
outed-0.015
nam-0.015
ateful-0.015
Token "
Token ID366
Feature activation+7.87e-03

Pos logit contributions
age+0.004
est+0.003
+0.003
 ok+0.003
ze+0.003
Neg logit contributions
yles-0.005
outing-0.004
outed-0.004
ries-0.004
ateful-0.004
TokenChurch
Token ID46686
Feature activation-1.11e-01

Pos logit contributions
yles+0.014
outing+0.013
ries+0.012
outed+0.012
ateful+0.012
Neg logit contributions
age-0.015
est-0.013
-0.011
 ok-0.011
ze-0.010
Token is
Token ID318
Feature activation+2.47e-02

Pos logit contributions
age+0.186
est+0.132
tted+0.120
+0.117
 ok+0.116
Neg logit contributions
yles-0.201
ries-0.186
eling-0.183
outing-0.183
outed-0.175
Token so
Token ID523
Feature activation+1.29e-02

Pos logit contributions
yles+0.043
outing+0.039
eling+0.038
ries+0.038
nam+0.038
Neg logit contributions
age-0.045
est-0.037
ench-0.029
-0.029
tted-0.029
Token nice
Token ID3621
Feature activation-1.79e-02

Pos logit contributions
yles+0.029
outing+0.027
ries+0.027
outed+0.026
ateful+0.025
Neg logit contributions
age-0.018
est-0.015
-0.013
 ok-0.012
 best-0.011
Token mom
Token ID1995
Feature activation-1.04e-02

Pos logit contributions
age+0.030
est+0.023
+0.020
tted+0.020
 ok+0.020
Neg logit contributions
yles-0.033
ries-0.030
outing-0.029
 passports-0.029
 they-0.028
Tokenmy
Token ID1820
Feature activation-1.30e-02

Pos logit contributions
age+0.017
est+0.014
ze+0.012
+0.012
 middle+0.011
Neg logit contributions
yles-0.020
outing-0.019
ries-0.018
outed-0.017
ateful-0.017
Token the
Token ID262
Feature activation-1.19e-02

Pos logit contributions
age+0.014
est+0.012
+0.012
 right+0.010
 middle+0.010
Neg logit contributions
yles-0.017
outing-0.016
outed-0.016
ateful-0.015
eling-0.014
Token ground
Token ID2323
Feature activation+1.92e-02

Pos logit contributions
age+0.021
est+0.018
 ok+0.016
+0.015
ench+0.014
Neg logit contributions
yles-0.019
outing-0.019
nam-0.019
 spill-0.018
ries-0.018
Token that
Token ID326
Feature activation+1.01e-02

Pos logit contributions
yles+0.046
outing+0.041
ateful+0.041
nam+0.040
outed+0.040
Neg logit contributions
age-0.025
est-0.020
-0.017
ze-0.014
 ok-0.014
Token said
Token ID531
Feature activation-1.35e-03

Pos logit contributions
yles+0.016
outing+0.015
eling+0.014
ateful+0.013
ries+0.013
Neg logit contributions
age-0.020
est-0.018
-0.017
 right-0.016
 best-0.016
Token "
Token ID366
Feature activation+7.10e-03

Pos logit contributions
age+0.002
est+0.002
+0.002
ench+0.002
 entire+0.002
Neg logit contributions
yles-0.002
outing-0.002
ries-0.002
ateful-0.002
outed-0.002
Tokenshort
Token ID19509
Feature activation-1.11e-01

Pos logit contributions
yles+0.012
outing+0.011
outed+0.011
ries+0.011
ateful+0.011
Neg logit contributions
age-0.013
est-0.012
-0.010
 ok-0.010
ze-0.009
Tokencut
Token ID8968
Feature activation+2.59e-02

Pos logit contributions
age+0.143
est+0.112
 ok+0.096
+0.091
 biggest+0.091
Neg logit contributions
yles-0.218
outing-0.211
ries-0.206
 arose-0.202
 passports-0.200
Token".
Token ID1911
Feature activation+7.85e-03

Pos logit contributions
yles+0.044
ries+0.044
outing+0.042
ateful+0.041
eling+0.038
Neg logit contributions
age-0.044
-0.034
est-0.034
 ok-0.032
nob-0.030
Token She
Token ID1375
Feature activation-1.80e-02

Pos logit contributions
yles+0.012
outing+0.011
outed+0.011
ries+0.011
nam+0.011
Neg logit contributions
age-0.015
est-0.013
-0.012
 ok-0.012
ze-0.011
Token thought
Token ID1807
Feature activation-2.92e-02

Pos logit contributions
age+0.037
est+0.032
+0.031
 ok+0.028
ze+0.028
Neg logit contributions
yles-0.028
outing-0.026
ateful-0.025
ries-0.024
nam-0.024
Token it
Token ID340
Feature activation-3.96e-03

Pos logit contributions
age+0.056
est+0.049
+0.045
 ok+0.042
ze+0.040
Neg logit contributions
yles-0.049
outing-0.045
outed-0.043
ateful-0.042
ries-0.042
Token little
Token ID1310
Feature activation+1.45e-02

Pos logit contributions
age+0.028
est+0.023
+0.021
 ok+0.020
ench+0.020
Neg logit contributions
yles-0.021
outing-0.019
nam-0.019
outed-0.018
ateful-0.018
Token one
Token ID530
Feature activation-1.93e-02

Pos logit contributions
yles+0.023
outing+0.021
ries+0.020
outed+0.020
ateful+0.020
Neg logit contributions
age-0.030
est-0.025
-0.023
 ok-0.022
ze-0.021
Token's
Token ID338
Feature activation+8.78e-03

Pos logit contributions
age+0.035
est+0.030
+0.027
 ok+0.026
ze+0.024
Neg logit contributions
yles-0.034
outing-0.031
outed-0.030
ries-0.030
ateful-0.029
Token costume
Token ID16569
Feature activation-2.39e-02

Pos logit contributions
yles+0.015
outing+0.013
outed+0.013
ateful+0.013
ries+0.012
Neg logit contributions
age-0.017
est-0.014
-0.013
 ok-0.012
nob-0.012
Token was
Token ID373
Feature activation-9.11e-05

Pos logit contributions
age+0.044
est+0.037
+0.033
 ok+0.032
ze+0.030
Neg logit contributions
yles-0.042
outing-0.038
outed-0.037
ries-0.036
ateful-0.036
Token voted
Token ID7052
Feature activation-1.09e-01

Pos logit contributions
age+0.000
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.000
outing-0.000
outed-0.000
ries-0.000
ateful-0.000
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
age+0.181
est+0.143
+0.121
ze+0.112
 ok+0.112
Neg logit contributions
yles-0.217
outing-0.205
ries-0.195
outed-0.192
ateful-0.192
Token best
Token ID1266
Feature activation-6.43e-02

Pos logit contributions
age+0.017
est+0.011
ench+0.010
+0.010
nob+0.010
Neg logit contributions
yles-0.021
 passports-0.020
outing-0.019
ateful-0.019
nam-0.019
Token!
Token ID0
Feature activation-9.53e-03

Pos logit contributions
age+0.103
est+0.083
+0.073
 ok+0.069
ze+0.066
Neg logit contributions
yles-0.129
outing-0.118
ries-0.113
ateful-0.113
outed-0.113
Token Everyone
Token ID11075
Feature activation+1.98e-02

Pos logit contributions
age+0.015
est+0.012
 ok+0.010
+0.010
ze+0.010
Neg logit contributions
yles-0.020
outing-0.018
outed-0.018
ries-0.017
ateful-0.017
Token cheered
Token ID34767
Feature activation+2.19e-02

Pos logit contributions
yles+0.039
outing+0.037
ries+0.035
ateful+0.034
outed+0.034
Neg logit contributions
age-0.032
est-0.028
-0.026
 ok-0.021
ze-0.021
Token -
Token ID532
Feature activation+1.95e-03

Pos logit contributions
age+0.050
est+0.042
+0.035
 ok+0.035
ench+0.034
Neg logit contributions
yles-0.062
outing-0.059
ries-0.056
outed-0.056
nam-0.054
Token a
Token ID257
Feature activation-8.82e-03

Pos logit contributions
yles+0.003
outing+0.003
ries+0.003
nam+0.003
outed+0.003
Neg logit contributions
age-0.004
est-0.003
-0.003
 ok-0.003
ench-0.003
Token shirt
Token ID10147
Feature activation-2.87e-02

Pos logit contributions
age+0.018
est+0.015
nob+0.013
 ok+0.013
ench+0.012
Neg logit contributions
yles-0.013
nam-0.012
outing-0.012
 salon-0.012
 spill-0.011
Token and
Token ID290
Feature activation+8.54e-04

Pos logit contributions
age+0.046
est+0.037
 ok+0.035
ench+0.034
 advantage+0.031
Neg logit contributions
yles-0.050
outing-0.048
ries-0.046
 spill-0.045
 brushes-0.045
Token pants
Token ID12581
Feature activation-3.89e-02

Pos logit contributions
yles+0.002
outing+0.001
ries+0.001
outed+0.001
nam+0.001
Neg logit contributions
age-0.002
est-0.001
-0.001
 ok-0.001
ze-0.001
Token combo
Token ID14831
Feature activation-1.09e-01

Pos logit contributions
age+0.060
est+0.050
+0.042
 ok+0.042
ze+0.039
Neg logit contributions
yles-0.078
outing-0.073
ries-0.070
outed-0.070
ateful-0.068
Token -
Token ID532
Feature activation+2.47e-03

Pos logit contributions
age+0.173
est+0.140
 ok+0.122
ench+0.118
+0.117
Neg logit contributions
yles-0.204
outing-0.193
ries-0.183
outed-0.181
ateful-0.177
Token and
Token ID290
Feature activation+3.84e-04

Pos logit contributions
yles+0.004
outing+0.004
outed+0.003
ries+0.003
ateful+0.003
Neg logit contributions
age-0.005
est-0.004
-0.004
 ok-0.004
ze-0.003
Token brushed
Token ID31782
Feature activation+5.18e-03

Pos logit contributions
yles+0.001
outing+0.001
ries+0.001
outed+0.001
nam+0.001
Neg logit contributions
age-0.001
est-0.001
-0.001
 ok-0.001
ze-0.001
Token his
Token ID465
Feature activation+2.97e-02

Pos logit contributions
yles+0.010
outing+0.010
ries+0.009
outed+0.009
ateful+0.009
Neg logit contributions
age-0.008
est-0.007
-0.006
 ok-0.006
ze-0.005
Token hair
Token ID4190
Feature activation-3.22e-03

Pos logit contributions
yles+0.045
outing+0.041
outed+0.040
ries+0.038
nam+0.038
Neg logit contributions
age-0.061
est-0.052
-0.047
 ok-0.045
nob-0.044
Token
Token ID198
Feature activation-8.94e-03

Pos logit contributions
yles+0.008
outing+0.008
ateful+0.007
ries+0.007
outed+0.007
Neg logit contributions
age-0.005
est-0.005
-0.004
 ok-0.003
ze-0.003
Token
Token ID198
Feature activation-1.08e-02

Pos logit contributions
age+0.015
est+0.014
 ok+0.011
+0.010
 biggest+0.010
Neg logit contributions
yles-0.017
outing-0.015
outed-0.015
ateful-0.014
ries-0.014
TokenSo
Token ID2396
Feature activation-2.32e-02

Pos logit contributions
age+0.020
est+0.018
 ok+0.015
+0.015
 biggest+0.014
Neg logit contributions
yles-0.018
outing-0.018
ateful-0.016
outed-0.016
eling-0.016
Token,
Token ID11
Feature activation-7.92e-03

Pos logit contributions
age+0.031
est+0.026
+0.023
 ok+0.020
ze+0.018
Neg logit contributions
yles-0.052
outing-0.049
ries-0.047
outed-0.047
ateful-0.046
Token with
Token ID351
Feature activation+3.62e-05

Pos logit contributions
age+0.014
est+0.013
+0.013
 right+0.012
 best+0.012
Neg logit contributions
yles-0.013
outing-0.012
ateful-0.011
outed-0.011
ries-0.011
Token artificial
Token ID11666
Feature activation-1.08e-01

Pos logit contributions
yles+0.000
outing+0.000
ries+0.000
ateful+0.000
outed+0.000
Neg logit contributions
age-0.000
est-0.000
-0.000
 ok-0.000
 middle-0.000
Token so
Token ID523
Feature activation+1.12e-02

Pos logit contributions
age+0.202
est+0.163
+0.149
 ok+0.140
ze+0.135
Neg logit contributions
yles-0.189
outing-0.177
ries-0.168
eling-0.168
outed-0.168
Tokenaps
Token ID1686
Feature activation-7.16e-03

Pos logit contributions
yles+0.023
outing+0.021
ries+0.020
outed+0.020
ateful+0.020
Neg logit contributions
age-0.017
est-0.015
-0.013
 ok-0.012
 best-0.012
Token,
Token ID11
Feature activation-5.93e-03

Pos logit contributions
age+0.011
est+0.009
+0.008
 ok+0.007
ze+0.007
Neg logit contributions
yles-0.015
outing-0.014
outed-0.014
ries-0.013
ateful-0.013
Token they
Token ID484
Feature activation+1.72e-03

Pos logit contributions
age+0.011
est+0.011
+0.011
 ok+0.010
 best+0.010
Neg logit contributions
yles-0.009
outing-0.008
outed-0.008
ateful-0.007
eling-0.007
Token made
Token ID925
Feature activation-3.98e-02

Pos logit contributions
yles+0.003
outing+0.003
ries+0.003
ateful+0.003
outed+0.003
Neg logit contributions
age-0.003
-0.003
est-0.003
sy-0.002
 ok-0.002
Token yellow
Token ID7872
Feature activation-1.43e-02

Pos logit contributions
age+0.045
est+0.038
 ok+0.034
ench+0.033
+0.033
Neg logit contributions
yles-0.034
outing-0.031
ries-0.030
nam-0.030
outed-0.029
Token and
Token ID290
Feature activation-1.52e-02

Pos logit contributions
age+0.024
 ok+0.018
est+0.018
+0.017
sy+0.016
Neg logit contributions
yles-0.025
ries-0.025
outing-0.024
 brushes-0.024
outed-0.023
Token green
Token ID4077
Feature activation-1.23e-02

Pos logit contributions
age+0.029
est+0.025
+0.022
 ok+0.021
ze+0.020
Neg logit contributions
yles-0.026
outing-0.024
ries-0.023
outed-0.023
ateful-0.022
Token until
Token ID1566
Feature activation+1.85e-02

Pos logit contributions
age+0.021
est+0.017
 ok+0.017
+0.016
ench+0.015
Neg logit contributions
yles-0.021
ries-0.021
outing-0.020
outed-0.019
 brushes-0.019
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
outing+0.030
yles+0.029
outed+0.026
ateful+0.026
eling+0.026
Neg logit contributions
age-0.033
-0.030
est-0.030
 middle-0.027
 ok-0.027
Token formerly
Token ID15734
Feature activation-1.07e-01

Pos logit contributions
age+0.021
est+0.017
 ok+0.015
+0.015
ench+0.015
Neg logit contributions
yles-0.017
nam-0.016
outing-0.016
ries-0.016
outed-0.015
Token color
Token ID3124
Feature activation+6.85e-03

Pos logit contributions
age+0.219
+0.173
''+0.169
nob+0.169
ench+0.163
Neg logit contributions
 brushes-0.128
outing-0.122
outed-0.121
nam-0.118
 frowned-0.113
Tokenless
Token ID1203
Feature activation+1.27e-02

Pos logit contributions
yles+0.012
outing+0.012
outed+0.011
ries+0.011
ateful+0.011
Neg logit contributions
age-0.012
est-0.010
-0.009
 ok-0.009
ze-0.008
Token walls
Token ID7714
Feature activation-9.35e-03

Pos logit contributions
yles+0.024
ries+0.022
outing+0.022
outed+0.021
ateful+0.021
Neg logit contributions
age-0.022
est-0.018
-0.016
 ok-0.015
sy-0.015
Token seemed
Token ID3947
Feature activation-3.13e-04

Pos logit contributions
age+0.014
est+0.012
+0.010
 ok+0.009
ze+0.009
Neg logit contributions
yles-0.020
outing-0.018
ries-0.018
outed-0.017
ateful-0.017
Token to
Token ID284
Feature activation+1.76e-02

Pos logit contributions
age+0.001
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.000
ries-0.000
ateful-0.000
Token on
Token ID319
Feature activation-5.84e-03

Pos logit contributions
yles+0.001
outing+0.001
ries+0.001
ateful+0.000
nam+0.000
Neg logit contributions
age-0.001
est-0.001
-0.000
 ok-0.000
ze-0.000
Token the
Token ID262
Feature activation-7.00e-03

Pos logit contributions
age+0.012
est+0.010
+0.009
 ok+0.009
ze+0.009
Neg logit contributions
yles-0.009
outing-0.008
ries-0.008
outed-0.008
ateful-0.008
Token airplane
Token ID19401
Feature activation-3.58e-03

Pos logit contributions
age+0.014
est+0.011
+0.010
 ok+0.010
ench+0.010
Neg logit contributions
yles-0.011
outing-0.010
nam-0.010
 passports-0.010
ries-0.009
Token said
Token ID531
Feature activation-1.75e-03

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
ze+0.005
Neg logit contributions
yles-0.006
outing-0.006
outed-0.005
ries-0.005
ateful-0.005
Token "
Token ID366
Feature activation+9.91e-03

Pos logit contributions
age+0.003
est+0.002
+0.002
sy+0.002
 entire+0.002
Neg logit contributions
yles-0.003
outing-0.003
outed-0.003
 they-0.003
ateful-0.003
Token747
Token ID48882
Feature activation-1.06e-01

Pos logit contributions
yles+0.017
outing+0.016
outed+0.015
ries+0.015
ateful+0.015
Neg logit contributions
age-0.019
est-0.016
-0.015
 ok-0.014
ze-0.013
Token".
Token ID1911
Feature activation+2.12e-02

Pos logit contributions
age+0.130
+0.104
est+0.099
 ok+0.086
 biggest+0.084
Neg logit contributions
outing-0.218
yles-0.218
ries-0.204
outed-0.203
eling-0.201
Token The
Token ID383
Feature activation-3.64e-03

Pos logit contributions
yles+0.041
outing+0.038
outed+0.038
ries+0.037
ateful+0.036
Neg logit contributions
age-0.033
est-0.029
 ok-0.023
-0.023
ze-0.022
Token people
Token ID661
Feature activation+3.29e-03

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
ench+0.005
Neg logit contributions
yles-0.006
outing-0.006
ateful-0.005
outed-0.005
ries-0.005
Token were
Token ID547
Feature activation+3.11e-02

Pos logit contributions
yles+0.006
outing+0.005
ateful+0.005
ries+0.005
nam+0.005
Neg logit contributions
age-0.006
est-0.005
-0.005
ze-0.005
 ok-0.004
Token scared
Token ID12008
Feature activation+1.13e-02

Pos logit contributions
yles+0.058
outing+0.054
outed+0.051
ries+0.051
ateful+0.051
Neg logit contributions
age-0.054
est-0.046
-0.041
 ok-0.038
ze-0.036
TokenThey
Token ID2990
Feature activation+4.30e-03

Pos logit contributions
age+0.008
est+0.008
 ok+0.007
 biggest+0.006
ze+0.006
Neg logit contributions
outing-0.005
yles-0.005
ila-0.005
outed-0.005
ateful-0.005
Token chase
Token ID15505
Feature activation+9.75e-03

Pos logit contributions
yles+0.008
outing+0.007
ries+0.007
outed+0.007
ateful+0.007
Neg logit contributions
age-0.008
est-0.007
-0.006
 ok-0.006
ze-0.006
Token the
Token ID262
Feature activation-1.03e-02

Pos logit contributions
yles+0.013
outing+0.012
ries+0.011
outed+0.011
ateful+0.011
Neg logit contributions
age-0.022
est-0.019
-0.018
 ok-0.017
ze-0.016
Token car
Token ID1097
Feature activation-6.74e-03

Pos logit contributions
age+0.018
est+0.015
+0.014
 ok+0.013
ench+0.012
Neg logit contributions
yles-0.019
outing-0.017
ateful-0.016
ries-0.016
outed-0.016
Token-
Token ID12
Feature activation+2.25e-02

Pos logit contributions
age+0.009
est+0.008
+0.006
 ok+0.006
ze+0.005
Neg logit contributions
yles-0.015
outing-0.014
ries-0.014
outed-0.014
ateful-0.013
Tokennos
Token ID39369
Feature activation-1.06e-01

Pos logit contributions
yles+0.039
outing+0.035
ries+0.034
outed+0.033
ateful+0.033
Neg logit contributions
age-0.044
est-0.037
-0.034
ze-0.031
 ok-0.030
Tokenaur
Token ID2899
Feature activation+9.16e-03

Pos logit contributions
age+0.207
est+0.182
+0.160
 ok+0.152
ze+0.146
Neg logit contributions
yles-0.177
outing-0.161
ries-0.152
outed-0.151
ateful-0.150
Token around
Token ID1088
Feature activation+1.73e-02

Pos logit contributions
yles+0.016
outing+0.015
nam+0.014
outed+0.014
ateful+0.014
Neg logit contributions
age-0.017
est-0.015
-0.013
ze-0.012
 ok-0.012
Token the
Token ID262
Feature activation-8.39e-03

Pos logit contributions
yles+0.030
outing+0.028
outed+0.027
nam+0.026
ries+0.025
Neg logit contributions
age-0.031
est-0.028
-0.026
 ok-0.024
ze-0.024
Token room
Token ID2119
Feature activation-6.15e-03

Pos logit contributions
age+0.017
est+0.015
 ok+0.015
ench+0.013
+0.013
Neg logit contributions
yles-0.012
nam-0.011
 passports-0.011
 spill-0.011
 brushes-0.011
Token,
Token ID11
Feature activation-1.53e-03

Pos logit contributions
age+0.008
est+0.007
+0.006
 ok+0.005
ze+0.005
Neg logit contributions
yles-0.014
outing-0.013
ries-0.013
nam-0.013
outed-0.013
Token.
Token ID13
Feature activation+9.22e-03

Pos logit contributions
yles+0.048
outing+0.048
outed+0.044
ries+0.042
ateful+0.041
Neg logit contributions
age-0.054
est-0.045
-0.038
ench-0.037
 ok-0.036
Token "
Token ID366
Feature activation+9.42e-03

Pos logit contributions
yles+0.017
outing+0.016
outed+0.015
ries+0.015
ateful+0.015
Neg logit contributions
age-0.016
est-0.014
-0.012
 ok-0.011
ze-0.011
TokenA
Token ID32
Feature activation+4.10e-03

Pos logit contributions
yles+0.017
outing+0.015
ateful+0.014
outed+0.014
nam+0.014
Neg logit contributions
age-0.017
est-0.015
-0.013
 ok-0.013
ench-0.012
Token car
Token ID1097
Feature activation-7.58e-03

Pos logit contributions
yles+0.006
outing+0.006
ateful+0.005
 passports+0.005
ila+0.005
Neg logit contributions
age-0.008
est-0.007
 ok-0.006
ench-0.006
-0.006
Token-
Token ID12
Feature activation+2.23e-02

Pos logit contributions
age+0.013
est+0.011
+0.009
 ok+0.009
ze+0.009
Neg logit contributions
yles-0.014
outing-0.013
ries-0.012
outed-0.012
ateful-0.012
Tokennos
Token ID39369
Feature activation-1.06e-01

Pos logit contributions
yles+0.038
outing+0.035
ries+0.033
outed+0.033
ateful+0.033
Neg logit contributions
age-0.043
est-0.037
-0.034
 ok-0.030
ze-0.030
Tokenaur
Token ID2899
Feature activation+8.23e-03

Pos logit contributions
age+0.208
+0.171
est+0.169
 ok+0.163
ze+0.156
Neg logit contributions
yles-0.158
outing-0.153
outed-0.145
ateful-0.145
ila-0.137
Token!"
Token ID2474
Feature activation+1.40e-02

Pos logit contributions
yles+0.018
outing+0.017
outed+0.016
ries+0.016
ateful+0.016
Neg logit contributions
age-0.012
est-0.010
-0.008
 ok-0.008
ze-0.007
Token
Token ID198
Feature activation-2.28e-03

Pos logit contributions
yles+0.030
outing+0.028
ries+0.026
outed+0.026
ateful+0.026
Neg logit contributions
age-0.021
est-0.017
-0.015
 ok-0.014
ze-0.013
Token
Token ID198
Feature activation-3.84e-03

Pos logit contributions
age+0.004
est+0.003
+0.003
 ok+0.003
ze+0.002
Neg logit contributions
yles-0.004
outing-0.004
outed-0.004
ries-0.004
ateful-0.004
TokenThey
Token ID2990
Feature activation+4.30e-03

Pos logit contributions
age+0.008
est+0.008
 ok+0.007
 biggest+0.006
ze+0.006
Neg logit contributions
outing-0.005
yles-0.005
ila-0.005
outed-0.005
ateful-0.005
Token making
Token ID1642
Feature activation-4.06e-02

Pos logit contributions
yles+0.034
outing+0.032
outed+0.030
ries+0.030
ateful+0.030
Neg logit contributions
age-0.033
est-0.029
-0.025
 ok-0.023
ze-0.023
Token breakfast
Token ID12607
Feature activation-6.64e-02

Pos logit contributions
age+0.071
est+0.062
+0.056
 ok+0.052
ze+0.050
Neg logit contributions
yles-0.074
outing-0.069
outed-0.065
ateful-0.064
ries-0.064
Token.
Token ID13
Feature activation-3.37e-04

Pos logit contributions
age+0.103
est+0.086
+0.074
 ok+0.070
ze+0.065
Neg logit contributions
yles-0.134
outing-0.127
ries-0.121
outed-0.119
ateful-0.118
Token They
Token ID1119
Feature activation-7.35e-03

Pos logit contributions
age+0.001
est+0.001
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.000
ries-0.000
ateful-0.000
Token smelled
Token ID37609
Feature activation-1.93e-02

Pos logit contributions
age+0.013
+0.011
est+0.011
sy+0.010
 ok+0.010
Neg logit contributions
yles-0.013
outing-0.012
ries-0.012
ateful-0.011
outed-0.011
Token pancakes
Token ID47008
Feature activation-1.05e-01

Pos logit contributions
age+0.039
est+0.032
+0.029
 ok+0.027
ze+0.027
Neg logit contributions
yles-0.032
outing-0.029
ries-0.028
outed-0.028
ateful-0.028
Token and
Token ID290
Feature activation-4.33e-03

Pos logit contributions
age+0.145
est+0.118
+0.099
 ok+0.092
ze+0.086
Neg logit contributions
yles-0.234
outing-0.220
ries-0.211
outed-0.210
ateful-0.208
Token syrup
Token ID24208
Feature activation-4.71e-02

Pos logit contributions
age+0.008
est+0.007
+0.007
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.008
outing-0.007
ateful-0.007
outed-0.007
ries-0.006
Token.
Token ID13
Feature activation-5.75e-04

Pos logit contributions
age+0.059
est+0.048
+0.039
 ok+0.034
ze+0.034
Neg logit contributions
yles-0.113
outing-0.105
ateful-0.102
nam-0.102
outed-0.101
Token They
Token ID1119
Feature activation-7.05e-03

Pos logit contributions
age+0.001
est+0.001
+0.001
ze+0.001
 ok+0.001
Neg logit contributions
yles-0.001
outing-0.001
outed-0.001
ateful-0.001
ries-0.001
Token were
Token ID547
Feature activation+1.78e-02

Pos logit contributions
age+0.012
+0.011
est+0.011
 ok+0.009
 even+0.009
Neg logit contributions
yles-0.013
outing-0.012
ries-0.011
ateful-0.011
irs-0.011
Token said
Token ID531
Feature activation+2.98e-03

Pos logit contributions
yles+0.030
outing+0.028
outed+0.025
ateful+0.025
eling+0.025
Neg logit contributions
age-0.042
est-0.037
-0.035
 ok-0.033
ze-0.031
Token his
Token ID465
Feature activation+3.29e-02

Pos logit contributions
yles+0.005
outing+0.004
outed+0.004
ries+0.004
ateful+0.004
Neg logit contributions
age-0.006
est-0.005
-0.005
 ok-0.004
ze-0.004
Token mom
Token ID1995
Feature activation-2.48e-03

Pos logit contributions
yles+0.047
outed+0.044
outing+0.044
ries+0.041
ateful+0.040
Neg logit contributions
age-0.072
est-0.062
-0.056
nob-0.052
ench-0.052
Token.
Token ID13
Feature activation+6.50e-03

Pos logit contributions
age+0.004
est+0.003
+0.003
 ok+0.003
 biggest+0.003
Neg logit contributions
yles-0.005
outing-0.005
outed-0.004
ries-0.004
nam-0.004
Token "
Token ID366
Feature activation+1.07e-02

Pos logit contributions
yles+0.012
outing+0.012
outed+0.011
ries+0.011
ateful+0.011
Neg logit contributions
age-0.011
est-0.010
-0.008
 ok-0.008
ze-0.007
TokenFlags
Token ID40053
Feature activation-1.05e-01

Pos logit contributions
yles+0.018
outing+0.017
outed+0.016
ries+0.016
ateful+0.016
Neg logit contributions
age-0.020
est-0.018
-0.016
 ok-0.015
ze-0.014
Token go
Token ID467
Feature activation+4.82e-03

Pos logit contributions
age+0.216
est+0.189
+0.163
 ok+0.163
ze+0.156
Neg logit contributions
yles-0.155
outing-0.140
ateful-0.131
ries-0.131
eling-0.130
Token up
Token ID510
Feature activation+1.16e-02

Pos logit contributions
yles+0.009
outing+0.008
ries+0.008
outed+0.008
nam+0.008
Neg logit contributions
age-0.009
est-0.007
-0.006
 ok-0.006
ze-0.006
Token there
Token ID612
Feature activation-1.14e-02

Pos logit contributions
yles+0.017
outing+0.016
ateful+0.015
nam+0.015
ries+0.015
Neg logit contributions
age-0.024
est-0.021
ze-0.017
-0.017
ench-0.017
Token to
Token ID284
Feature activation+2.33e-02

Pos logit contributions
age+0.018
est+0.015
+0.013
ze+0.012
 ok+0.012
Neg logit contributions
yles-0.022
outing-0.020
ries-0.019
ateful-0.019
outed-0.019
Token wave
Token ID6769
Feature activation+3.25e-02

Pos logit contributions
yles+0.048
outing+0.045
outed+0.044
ries+0.042
ateful+0.041
Neg logit contributions
age-0.037
est-0.031
-0.028
 ok-0.026
ze-0.025
Token didn
Token ID1422
Feature activation-2.94e-02

Pos logit contributions
age+0.027
est+0.023
+0.023
 ok+0.020
ze+0.020
Neg logit contributions
yles-0.020
outing-0.019
ries-0.018
ateful-0.017
outed-0.017
Token't
Token ID470
Feature activation-1.02e-02

Pos logit contributions
age+0.055
est+0.051
 ok+0.041
ench+0.038
 biggest+0.038
Neg logit contributions
yles-0.049
outing-0.044
ries-0.042
ateful-0.041
outed-0.041
Token know
Token ID760
Feature activation+3.38e-02

Pos logit contributions
age+0.019
est+0.017
+0.015
 ok+0.014
ze+0.013
Neg logit contributions
yles-0.018
outing-0.017
outed-0.016
ries-0.016
ateful-0.015
Token what
Token ID644
Feature activation+1.49e-02

Pos logit contributions
yles+0.052
outing+0.051
outed+0.050
ateful+0.047
eling+0.044
Neg logit contributions
age-0.062
est-0.059
-0.055
 ok-0.053
 best-0.051
Token "
Token ID366
Feature activation+8.19e-03

Pos logit contributions
yles+0.027
outing+0.025
outed+0.023
ries+0.023
ateful+0.023
Neg logit contributions
age-0.027
est-0.024
-0.021
 ok-0.020
ze-0.019
Tokennos
Token ID39369
Feature activation-1.05e-01

Pos logit contributions
yles+0.014
outing+0.013
outed+0.012
ries+0.012
ateful+0.012
Neg logit contributions
age-0.016
est-0.014
-0.012
 ok-0.011
ze-0.011
Tokeny
Token ID88
Feature activation-8.35e-03

Pos logit contributions
age+0.253
est+0.224
+0.214
 ok+0.206
ze+0.203
Neg logit contributions
yles-0.111
outing-0.107
ateful-0.096
outed-0.095
ries-0.091
Token"
Token ID1
Feature activation+2.49e-02

Pos logit contributions
age+0.009
est+0.007
 ok+0.006
+0.006
 biggest+0.006
Neg logit contributions
yles-0.018
outing-0.017
ries-0.017
ateful-0.017
 arose-0.016
Token meant
Token ID4001
Feature activation-5.24e-03

Pos logit contributions
yles+0.041
outing+0.038
outed+0.036
ries+0.036
ateful+0.035
Neg logit contributions
age-0.048
est-0.042
-0.038
 ok-0.036
ze-0.035
Token,
Token ID11
Feature activation+4.45e-03

Pos logit contributions
age+0.008
est+0.006
ench+0.005
+0.005
 biggest+0.005
Neg logit contributions
yles-0.011
outing-0.010
ries-0.010
nam-0.010
ateful-0.009
Token so
Token ID523
Feature activation+2.31e-02

Pos logit contributions
yles+0.010
outing+0.009
ries+0.009
ateful+0.009
outed+0.009
Neg logit contributions
age-0.006
est-0.005
-0.004
 ok-0.004
ze-0.004
Token?"
Token ID1701
Feature activation+3.53e-02

Pos logit contributions
yles+0.050
ries+0.048
outing+0.047
ila+0.044
outed+0.044
Neg logit contributions
age-0.042
est-0.036
-0.032
 ok-0.031
 biggest-0.030
Token Mom
Token ID11254
Feature activation+1.20e-02

Pos logit contributions
yles+0.062
outing+0.060
ries+0.056
eling+0.055
ge+0.054
Neg logit contributions
age-0.058
-0.057
est-0.052
 middle-0.048
 ok-0.048
Token yells
Token ID42675
Feature activation+4.34e-03

Pos logit contributions
yles+0.015
nam+0.013
outing+0.012
ateful+0.012
outed+0.011
Neg logit contributions
age-0.027
-0.025
est-0.025
 right-0.022
 ok-0.022
Token.
Token ID13
Feature activation+8.89e-03

Pos logit contributions
yles+0.008
outing+0.007
ries+0.007
outed+0.007
ateful+0.007
Neg logit contributions
age-0.008
est-0.007
 ok-0.006
-0.005
sy-0.005
Token "
Token ID366
Feature activation+1.21e-02

Pos logit contributions
yles+0.020
outing+0.019
eling+0.018
ries+0.018
ateful+0.018
Neg logit contributions
age-0.012
est-0.010
-0.009
 ok-0.008
ze-0.007
TokenYOU
Token ID36981
Feature activation-1.04e-01

Pos logit contributions
yles+0.024
outed+0.024
ries+0.023
outing+0.023
ours+0.022
Neg logit contributions
age-0.017
-0.015
ze-0.013
 entire-0.012
est-0.012
Token ARE
Token ID15986
Feature activation+2.59e-02

Pos logit contributions
age+0.183
est+0.160
+0.137
 ok+0.134
ze+0.125
Neg logit contributions
yles-0.186
outing-0.175
ries-0.165
outed-0.165
eling-0.164
Token MA
Token ID8779
Feature activation-6.96e-02

Pos logit contributions
yles+0.039
outing+0.037
ries+0.036
ateful+0.035
eling+0.034
Neg logit contributions
age-0.054
est-0.047
sy-0.038
 ok-0.038
nob-0.037
TokenKING
Token ID37286
Feature activation+1.03e-02

Pos logit contributions
age+0.127
est+0.116
+0.101
 ok+0.098
 best+0.092
Neg logit contributions
yles-0.114
outing-0.113
ateful-0.106
outed-0.105
ries-0.103
Token A
Token ID317
Feature activation+4.88e-03

Pos logit contributions
yles+0.017
ries+0.015
outing+0.015
 arose+0.015
ila+0.015
Neg logit contributions
age-0.017
est-0.016
 ok-0.014
 best-0.014
sy-0.014
Token M
Token ID337
Feature activation-1.04e-02

Pos logit contributions
yles+0.009
outing+0.008
ries+0.008
outed+0.008
ateful+0.007
Neg logit contributions
age-0.009
est-0.008
-0.007
 ok-0.006
ze-0.006
Token she
Token ID673
Feature activation-5.43e-03

Pos logit contributions
age+0.007
+0.006
 ok+0.006
est+0.006
 best+0.006
Neg logit contributions
yles-0.004
outing-0.004
outed-0.004
ateful-0.004
eling-0.004
Token could
Token ID714
Feature activation+8.04e-03

Pos logit contributions
age+0.011
est+0.010
+0.009
 ok+0.009
ze+0.008
Neg logit contributions
yles-0.008
outing-0.007
ries-0.007
outed-0.007
ateful-0.007
Token help
Token ID1037
Feature activation+3.59e-03

Pos logit contributions
yles+0.011
 spill+0.010
outing+0.010
 brushes+0.009
ries+0.009
Neg logit contributions
age-0.016
est-0.015
 biggest-0.012
>-0.012
 ok-0.012
Token the
Token ID262
Feature activation-1.17e-02

Pos logit contributions
yles+0.005
ries+0.005
outing+0.005
nam+0.005
eling+0.005
Neg logit contributions
age-0.008
est-0.007
-0.006
 ok-0.006
sy-0.005
Token tea
Token ID8887
Feature activation-5.79e-02

Pos logit contributions
age+0.023
est+0.020
+0.017
 ok+0.017
sy+0.016
Neg logit contributions
yles-0.019
outing-0.017
ries-0.017
ateful-0.017
nam-0.017
Token del
Token ID1619
Feature activation-1.04e-01

Pos logit contributions
age+0.094
est+0.079
+0.067
 ok+0.065
ze+0.062
Neg logit contributions
yles-0.108
outing-0.103
ries-0.101
outed-0.097
ateful-0.095
Tokenive
Token ID425
Feature activation-5.99e-03

Pos logit contributions
age+0.164
est+0.136
+0.122
 ok+0.113
 biggest+0.109
Neg logit contributions
yles-0.206
outing-0.196
ries-0.187
outed-0.186
ateful-0.181
Tokenrer
Token ID11751
Feature activation-5.37e-02

Pos logit contributions
age+0.010
est+0.008
+0.007
 ok+0.007
ze+0.007
Neg logit contributions
yles-0.011
outing-0.011
ries-0.010
outed-0.010
ateful-0.010
Token by
Token ID416
Feature activation-5.52e-03

Pos logit contributions
age+0.091
est+0.077
 ok+0.060
ench+0.059
+0.059
Neg logit contributions
yles-0.097
outing-0.092
ries-0.091
outed-0.085
ateful-0.084
Token taking
Token ID2263
Feature activation-1.60e-02

Pos logit contributions
age+0.010
est+0.009
+0.008
 ok+0.008
ze+0.008
Neg logit contributions
yles-0.010
outing-0.009
outed-0.008
ateful-0.008
ries-0.008
Token the
Token ID262
Feature activation-8.79e-03

Pos logit contributions
age+0.034
est+0.030
+0.025
 ok+0.025
ench+0.024
Neg logit contributions
yles-0.023
ries-0.021
outing-0.020
eling-0.020
ateful-0.019
Token on
Token ID319
Feature activation-1.88e-03

Pos logit contributions
yles+0.020
outing+0.018
ries+0.018
outed+0.018
ateful+0.017
Neg logit contributions
age-0.012
est-0.010
-0.008
 ok-0.008
ze-0.007
Token long
Token ID890
Feature activation+3.55e-03

Pos logit contributions
age+0.003
est+0.002
+0.002
 best+0.002
 ok+0.002
Neg logit contributions
outing-0.004
yles-0.004
outed-0.003
ateful-0.003
ries-0.003
Token car
Token ID1097
Feature activation+7.17e-04

Pos logit contributions
yles+0.006
outing+0.006
ateful+0.005
outed+0.005
ries+0.005
Neg logit contributions
age-0.007
est-0.006
-0.005
 ok-0.005
ze-0.005
Token trips
Token ID13229
Feature activation+2.33e-02

Pos logit contributions
yles+0.002
outing+0.001
outed+0.001
ries+0.001
ateful+0.001
Neg logit contributions
age-0.001
est-0.001
-0.001
 ok-0.001
ze-0.001
Token to
Token ID284
Feature activation+2.45e-02

Pos logit contributions
yles+0.045
outing+0.042
outed+0.040
ries+0.039
nam+0.039
Neg logit contributions
age-0.039
est-0.034
-0.029
 ok-0.028
ze-0.027
Token many
Token ID867
Feature activation+7.58e-02

Pos logit contributions
yles+0.050
outing+0.049
outed+0.047
ries+0.046
ateful+0.044
Neg logit contributions
age-0.038
est-0.033
-0.028
 ok-0.026
 biggest-0.026
Token different
Token ID1180
Feature activation+2.46e-03

Pos logit contributions
yles+0.145
outing+0.140
outed+0.132
ries+0.128
ateful+0.125
Neg logit contributions
age-0.121
est-0.113
-0.096
 best-0.088
 ok-0.086
Token places
Token ID4113
Feature activation+1.81e-02

Pos logit contributions
yles+0.004
outing+0.004
outed+0.004
ries+0.004
ateful+0.004
Neg logit contributions
age-0.004
est-0.004
-0.003
 ok-0.003
 best-0.003
Token.
Token ID13
Feature activation+3.19e-03

Pos logit contributions
yles+0.038
outing+0.035
ries+0.034
outed+0.033
ateful+0.033
Neg logit contributions
age-0.027
est-0.023
-0.020
 ok-0.018
ze-0.017
Token One
Token ID1881
Feature activation-2.12e-02

Pos logit contributions
yles+0.007
outing+0.006
outed+0.006
ries+0.006
ateful+0.006
Neg logit contributions
age-0.005
est-0.004
-0.003
 ok-0.003
ze-0.003
Token day
Token ID1110
Feature activation-1.78e-03

Pos logit contributions
age+0.026
est+0.021
+0.017
 ok+0.015
ze+0.014
Neg logit contributions
yles-0.052
outing-0.049
ries-0.047
outed-0.046
ateful-0.046
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
yles+0.015
ries+0.013
outing+0.013
eling+0.012
outed+0.012
Neg logit contributions
age-0.023
est-0.019
 ok-0.017
ench-0.017
-0.016
Token handles
Token ID17105
Feature activation-1.22e-02

Pos logit contributions
age+0.033
est+0.029
 ok+0.026
+0.026
nob+0.025
Neg logit contributions
yles-0.022
 brushes-0.022
outing-0.021
nam-0.021
outed-0.020
Token and
Token ID290
Feature activation+1.44e-03

Pos logit contributions
age+0.019
est+0.015
 ok+0.013
+0.012
ze+0.012
Neg logit contributions
yles-0.024
outing-0.024
ries-0.022
outed-0.022
nam-0.022
Token g
Token ID308
Feature activation+8.94e-03

Pos logit contributions
yles+0.002
outing+0.002
outed+0.002
ateful+0.002
ries+0.002
Neg logit contributions
age-0.003
est-0.002
-0.002
 ok-0.002
ze-0.002
Tokeniggle
Token ID24082
Feature activation-1.04e-02

Pos logit contributions
yles+0.017
nam+0.016
outing+0.016
ateful+0.015
ries+0.015
Neg logit contributions
age-0.015
est-0.013
 ok-0.010
-0.010
ze-0.010
Token as
Token ID355
Feature activation+6.59e-02

Pos logit contributions
age+0.019
est+0.015
+0.013
 ok+0.013
ench+0.013
Neg logit contributions
yles-0.018
outing-0.016
ries-0.015
nam-0.015
outed-0.015
Token she
Token ID673
Feature activation-1.22e-02

Pos logit contributions
yles+0.069
outing+0.060
outed+0.054
ries+0.054
ateful+0.053
Neg logit contributions
age-0.168
est-0.152
-0.141
 ok-0.136
ze-0.132
Token went
Token ID1816
Feature activation-7.08e-04

Pos logit contributions
age+0.026
est+0.023
+0.022
ze+0.020
 ok+0.019
Neg logit contributions
yles-0.017
outing-0.016
ateful-0.015
ries-0.015
nam-0.015
Token up
Token ID510
Feature activation+3.10e-03

Pos logit contributions
age+0.001
est+0.001
 ok+0.001
+0.001
ze+0.001
Neg logit contributions
yles-0.001
ries-0.001
outing-0.001
 brushes-0.001
 spill-0.001
Token,
Token ID11
Feature activation-2.62e-03

Pos logit contributions
yles+0.006
outing+0.005
ries+0.005
outed+0.005
nam+0.005
Neg logit contributions
age-0.006
est-0.005
 ok-0.004
-0.004
ze-0.004
Token up
Token ID510
Feature activation+2.77e-03

Pos logit contributions
age+0.005
est+0.004
+0.003
 ok+0.003
ench+0.003
Neg logit contributions
yles-0.005
outing-0.004
nam-0.004
eling-0.004
outed-0.004
Token and
Token ID290
Feature activation-3.90e-03

Pos logit contributions
yles+0.004
ries+0.003
outing+0.003
nam+0.003
 brushes+0.003
Neg logit contributions
age-0.006
est-0.005
ench-0.004
ze-0.004
 ok-0.004
Token tug
Token ID27762
Feature activation+4.56e-02

Pos logit contributions
age+0.007
+0.007
est+0.006
 ok+0.006
 right+0.006
Neg logit contributions
outing-0.006
yles-0.006
ateful-0.006
outed-0.006
ries-0.006
Tokenged
Token ID2004
Feature activation+5.58e-02

Pos logit contributions
yles+0.067
outing+0.061
ries+0.057
outed+0.057
ateful+0.056
Neg logit contributions
age-0.098
est-0.086
-0.078
 ok-0.075
ze-0.072
Token as
Token ID355
Feature activation+6.93e-02

Pos logit contributions
yles+0.106
outing+0.099
ries+0.097
nam+0.092
eling+0.091
Neg logit contributions
age-0.095
est-0.075
ench-0.061
ze-0.060
 entire-0.059
Token hard
Token ID1327
Feature activation+1.23e-03

Pos logit contributions
yles+0.133
outing+0.122
outed+0.117
ries+0.117
eling+0.116
Neg logit contributions
age-0.112
est-0.098
-0.097
 ok-0.084
 best-0.083
Token as
Token ID355
Feature activation+6.91e-02

Pos logit contributions
yles+0.002
outing+0.002
outed+0.002
ateful+0.002
ries+0.002
Neg logit contributions
age-0.002
est-0.002
-0.002
 ok-0.001
ze-0.001
Token she
Token ID673
Feature activation-1.39e-02

Pos logit contributions
yles+0.077
outing+0.069
outed+0.063
ries+0.061
ateful+0.060
Neg logit contributions
age-0.170
est-0.155
-0.147
 ok-0.140
 best-0.134
Token could
Token ID714
Feature activation+7.74e-03

Pos logit contributions
age+0.025
est+0.022
+0.021
 ok+0.019
 best+0.018
Neg logit contributions
yles-0.025
outing-0.023
ries-0.023
ateful-0.022
eling-0.022
Token,
Token ID11
Feature activation-1.20e-03

Pos logit contributions
yles+0.016
outing+0.015
outed+0.014
ries+0.014
ateful+0.014
Neg logit contributions
age-0.011
est-0.010
-0.008
 ok-0.007
ze-0.007
Token but
Token ID475
Feature activation-3.06e-02

Pos logit contributions
age+0.002
est+0.002
+0.001
 ok+0.001
ench+0.001
Neg logit contributions
yles-0.002
outing-0.002
eling-0.002
nam-0.002
ries-0.002
Token the
Token ID262
Feature activation-1.15e-02

Pos logit contributions
age+0.062
est+0.054
+0.052
 ok+0.049
ze+0.046
Neg logit contributions
yles-0.048
outing-0.044
ateful-0.041
ries-0.041
outed-0.041
Token
Token ID220
Feature activation+3.05e-02

Pos logit contributions
age+0.035
est+0.034
 ok+0.025
 biggest+0.025
+0.024
Neg logit contributions
yles-0.044
outing-0.041
outed-0.040
ries-0.038
eling-0.038
Token
Token ID198
Feature activation-1.38e-02

Pos logit contributions
yles+0.059
outing+0.056
outed+0.054
ries+0.051
ateful+0.050
Neg logit contributions
age-0.049
est-0.044
ze-0.035
 ok-0.034
-0.034
Token
Token ID198
Feature activation-1.41e-02

Pos logit contributions
age+0.023
est+0.022
ze+0.017
 ok+0.016
 biggest+0.016
Neg logit contributions
yles-0.026
outing-0.024
outed-0.023
ila-0.022
ateful-0.022
TokenThe
Token ID464
Feature activation-1.12e-02

Pos logit contributions
age+0.027
est+0.025
 biggest+0.020
 ok+0.020
 best+0.020
Neg logit contributions
yles-0.023
outing-0.021
ateful-0.019
outed-0.019
eling-0.019
Token b
Token ID275
Feature activation-1.87e-02

Pos logit contributions
age+0.021
est+0.018
ench+0.015
+0.015
nob+0.014
Neg logit contributions
yles-0.018
outing-0.018
nam-0.017
outed-0.017
ateful-0.017
Tokenunn
Token ID20935
Feature activation+7.20e-02

Pos logit contributions
age+0.041
est+0.036
+0.032
 ok+0.031
ze+0.030
Neg logit contributions
yles-0.027
outing-0.025
ries-0.023
outed-0.023
ateful-0.023
Tokenies
Token ID444
Feature activation-1.12e-02

Pos logit contributions
yles+0.058
outing+0.049
ries+0.042
outed+0.042
ateful+0.041
Neg logit contributions
age-0.201
est-0.182
-0.170
 ok-0.165
ze-0.161
Token looked
Token ID3114
Feature activation-4.29e-04

Pos logit contributions
age+0.024
est+0.021
+0.019
 ok+0.018
ze+0.018
Neg logit contributions
yles-0.016
outing-0.015
ries-0.014
ateful-0.014
outed-0.014
Token at
Token ID379
Feature activation+2.00e-02

Pos logit contributions
age+0.001
est+0.001
nob+0.001
+0.001
ze+0.001
Neg logit contributions
yles-0.001
outed-0.001
outing-0.001
nam-0.001
ries-0.001
Token each
Token ID1123
Feature activation-8.56e-03

Pos logit contributions
yles+0.034
outing+0.034
outed+0.030
ateful+0.029
eling+0.028
Neg logit contributions
age-0.033
est-0.032
-0.029
 ok-0.027
 best-0.026
Token other
Token ID584
Feature activation+3.07e-02

Pos logit contributions
age+0.015
est+0.013
+0.012
 ok+0.011
ze+0.011
Neg logit contributions
yles-0.016
outing-0.014
ries-0.014
outed-0.014
ateful-0.014
Token were
Token ID547
Feature activation+2.73e-02

Pos logit contributions
age+0.001
est+0.000
+0.000
 ok+0.000
 best+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.000
ateful-0.000
ries-0.000
Token burying
Token ID48360
Feature activation+1.48e-02

Pos logit contributions
yles+0.047
outing+0.044
ries+0.041
outed+0.041
ateful+0.041
Neg logit contributions
age-0.051
est-0.044
-0.038
 ok-0.036
ze-0.035
Token something
Token ID1223
Feature activation+3.48e-02

Pos logit contributions
yles+0.024
outing+0.022
ries+0.022
ateful+0.021
outed+0.021
Neg logit contributions
age-0.030
est-0.025
-0.022
 ok-0.020
ze-0.020
Token from
Token ID422
Feature activation+3.74e-03

Pos logit contributions
yles+0.058
outing+0.056
ries+0.053
outed+0.052
eling+0.051
Neg logit contributions
age-0.067
est-0.055
-0.045
ze-0.045
 ok-0.044
Token long
Token ID890
Feature activation-1.45e-03

Pos logit contributions
yles+0.006
outing+0.006
outed+0.006
ateful+0.005
ries+0.005
Neg logit contributions
age-0.007
est-0.006
-0.005
 ok-0.005
ze-0.005
Token ago
Token ID2084
Feature activation+8.72e-02

Pos logit contributions
age+0.002
est+0.002
+0.002
 ok+0.002
ze+0.002
Neg logit contributions
yles-0.003
outing-0.003
ries-0.002
outed-0.002
ateful-0.002
Token that
Token ID326
Feature activation+1.22e-02

Pos logit contributions
yles+0.169
outing+0.159
ries+0.156
outed+0.153
ateful+0.150
Neg logit contributions
age-0.138
est-0.115
-0.100
 ok-0.094
ze-0.089
Token made
Token ID925
Feature activation-3.42e-02

Pos logit contributions
yles+0.019
outing+0.017
ries+0.016
outed+0.016
ateful+0.016
Neg logit contributions
age-0.025
est-0.022
-0.019
 ok-0.018
ze-0.018
Token them
Token ID606
Feature activation-1.73e-02

Pos logit contributions
age+0.071
est+0.064
+0.059
 ok+0.057
ze+0.054
Neg logit contributions
yles-0.051
outing-0.047
outed-0.044
ateful-0.043
ries-0.043
Token feel
Token ID1254
Feature activation-2.12e-03

Pos logit contributions
age+0.030
est+0.026
+0.021
 ok+0.020
ze+0.020
Neg logit contributions
yles-0.031
outing-0.029
nam-0.028
ateful-0.028
outed-0.028
Token sad
Token ID6507
Feature activation+1.82e-02

Pos logit contributions
age+0.004
est+0.003
nob+0.003
>+0.002
ze+0.002
Neg logit contributions
yles-0.004
outing-0.003
eling-0.003
ateful-0.003
outed-0.003
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
age+0.008
est+0.007
+0.007
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.006
outing-0.005
outed-0.005
ries-0.005
ateful-0.005
Token king
Token ID5822
Feature activation-8.71e-03

Pos logit contributions
age+0.024
est+0.019
+0.018
 ok+0.017
ze+0.016
Neg logit contributions
yles-0.021
ateful-0.020
outing-0.020
nam-0.020
eling-0.019
Token knew
Token ID2993
Feature activation+3.42e-03

Pos logit contributions
age+0.015
est+0.013
+0.011
 ok+0.011
ze+0.010
Neg logit contributions
yles-0.016
outing-0.015
outed-0.014
ries-0.014
ateful-0.014
Token that
Token ID326
Feature activation+1.23e-02

Pos logit contributions
yles+0.006
outing+0.006
outed+0.005
ries+0.005
ateful+0.005
Neg logit contributions
age-0.006
est-0.005
-0.005
 ok-0.005
 best-0.004
Token he
Token ID339
Feature activation+1.37e-02

Pos logit contributions
yles+0.020
outing+0.018
ries+0.017
ateful+0.017
outed+0.017
Neg logit contributions
age-0.024
est-0.021
-0.019
 ok-0.018
ze-0.017
Token could
Token ID714
Feature activation+1.26e-02

Pos logit contributions
yles+0.022
outing+0.020
outed+0.019
ries+0.019
ateful+0.019
Neg logit contributions
age-0.027
est-0.023
-0.021
 ok-0.020
ze-0.019
Token always
Token ID1464
Feature activation-3.88e-03

Pos logit contributions
yles+0.019
eling+0.017
outing+0.017
 spill+0.017
ateful+0.017
Neg logit contributions
age-0.023
est-0.022
 ok-0.017
>-0.017
ger-0.017
Token count
Token ID954
Feature activation-3.05e-03

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
ze+0.005
Neg logit contributions
yles-0.007
outing-0.006
eling-0.006
ateful-0.006
nam-0.006
Token on
Token ID319
Feature activation-9.12e-03

Pos logit contributions
age+0.005
est+0.004
+0.004
 ok+0.003
ze+0.003
Neg logit contributions
yles-0.006
outing-0.006
outed-0.005
ries-0.005
ateful-0.005
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
age+0.018
est+0.016
+0.014
 ok+0.014
ze+0.013
Neg logit contributions
yles-0.015
outing-0.013
ries-0.013
outed-0.013
ateful-0.013
Token wizard
Token ID18731
Feature activation+4.48e-02

Pos logit contributions
age+0.021
est+0.016
+0.015
 ok+0.014
ench+0.014
Neg logit contributions
yles-0.017
outing-0.016
nam-0.016
ateful-0.015
 brushes-0.015
Token catch
Token ID4929
Feature activation+2.24e-02

Pos logit contributions
yles+0.044
outing+0.042
outed+0.040
ries+0.040
ateful+0.038
Neg logit contributions
age-0.036
est-0.030
-0.027
 ok-0.024
ze-0.024
Token fish
Token ID5916
Feature activation+6.12e-03

Pos logit contributions
yles+0.033
ries+0.029
outing+0.029
ateful+0.028
eling+0.027
Neg logit contributions
age-0.050
est-0.040
 ok-0.036
-0.036
sy-0.034
Token.
Token ID13
Feature activation-1.20e-03

Pos logit contributions
yles+0.011
outing+0.011
ries+0.010
ateful+0.010
outed+0.010
Neg logit contributions
age-0.010
est-0.009
 ok-0.008
-0.007
nob-0.007
Token He
Token ID679
Feature activation-7.09e-03

Pos logit contributions
age+0.002
est+0.001
+0.001
 ok+0.001
ze+0.001
Neg logit contributions
yles-0.003
outing-0.003
ries-0.002
outed-0.002
ateful-0.002
Token liked
Token ID8288
Feature activation-2.64e-04

Pos logit contributions
age+0.013
est+0.011
+0.010
 ok+0.010
ze+0.009
Neg logit contributions
yles-0.012
outing-0.011
ries-0.011
ateful-0.011
outed-0.011
Token his
Token ID465
Feature activation+3.06e-02

Pos logit contributions
age+0.000
est+0.000
+0.000
 right+0.000
 best+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.001
ateful-0.001
eling-0.001
Token job
Token ID1693
Feature activation-9.43e-03

Pos logit contributions
yles+0.056
outing+0.052
ries+0.049
outed+0.048
ateful+0.048
Neg logit contributions
age-0.055
est-0.048
-0.041
 ok-0.040
 best-0.039
Token.
Token ID13
Feature activation+1.08e-03

Pos logit contributions
age+0.015
est+0.013
+0.011
 ok+0.010
ze+0.010
Neg logit contributions
yles-0.019
outing-0.018
ries-0.017
outed-0.017
ateful-0.017
Token
Token ID198
Feature activation-6.81e-03

Pos logit contributions
yles+0.002
outing+0.002
outed+0.002
ries+0.002
ateful+0.002
Neg logit contributions
age-0.002
est-0.001
-0.001
 ok-0.001
ze-0.001
Token
Token ID198
Feature activation-7.60e-03

Pos logit contributions
age+0.010
est+0.008
+0.007
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.015
outing-0.014
outed-0.013
ries-0.013
ateful-0.013
TokenOne
Token ID3198
Feature activation-1.89e-02

Pos logit contributions
age+0.013
est+0.012
 ok+0.010
+0.010
ze+0.010
Neg logit contributions
yles-0.013
outing-0.013
outed-0.012
ateful-0.011
ries-0.011
Token beach
Token ID10481
Feature activation+2.24e-02

Pos logit contributions
age+0.021
est+0.018
 ok+0.016
+0.016
nob+0.015
Neg logit contributions
yles-0.013
outing-0.012
ateful-0.011
outed-0.011
eling-0.011
Token.
Token ID13
Feature activation-2.64e-04

Pos logit contributions
yles+0.043
outing+0.040
ries+0.039
outed+0.038
ateful+0.037
Neg logit contributions
age-0.037
est-0.031
-0.027
 ok-0.026
ze-0.025
Token Jane
Token ID12091
Feature activation+1.82e-03

Pos logit contributions
age+0.000
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.000
outing-0.000
outed-0.000
ries-0.000
ateful-0.000
Token looked
Token ID3114
Feature activation+1.78e-03

Pos logit contributions
yles+0.003
outing+0.002
outed+0.002
ries+0.002
eling+0.002
Neg logit contributions
age-0.004
est-0.003
-0.003
 ok-0.003
ze-0.003
Token at
Token ID379
Feature activation+2.50e-02

Pos logit contributions
yles+0.003
outed+0.003
outing+0.003
nam+0.003
eling+0.003
Neg logit contributions
age-0.003
est-0.002
ze-0.002
nob-0.002
-0.002
Token Joe
Token ID5689
Feature activation+1.85e-02

Pos logit contributions
outing+0.052
yles+0.050
outed+0.047
ateful+0.046
ins+0.045
Neg logit contributions
est-0.033
age-0.029
-0.028
 biggest-0.027
 back-0.027
Token,
Token ID11
Feature activation-3.25e-03

Pos logit contributions
yles+0.038
outing+0.036
ries+0.034
eling+0.034
outed+0.034
Neg logit contributions
age-0.028
est-0.023
 ok-0.019
-0.017
ze-0.017
Token who
Token ID508
Feature activation-8.88e-03

Pos logit contributions
age+0.005
est+0.005
+0.004
 ok+0.004
ze+0.004
Neg logit contributions
yles-0.006
outing-0.006
ateful-0.006
ries-0.006
outed-0.005
Token was
Token ID373
Feature activation+8.75e-04

Pos logit contributions
age+0.011
+0.010
est+0.009
 ok+0.007
 best+0.007
Neg logit contributions
yles-0.019
outing-0.019
ries-0.018
ateful-0.018
nam-0.018
Token jumping
Token ID14284
Feature activation-3.26e-02

Pos logit contributions
yles+0.002
outing+0.002
outed+0.001
ateful+0.001
ries+0.001
Neg logit contributions
age-0.002
est-0.001
-0.001
 ok-0.001
ze-0.001
Token up
Token ID510
Feature activation+7.98e-03

Pos logit contributions
age+0.060
est+0.044
 ok+0.038
ench+0.037
house+0.036
Neg logit contributions
outing-0.056
yles-0.054
outed-0.051
ries-0.049
 they-0.049
Token shining
Token ID22751
Feature activation+4.69e-03

Pos logit contributions
age+0.016
est+0.014
+0.011
nob+0.011
 ok+0.011
Neg logit contributions
yles-0.012
outing-0.012
nam-0.011
 spill-0.011
ateful-0.010
Token penny
Token ID26369
Feature activation-8.30e-03

Pos logit contributions
ries+0.006
 spill+0.006
yles+0.006
outing+0.006
 tilted+0.005
Neg logit contributions
age-0.010
 ok-0.008
-0.007
tted-0.007
est-0.007
Token and
Token ID290
Feature activation+1.70e-03

Pos logit contributions
age+0.013
est+0.011
 ok+0.009
+0.008
ench+0.008
Neg logit contributions
yles-0.016
outing-0.015
ries-0.015
eling-0.015
outed-0.014
Token picked
Token ID6497
Feature activation+1.45e-02

Pos logit contributions
yles+0.002
outing+0.002
ateful+0.002
ries+0.002
outed+0.002
Neg logit contributions
age-0.004
est-0.003
-0.003
 ok-0.003
ze-0.003
Token it
Token ID340
Feature activation+1.00e-03

Pos logit contributions
yles+0.016
ries+0.013
outing+0.012
eling+0.011
 inspection+0.011
Neg logit contributions
age-0.037
est-0.031
 ok-0.029
iver-0.028
sy-0.028
Token up
Token ID510
Feature activation+1.03e-02

Pos logit contributions
yles+0.001
outing+0.001
 they+0.001
ries+0.001
outed+0.001
Neg logit contributions
age-0.002
est-0.001
tted-0.001
iver-0.001
 virtue-0.001
Token.
Token ID13
Feature activation-1.26e-03

Pos logit contributions
outing+0.017
yles+0.017
outed+0.016
ries+0.016
nam+0.016
Neg logit contributions
age-0.019
est-0.016
ze-0.013
-0.013
 ok-0.012
Token She
Token ID1375
Feature activation-1.51e-02

Pos logit contributions
age+0.003
est+0.002
ze+0.002
sy+0.002
 ok+0.002
Neg logit contributions
yles-0.002
outed-0.002
outing-0.002
nam-0.002
 brushes-0.001
Token smiled
Token ID13541
Feature activation+5.01e-03

Pos logit contributions
age+0.033
est+0.029
+0.027
 ok+0.026
ze+0.025
Neg logit contributions
yles-0.021
outing-0.019
ries-0.018
outed-0.018
ateful-0.018
Token and
Token ID290
Feature activation-4.16e-04

Pos logit contributions
yles+0.009
outing+0.009
outed+0.008
ateful+0.008
ries+0.008
Neg logit contributions
age-0.009
est-0.007
-0.006
nob-0.006
 ok-0.006
Token said
Token ID531
Feature activation-4.97e-03

Pos logit contributions
age+0.001
+0.001
est+0.001
 ok+0.001
 right+0.001
Neg logit contributions
yles-0.001
outing-0.001
ateful-0.001
ries-0.001
eling-0.001
Token baby
Token ID5156
Feature activation-3.18e-02

Pos logit contributions
age+0.011
est+0.009
+0.008
 ok+0.008
nob+0.008
Neg logit contributions
yles-0.008
outing-0.007
outed-0.007
ries-0.007
ateful-0.007
Token's
Token ID338
Feature activation+1.38e-02

Pos logit contributions
age+0.069
est+0.062
+0.056
 ok+0.055
ench+0.052
Neg logit contributions
yles-0.041
outing-0.039
outed-0.037
ries-0.036
eling-0.035
Token tears
Token ID10953
Feature activation+3.11e-02

Pos logit contributions
yles+0.023
outing+0.022
outed+0.021
ries+0.020
ateful+0.020
Neg logit contributions
age-0.025
est-0.022
-0.020
nob-0.018
 ok-0.018
Token slowly
Token ID6364
Feature activation-6.22e-03

Pos logit contributions
yles+0.057
outing+0.051
ateful+0.049
ries+0.049
nam+0.048
Neg logit contributions
age-0.057
est-0.050
-0.045
 ok-0.042
ze-0.041
Token stopped
Token ID5025
Feature activation+9.00e-03

Pos logit contributions
age+0.011
est+0.009
+0.008
ze+0.007
 ok+0.007
Neg logit contributions
yles-0.013
outing-0.011
ateful-0.011
nam-0.011
ries-0.011
Token and
Token ID290
Feature activation-5.15e-05

Pos logit contributions
yles+0.017
outing+0.016
outed+0.015
ateful+0.015
ries+0.015
Neg logit contributions
age-0.015
est-0.013
-0.012
 ok-0.011
ze-0.010
Token the
Token ID262
Feature activation-6.72e-03

Pos logit contributions
age+0.000
+0.000
est+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.000
outing-0.000
ateful-0.000
ries-0.000
outed-0.000
Token baby
Token ID5156
Feature activation-3.03e-02

Pos logit contributions
age+0.014
est+0.012
+0.011
 ok+0.011
nob+0.010
Neg logit contributions
yles-0.010
outing-0.009
ries-0.008
outed-0.008
ateful-0.008
Token fell
Token ID3214
Feature activation-3.03e-02

Pos logit contributions
age+0.062
est+0.055
+0.049
 ok+0.047
ze+0.045
Neg logit contributions
yles-0.046
outing-0.042
outed-0.040
ries-0.040
ateful-0.039
Token asleep
Token ID16039
Feature activation-1.20e-02

Pos logit contributions
age+0.051
est+0.046
+0.040
 ok+0.037
ench+0.037
Neg logit contributions
outing-0.051
yles-0.049
outed-0.048
ries-0.046
nam-0.043
Token.
Token ID13
Feature activation-2.40e-03

Pos logit contributions
age+0.020
est+0.017
+0.015
 ok+0.014
 biggest+0.013
Neg logit contributions
yles-0.022
outing-0.021
nam-0.020
outed-0.020
eling-0.020
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
 right+0.020
 back+0.020
 middle+0.020
 safe+0.019
 best+0.019
Neg logit contributions
outing-0.054
yles-0.054
outed-0.051
ateful-0.050
ins-0.048
Token top
Token ID1353
Feature activation-5.04e-02

Pos logit contributions
age+0.022
est+0.019
+0.017
 ok+0.016
ze+0.015
Neg logit contributions
yles-0.017
outing-0.016
outed-0.015
ries-0.015
eling-0.014
Token.
Token ID13
Feature activation+1.90e-03

Pos logit contributions
age+0.076
est+0.063
+0.055
 ok+0.050
ze+0.047
Neg logit contributions
yles-0.106
outing-0.099
outed-0.095
ries-0.094
ateful-0.094
Token They
Token ID1119
Feature activation-5.65e-03

Pos logit contributions
yles+0.004
outing+0.004
eling+0.004
ries+0.004
ateful+0.003
Neg logit contributions
age-0.003
est-0.002
-0.002
 ok-0.002
 middle-0.002
Token found
Token ID1043
Feature activation-4.44e-02

Pos logit contributions
age+0.009
+0.009
 even+0.007
est+0.007
 middle+0.007
Neg logit contributions
yles-0.011
ries-0.009
outing-0.009
ateful-0.009
irs-0.009
Token a
Token ID257
Feature activation-9.12e-03

Pos logit contributions
age+0.072
est+0.060
+0.052
 ok+0.049
ze+0.046
Neg logit contributions
yles-0.089
outing-0.083
ries-0.079
outed-0.079
ateful-0.079
Token big
Token ID1263
Feature activation-2.04e-02

Pos logit contributions
age+0.017
est+0.015
+0.013
 ok+0.013
ze+0.012
Neg logit contributions
yles-0.015
outing-0.014
nam-0.013
outed-0.013
 spill-0.013
Token bag
Token ID6131
Feature activation-1.94e-02

Pos logit contributions
age+0.044
est+0.035
 ok+0.032
+0.032
ze+0.031
Neg logit contributions
 spill-0.027
ries-0.027
yles-0.026
outing-0.026
 brushes-0.026
Token of
Token ID286
Feature activation+2.24e-02

Pos logit contributions
age+0.033
est+0.029
 ok+0.024
+0.024
ze+0.023
Neg logit contributions
outing-0.034
yles-0.034
outed-0.032
ries-0.031
ateful-0.030
Token flour
Token ID10601
Feature activation-5.32e-02

Pos logit contributions
yles+0.037
outing+0.034
outed+0.032
ateful+0.032
ries+0.031
Neg logit contributions
age-0.044
est-0.039
-0.034
 ok-0.033
ze-0.031
Token and
Token ID290
Feature activation+1.82e-04

Pos logit contributions
age+0.070
est+0.056
+0.047
 ok+0.043
ze+0.040
Neg logit contributions
yles-0.122
outing-0.115
ries-0.110
outed-0.110
ateful-0.109
TokenOne
Token ID3198
Feature activation-2.28e-02

Pos logit contributions
age+0.015
est+0.013
+0.011
 ok+0.010
ze+0.009
Neg logit contributions
yles-0.024
outing-0.022
ries-0.022
outed-0.022
ateful-0.022
Token day
Token ID1110
Feature activation-1.20e-02

Pos logit contributions
age+0.029
est+0.023
+0.019
 ok+0.017
ze+0.016
Neg logit contributions
yles-0.054
outing-0.051
ries-0.049
outed-0.049
ateful-0.048
Token,
Token ID11
Feature activation-9.59e-03

Pos logit contributions
age+0.010
est+0.008
+0.006
 ok+0.004
 best+0.004
Neg logit contributions
yles-0.033
outing-0.031
outed-0.030
ateful-0.030
ries-0.030
Token Sara
Token ID24799
Feature activation-1.60e-02

Pos logit contributions
est+0.017
 best+0.016
+0.016
age+0.016
 ok+0.015
Neg logit contributions
yles-0.014
outing-0.013
eling-0.013
ateful-0.012
irs-0.012
Token finds
Token ID7228
Feature activation-2.50e-02

Pos logit contributions
age+0.030
est+0.026
 ok+0.024
ench+0.022
ze+0.021
Neg logit contributions
yles-0.026
outed-0.023
ila-0.023
ateful-0.023
outing-0.023
Token a
Token ID257
Feature activation-1.19e-02

Pos logit contributions
age+0.038
est+0.031
+0.027
 ok+0.025
ze+0.024
Neg logit contributions
yles-0.053
outing-0.050
outed-0.047
ries-0.047
ateful-0.047
Token big
Token ID1263
Feature activation-2.27e-02

Pos logit contributions
age+0.023
est+0.020
+0.017
 ok+0.017
ze+0.016
Neg logit contributions
yles-0.019
outing-0.018
nam-0.017
outed-0.017
ateful-0.017
Token bottle
Token ID9294
Feature activation-1.44e-02

Pos logit contributions
age+0.046
est+0.037
 ok+0.036
+0.035
tted+0.034
Neg logit contributions
yles-0.031
 passports-0.030
ries-0.030
nam-0.029
 spill-0.029
Token of
Token ID286
Feature activation+2.07e-02

Pos logit contributions
age+0.026
est+0.024
 ok+0.023
ze+0.020
 advantage+0.020
Neg logit contributions
outing-0.022
outed-0.020
yles-0.020
ila-0.019
ries-0.019
Token oil
Token ID3056
Feature activation-9.97e-03

Pos logit contributions
yles+0.033
outing+0.030
ries+0.029
outed+0.028
ateful+0.028
Neg logit contributions
age-0.042
est-0.036
-0.032
 ok-0.031
ze-0.030
Token in
Token ID287
Feature activation-1.57e-02

Pos logit contributions
age+0.015
est+0.013
 ok+0.012
+0.011
ench+0.010
Neg logit contributions
yles-0.019
outing-0.019
ries-0.018
outed-0.018
ateful-0.017
Token a
Token ID257
Feature activation-8.71e-03

Pos logit contributions
age+0.087
est+0.075
+0.067
 ok+0.064
ze+0.062
Neg logit contributions
yles-0.064
outing-0.057
ries-0.055
outed-0.054
ateful-0.053
Token fork
Token ID15563
Feature activation-1.09e-02

Pos logit contributions
age+0.020
est+0.017
+0.015
nob+0.014
tted+0.014
Neg logit contributions
yles-0.010
outing-0.010
nam-0.009
 spill-0.009
 frowned-0.009
Token!
Token ID0
Feature activation-9.17e-03

Pos logit contributions
age+0.018
est+0.015
 ok+0.012
ench+0.012
+0.012
Neg logit contributions
yles-0.020
outing-0.020
ries-0.018
 spill-0.018
outed-0.017
Token From
Token ID3574
Feature activation+6.62e-03

Pos logit contributions
age+0.017
est+0.015
ze+0.013
 ok+0.013
+0.012
Neg logit contributions
yles-0.015
outing-0.014
outed-0.014
ries-0.014
ateful-0.013
Token that
Token ID326
Feature activation+1.06e-02

Pos logit contributions
yles+0.012
outing+0.012
outed+0.011
ateful+0.011
ries+0.011
Neg logit contributions
age-0.011
est-0.010
-0.009
 ok-0.008
ze-0.008
Token day
Token ID1110
Feature activation-5.79e-03

Pos logit contributions
yles+0.014
 they+0.014
outing+0.013
nam+0.013
 frowned+0.013
Neg logit contributions
age-0.022
est-0.016
ze-0.016
tted-0.016
ench-0.016
Token Bob
Token ID5811
Feature activation+8.49e-03

Pos logit contributions
age+0.009
est+0.008
ze+0.006
ench+0.006
nob+0.006
Neg logit contributions
yles-0.011
outing-0.010
outed-0.010
ries-0.010
nam-0.010
Token knew
Token ID2993
Feature activation+4.47e-03

Pos logit contributions
yles+0.013
outing+0.012
outed+0.012
ries+0.012
eling+0.012
Neg logit contributions
age-0.016
est-0.015
 ok-0.013
-0.012
 biggest-0.012
Token what
Token ID644
Feature activation+1.40e-02

Pos logit contributions
yles+0.008
outing+0.007
outed+0.007
ateful+0.006
ries+0.006
Neg logit contributions
age-0.009
est-0.008
-0.007
 ok-0.007
 best-0.006
Token a
Token ID257
Feature activation-8.74e-03

Pos logit contributions
yles+0.022
outing+0.020
ries+0.019
outed+0.019
ateful+0.019
Neg logit contributions
age-0.028
est-0.025
-0.022
 ok-0.021
ze-0.020
Token fork
Token ID15563
Feature activation-1.05e-02

Pos logit contributions
age+0.024
est+0.020
tted+0.018
house+0.018
mates+0.018
Neg logit contributions
yles-0.007
outing-0.006
 spill-0.006
eling-0.005
 frowned-0.005
Token Mia
Token ID32189
Feature activation+1.92e-02

Pos logit contributions
yles+0.048
outing+0.044
ries+0.040
nam+0.040
ateful+0.039
Neg logit contributions
age-0.064
est-0.059
-0.057
 ok-0.051
 middle-0.050
Token asks
Token ID7893
Feature activation+3.07e-02

Pos logit contributions
yles+0.016
outing+0.013
outed+0.011
ries+0.011
ateful+0.011
Neg logit contributions
age-0.054
est-0.049
-0.045
 ok-0.044
ze-0.043
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
yles+0.058
outing+0.054
ries+0.052
outed+0.051
ateful+0.051
Neg logit contributions
age-0.054
est-0.045
-0.039
 ok-0.037
ze-0.035
Token She
Token ID1375
Feature activation-1.28e-02

Pos logit contributions
yles+0.023
outing+0.022
eling+0.021
ateful+0.021
ries+0.021
Neg logit contributions
age-0.013
est-0.011
-0.010
 ok-0.009
 right-0.008
Token takes
Token ID2753
Feature activation+1.59e-03

Pos logit contributions
age+0.026
est+0.024
+0.022
 ok+0.021
ze+0.020
Neg logit contributions
yles-0.019
outing-0.017
ateful-0.016
nam-0.016
ries-0.016
Token the
Token ID262
Feature activation-9.71e-03

Pos logit contributions
yles+0.003
outing+0.003
ries+0.003
outed+0.003
ateful+0.003
Neg logit contributions
age-0.003
est-0.002
-0.002
 ok-0.002
ze-0.002
Token shovel
Token ID33677
Feature activation+1.62e-02

Pos logit contributions
age+0.020
est+0.017
+0.015
 ok+0.014
ze+0.014
Neg logit contributions
yles-0.016
outing-0.015
outed-0.014
ries-0.014
ateful-0.013
Token from
Token ID422
Feature activation-3.28e-04

Pos logit contributions
yles+0.037
outing+0.034
eling+0.033
ateful+0.032
outed+0.032
Neg logit contributions
age-0.022
est-0.018
-0.016
 ok-0.014
 best-0.012
Token Ben
Token ID3932
Feature activation+2.85e-02

Pos logit contributions
age+0.001
est+0.001
 right+0.000
+0.000
 back+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.000
ateful-0.000
nam-0.000
Token and
Token ID290
Feature activation+1.06e-03

Pos logit contributions
yles+0.053
outing+0.051
ries+0.049
nam+0.047
outed+0.047
Neg logit contributions
age-0.045
est-0.039
 ok-0.032
 biggest-0.029
ze-0.029
Token fills
Token ID23816
Feature activation-5.54e-02

Pos logit contributions
outing+0.002
yles+0.002
ateful+0.002
outed+0.002
nam+0.001
Neg logit contributions
-0.002
est-0.002
age-0.002
 right-0.002
 back-0.001
Token
Token ID198
Feature activation-7.55e-03

Pos logit contributions
yles+0.009
outing+0.008
outed+0.008
ries+0.008
ateful+0.008
Neg logit contributions
age-0.009
est-0.008
-0.007
 ok-0.007
ze-0.007
Token
Token ID198
Feature activation-8.92e-03

Pos logit contributions
age+0.012
est+0.011
 ok+0.009
+0.008
 biggest+0.008
Neg logit contributions
yles-0.015
outing-0.014
outed-0.013
ateful-0.013
ries-0.013
TokenL
Token ID43
Feature activation+4.58e-02

Pos logit contributions
age+0.018
est+0.017
 ok+0.014
 biggest+0.013
 best+0.013
Neg logit contributions
yles-0.013
outing-0.013
outed-0.012
ateful-0.012
nam-0.011
Tokenily
Token ID813
Feature activation+2.19e-02

Pos logit contributions
yles+0.092
outing+0.087
outed+0.084
ries+0.083
ateful+0.083
Neg logit contributions
age-0.073
est-0.060
-0.052
 ok-0.049
ze-0.047
Token's
Token ID338
Feature activation+1.38e-02

Pos logit contributions
outed+0.024
yles+0.024
 frowned+0.023
outing+0.022
eling+0.021
Neg logit contributions
age-0.049
est-0.044
 ok-0.040
 biggest-0.039
 advantage-0.038
Token mom
Token ID1995
Feature activation-4.70e-03

Pos logit contributions
yles+0.020
outing+0.019
outed+0.019
ateful+0.018
nam+0.017
Neg logit contributions
age-0.029
est-0.025
-0.022
sy-0.021
 ok-0.021
Tokenmy
Token ID1820
Feature activation-7.80e-03

Pos logit contributions
age+0.007
est+0.006
+0.005
 ok+0.005
ze+0.004
Neg logit contributions
yles-0.010
outing-0.009
outed-0.009
ries-0.009
ateful-0.009
Token was
Token ID373
Feature activation+3.70e-03

Pos logit contributions
age+0.019
est+0.017
+0.015
 ok+0.015
ze+0.014
Neg logit contributions
yles-0.009
outing-0.008
outed-0.008
ries-0.008
ateful-0.007
Token so
Token ID523
Feature activation+1.37e-02

Pos logit contributions
yles+0.007
outing+0.007
outed+0.007
ateful+0.007
nam+0.007
Neg logit contributions
age-0.006
est-0.005
-0.004
nob-0.004
ze-0.004
Token touched
Token ID12615
Feature activation-1.15e-02

Pos logit contributions
yles+0.032
ries+0.030
outing+0.028
eling+0.027
irs+0.027
Neg logit contributions
age-0.018
-0.014
est-0.014
 ok-0.013
 best-0.012
Token by
Token ID416
Feature activation-1.26e-03

Pos logit contributions
age+0.025
est+0.022
+0.020
 ok+0.019
ze+0.019
Neg logit contributions
yles-0.016
outing-0.015
ries-0.014
outed-0.014
ateful-0.014
Token put
Token ID1234
Feature activation-1.45e-02

Pos logit contributions
yles+0.007
outing+0.007
ateful+0.006
ries+0.006
outed+0.006
Neg logit contributions
age-0.008
est-0.007
-0.006
ze-0.006
 ok-0.006
Token on
Token ID319
Feature activation-8.67e-03

Pos logit contributions
age+0.032
est+0.029
+0.026
 ok+0.025
ze+0.024
Neg logit contributions
yles-0.020
outing-0.018
outed-0.017
ateful-0.017
ries-0.017
Token her
Token ID607
Feature activation+1.21e-03

Pos logit contributions
age+0.020
est+0.018
+0.016
 ok+0.016
ze+0.015
Neg logit contributions
yles-0.011
outing-0.010
outed-0.010
ateful-0.010
ries-0.009
Token p
Token ID279
Feature activation+3.08e-02

Pos logit contributions
yles+0.002
nam+0.002
ries+0.002
outing+0.002
outed+0.002
Neg logit contributions
age-0.002
est-0.002
-0.002
 ok-0.002
ench-0.002
Tokenaj
Token ID1228
Feature activation-1.06e-02

Pos logit contributions
yles+0.054
ateful+0.048
nam+0.047
eling+0.047
outing+0.046
Neg logit contributions
age-0.060
est-0.050
-0.041
ze-0.039
sy-0.039
Tokenamas
Token ID17485
Feature activation-8.15e-02

Pos logit contributions
age+0.012
est+0.010
+0.008
 ok+0.008
 biggest+0.006
Neg logit contributions
yles-0.025
outing-0.024
ries-0.023
outed-0.023
ateful-0.022
Token.
Token ID13
Feature activation-1.12e-03

Pos logit contributions
age+0.136
est+0.120
+0.100
 ok+0.098
ze+0.091
Neg logit contributions
yles-0.148
outing-0.142
outed-0.131
nam-0.129
ateful-0.128
Token Mom
Token ID11254
Feature activation+1.69e-03

Pos logit contributions
age+0.002
est+0.002
+0.002
 ok+0.002
ze+0.002
Neg logit contributions
yles-0.002
outing-0.002
outed-0.002
ries-0.002
ateful-0.002
Tokenmy
Token ID1820
Feature activation-1.51e-02

Pos logit contributions
yles+0.003
outing+0.003
outed+0.003
ries+0.003
ateful+0.003
Neg logit contributions
age-0.003
est-0.003
-0.002
 ok-0.002
ze-0.002
Token read
Token ID1100
Feature activation+1.86e-02

Pos logit contributions
age+0.033
est+0.030
+0.026
 ok+0.026
ze+0.025
Neg logit contributions
yles-0.021
outing-0.019
outed-0.018
ries-0.018
ateful-0.017
Token her
Token ID607
Feature activation+5.91e-04

Pos logit contributions
yles+0.025
outing+0.023
outed+0.021
ateful+0.021
ries+0.021
Neg logit contributions
age-0.042
est-0.038
-0.034
 ok-0.033
ze-0.032
Token share
Token ID2648
Feature activation-2.16e-02

Pos logit contributions
yles+0.033
outing+0.029
ries+0.028
eling+0.028
ateful+0.028
Neg logit contributions
age-0.040
est-0.037
 ok-0.031
-0.030
sy-0.029
Token your
Token ID534
Feature activation-1.02e-02

Pos logit contributions
age+0.040
est+0.034
+0.029
 ok+0.028
sy+0.027
Neg logit contributions
yles-0.039
outing-0.035
ries-0.035
ateful-0.034
nam-0.033
Token food
Token ID2057
Feature activation-3.07e-02

Pos logit contributions
age+0.022
est+0.018
+0.018
 ok+0.017
sy+0.017
Neg logit contributions
yles-0.014
ries-0.013
outing-0.012
eling-0.012
outed-0.011
Token and
Token ID290
Feature activation+6.11e-03

Pos logit contributions
age+0.054
est+0.043
+0.038
 ok+0.038
nob+0.037
Neg logit contributions
yles-0.053
outing-0.051
ries-0.050
ateful-0.049
nam-0.047
Token make
Token ID787
Feature activation-1.10e-02

Pos logit contributions
yles+0.011
outing+0.010
outed+0.010
ries+0.010
ateful+0.010
Neg logit contributions
age-0.011
est-0.009
-0.008
 ok-0.008
ze-0.008
Token us
Token ID514
Feature activation-7.37e-02

Pos logit contributions
age+0.023
est+0.020
+0.017
 ok+0.016
sy+0.016
Neg logit contributions
yles-0.018
outing-0.016
ries-0.016
ateful-0.015
eling-0.015
Token happy
Token ID3772
Feature activation+2.89e-02

Pos logit contributions
age+0.152
est+0.129
nob+0.116
+0.114
antly+0.112
Neg logit contributions
yles-0.102
nam-0.096
outing-0.094
ateful-0.093
ries-0.092
Token."
Token ID526
Feature activation+1.28e-02

Pos logit contributions
yles+0.057
ries+0.052
ateful+0.051
outing+0.048
ins+0.047
Neg logit contributions
age-0.050
sy-0.037
est-0.036
-0.036
tted-0.034
Token
Token ID198
Feature activation+1.11e-03

Pos logit contributions
yles+0.026
outing+0.024
outed+0.023
ateful+0.023
ries+0.023
Neg logit contributions
age-0.020
est-0.017
-0.014
 ok-0.014
ze-0.013
Token
Token ID198
Feature activation-3.21e-04

Pos logit contributions
yles+0.002
outing+0.002
ateful+0.002
outed+0.002
ries+0.002
Neg logit contributions
age-0.002
est-0.002
 ok-0.001
-0.001
ze-0.001
TokenThe
Token ID464
Feature activation-5.84e-03

Pos logit contributions
age+0.001
est+0.001
 ok+0.000
+0.000
ze+0.000
Neg logit contributions
yles-0.001
outing-0.001
ateful-0.000
outed-0.000
ila-0.000
Token.
Token ID13
Feature activation+9.93e-03

Pos logit contributions
yles+0.069
outing+0.065
ries+0.062
outed+0.061
ateful+0.061
Neg logit contributions
age-0.060
est-0.049
-0.042
 ok-0.040
ze-0.039
Token "
Token ID366
Feature activation+1.22e-02

Pos logit contributions
yles+0.022
outing+0.021
ries+0.020
outed+0.020
ateful+0.020
Neg logit contributions
age-0.014
est-0.011
-0.009
 ok-0.009
ze-0.008
TokenHe
Token ID1544
Feature activation+6.89e-03

Pos logit contributions
yles+0.023
outing+0.022
ries+0.021
outed+0.021
eling+0.020
Neg logit contributions
age-0.021
-0.017
est-0.017
 ok-0.014
ze-0.014
Token is
Token ID318
Feature activation+2.47e-02

Pos logit contributions
yles+0.013
outing+0.012
ries+0.012
outed+0.012
eling+0.011
Neg logit contributions
age-0.012
est-0.010
-0.008
 ok-0.008
ze-0.008
Token making
Token ID1642
Feature activation-3.45e-02

Pos logit contributions
yles+0.043
outing+0.040
outed+0.038
nam+0.038
ries+0.037
Neg logit contributions
age-0.046
est-0.040
-0.034
 ok-0.031
ze-0.031
Token us
Token ID514
Feature activation-7.63e-02

Pos logit contributions
age+0.068
est+0.058
sy+0.048
ench+0.048
nob+0.047
Neg logit contributions
yles-0.054
ries-0.049
outing-0.049
eling-0.047
ateful-0.047
Token scared
Token ID12008
Feature activation+7.12e-03

Pos logit contributions
age+0.137
est+0.118
+0.097
 ok+0.096
nob+0.096
Neg logit contributions
yles-0.124
outing-0.120
ries-0.115
ateful-0.114
nam-0.114
Token."
Token ID526
Feature activation+1.47e-02

Pos logit contributions
yles+0.011
ries+0.011
outing+0.011
ateful+0.010
ila+0.010
Neg logit contributions
age-0.014
est-0.011
sy-0.010
ench-0.010
nob-0.010
Token
Token ID198
Feature activation-3.41e-04

Pos logit contributions
yles+0.027
outing+0.026
outed+0.025
ateful+0.024
ries+0.024
Neg logit contributions
age-0.026
est-0.022
-0.018
ze-0.018
 ok-0.017
Token
Token ID198
Feature activation-1.77e-03

Pos logit contributions
age+0.001
est+0.000
+0.000
 ok+0.000
ze+0.000
Neg logit contributions
yles-0.001
outing-0.001
outed-0.001
ateful-0.001
ries-0.001
TokenThe
Token ID464
Feature activation-9.63e-03

Pos logit contributions
age+0.003
est+0.003
 ok+0.002
+0.002
ze+0.002
Neg logit contributions
yles-0.003
outing-0.003
ateful-0.003
outed-0.003
ries-0.003
Token her
Token ID607
Feature activation+3.13e-03

Pos logit contributions
yles+0.034
outing+0.033
outed+0.031
ateful+0.030
ries+0.028
Neg logit contributions
age-0.029
-0.026
 back-0.025
 right-0.025
est-0.024
Token mom
Token ID1995
Feature activation-1.06e-02

Pos logit contributions
yles+0.004
ries+0.004
outing+0.004
outed+0.004
nam+0.004
Neg logit contributions
age-0.007
est-0.006
 ok-0.005
-0.005
tted-0.005
Token,
Token ID11
Feature activation-3.76e-03

Pos logit contributions
age+0.015
est+0.013
+0.010
 ok+0.010
ze+0.009
Neg logit contributions
yles-0.023
outing-0.022
ries-0.021
outed-0.021
ateful-0.020
Token who
Token ID508
Feature activation-6.19e-03

Pos logit contributions
age+0.008
est+0.007
+0.006
 ok+0.006
ze+0.006
Neg logit contributions
yles-0.006
outing-0.005
ateful-0.005
ries-0.005
outed-0.005
Token was
Token ID373
Feature activation+3.22e-03

Pos logit contributions
age+0.005
+0.005
est+0.004
 right+0.003
,+0.003
Neg logit contributions
yles-0.016
outing-0.016
ateful-0.015
nam-0.015
outed-0.015
Token sitting
Token ID5586
Feature activation-8.70e-02

Pos logit contributions
yles+0.006
outing+0.005
outed+0.005
ateful+0.005
ries+0.005
Neg logit contributions
age-0.006
est-0.005
-0.005
 ok-0.005
ze-0.004
Token on
Token ID319
Feature activation-4.87e-03

Pos logit contributions
age+0.126
est+0.103
+0.090
 ok+0.081
ze+0.076
Neg logit contributions
yles-0.187
outing-0.180
ries-0.173
outed-0.172
ateful-0.170
Token a
Token ID257
Feature activation-7.03e-03

Pos logit contributions
age+0.008
est+0.007
+0.006
ze+0.006
 right+0.006
Neg logit contributions
yles-0.010
outing-0.010
outed-0.009
ateful-0.009
eling-0.008
Token bench
Token ID7624
Feature activation+3.62e-02

Pos logit contributions
age+0.015
est+0.013
+0.012
 ok+0.011
ze+0.011
Neg logit contributions
yles-0.010
outing-0.009
outed-0.009
ries-0.009
ateful-0.009
Token.
Token ID13
Feature activation-2.60e-03

Pos logit contributions
yles+0.090
ateful+0.080
outing+0.080
ries+0.078
outed+0.078
Neg logit contributions
age-0.045
est-0.034
-0.029
 right-0.025
ze-0.024
Token She
Token ID1375
Feature activation-1.41e-02

Pos logit contributions
age+0.004
+0.003
est+0.003
 ok+0.003
 Just+0.003
Neg logit contributions
yles-0.006
eling-0.005
outing-0.005
ries-0.005
ateful-0.005
Token front
Token ID2166
Feature activation+4.78e-03

Pos logit contributions
age+0.014
est+0.013
+0.012
 right+0.011
 middle+0.011
Neg logit contributions
yles-0.020
outing-0.020
outed-0.019
eling-0.017
ours-0.017
Token of
Token ID286
Feature activation+2.29e-02

Pos logit contributions
yles+0.010
outing+0.009
outed+0.009
ries+0.009
ateful+0.009
Neg logit contributions
age-0.008
est-0.006
-0.006
 ok-0.005
ze-0.005
Token him
Token ID683
Feature activation-1.71e-02

Pos logit contributions
yles+0.043
outing+0.041
outed+0.039
eling+0.036
ateful+0.036
Neg logit contributions
age-0.036
est-0.033
 right-0.031
 back-0.030
 ok-0.030
Token.
Token ID13
Feature activation+1.26e-03

Pos logit contributions
age+0.024
est+0.020
+0.017
 ok+0.015
ze+0.015
Neg logit contributions
yles-0.038
outing-0.035
outed-0.034
ries-0.034
ateful-0.034
Token He
Token ID679
Feature activation-5.57e-03

Pos logit contributions
yles+0.003
outing+0.003
outed+0.002
ateful+0.002
ries+0.002
Neg logit contributions
age-0.002
est-0.002
-0.001
 ok-0.001
ze-0.001
Token tri
Token ID1333
Feature activation-6.96e-02

Pos logit contributions
age+0.010
+0.008
est+0.008
ze+0.007
 right+0.007
Neg logit contributions
yles-0.011
irs-0.010
ries-0.010
outing-0.009
ateful-0.009
Tokenpped
Token ID1496
Feature activation-5.74e-03

Pos logit contributions
age+0.147
est+0.135
+0.118
 ok+0.115
 biggest+0.113
Neg logit contributions
yles-0.101
outing-0.093
outed-0.088
ateful-0.085
ries-0.085
Token and
Token ID290
Feature activation-2.38e-03

Pos logit contributions
age+0.009
est+0.007
 ok+0.006
+0.006
ze+0.006
Neg logit contributions
yles-0.012
outing-0.011
ries-0.011
outed-0.010
ateful-0.010
Token fell
Token ID3214
Feature activation-3.71e-02

Pos logit contributions
age+0.004
+0.003
est+0.003
ze+0.003
 middle+0.002
Neg logit contributions
yles-0.005
outing-0.005
ries-0.004
ateful-0.004
 passports-0.004
Token.
Token ID13
Feature activation-1.78e-03

Pos logit contributions
age+0.058
est+0.049
+0.042
 ok+0.040
ze+0.038
Neg logit contributions
yles-0.073
outing-0.070
outed-0.067
ries-0.067
ateful-0.065
Token He
Token ID679
Feature activation-9.35e-03

Pos logit contributions
age+0.002
est+0.002
+0.002
 ok+0.002
ze+0.001
Neg logit contributions
yles-0.004
outing-0.004
ries-0.004
outed-0.004
ateful-0.004