TOP ACTIVATIONS
MAX = 0.156

made . The mer maid learnt that taking risks
was so thankful that the mer maid had forgiven him .
again . He said the mer maid and a dolphin were
. The more , the mer rier . Come to my
telling a story about a mer maid who lived in the
in the sea that the mer maid carefully chose . It
" I 'm a secret mer maid . Would you like
was happy and sailed away mer rily . <|endoftext|> Once there
sun . A mer maid that lived in the
bed . She dreamed of mer maid s and pirates ,
. It was the magical mer maid , who thanked the
yes . She followed the mer maid through the hidden door
" I am a gen ie ," the man said
sometimes pretend to be a mer maid .
, she saw a beautiful mer maid swimming around her .
Joe waved goodbye to the mer maid , and hopped back
passport belonged to a magical mer maid who had been visiting
man watched as she skipped mer rily away into the sunset
. He even saw a mer maid !
swimming around her . The mer maid smiled and said ,

MIN ACTIVATIONS
MIN = -0.182

rings , and neck l aces . " Wow
saw rings , neck l aces , brace lets and ear
These are beautiful neck l aces and brace lets . You
fish , some l ily pads and even a frog .
want to make neck l aces and brace lets with them
you tie my sho el aces for me ?"
he found two little m ittens lying in the snow .
seat . After a few attempts , the engine started and
some spark ly neck l aces and sil ky scar ves
together . After a few attempts , they finally got the
's tie your sho el aces together so they won 't
Its bright colors and l aces made it look very nice
brace lets and neck l aces with copper . They think
. There were neck l aces and rings with spark les
quickly tied her sho el aces and ran away from the
her mum 's shoe l aces together . One day ,
pped on her sho el aces and dropped her pencil .
like bright yellow neck l aces and flower crown s .
her to tie the l aces . She thought and thought
to your feet with l aces ." Her son nodded and

INTERVAL 0.072 - 0.156
CONTAINS 0.373%

are a good friend for whist ling ." They
We want to see the movie ." Mom and
" dog " and " star " and " cake ".
care of it . Happy birthday , sweet ie ." Mom
. John said , � � € � � Let â

INTERVAL -0.013 - 0.072
CONTAINS 71.549%

appeared near the island . Out stepped a tall and wise
The little girl was sad when it was time
Then , Tim saw a man with a club . He
To her surprise , the chest was not empty ! Inside
hug . She said " Thank you for being so fair

INTERVAL -0.097 - -0.013
CONTAINS 27.983%

chase the butterflies . " Look , Ben ,
flew away . Lily felt very sad and scared because she
! <|endoftext|> Once upon a time there was a little girl
the floor ! Tim my 's mom was not happy ,
believe his eyes . The man smiled and

INTERVAL -0.182 - -0.097
CONTAINS 0.096%

and put it in her mouth . The flower
. M ittens went home feeling down .
Here are Lily 's m ittens . They are warm and
named Mitt ens . Mitt ens liked to play with toys
join them , but she forgot something . She forgot to
Token made
Token ID925
Feature activation+2.00e-02

Pos logit contributions
 boy+0.027
 girl+0.026
 Year+0.023
 extingu+0.023
 asleep+0.023
Neg logit contributions
vern-0.017
aches-0.017
earned-0.016
imes-0.015
fters-0.015
Token.
Token ID13
Feature activation+7.60e-03

Pos logit contributions
 boy+0.040
 girl+0.038
 extingu+0.037
 Year+0.036
ksh+0.034
Neg logit contributions
vern-0.028
aches-0.028
ons-0.026
gh-0.026
ag-0.025
Token
Token ID220
Feature activation-1.11e-02

Pos logit contributions
 boy+0.015
 girl+0.014
 extingu+0.013
 Year+0.013
 asleep+0.012
Neg logit contributions
vern-0.011
aches-0.011
earned-0.011
imes-0.011
ough-0.010
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
vern+0.019
aches+0.019
earned+0.018
imes+0.018
ending+0.017
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.016
 asleep-0.015
TokenThe
Token ID464
Feature activation+9.34e-03

Pos logit contributions
aches+0.032
vern+0.032
earned+0.031
iable+0.030
imes+0.030
Neg logit contributions
 boy-0.035
 girl-0.033
 Year-0.030
 asleep-0.028
 extingu-0.028
Token mer
Token ID4017
Feature activation+1.56e-01

Pos logit contributions
 extingu+0.019
ksh+0.018
ucks+0.018
 asleep+0.018
 Year+0.018
Neg logit contributions
aches-0.012
Days-0.011
vern-0.011
 exercise-0.010
isky-0.010
Tokenmaid
Token ID23151
Feature activation+4.63e-02

Pos logit contributions
 boy+0.155
 extingu+0.147
 Sn+0.143
 girl+0.132
 Year+0.124
Neg logit contributions
aches-0.353
ag-0.344
ending-0.342
gh-0.329
ying-0.328
Token learnt
Token ID26338
Feature activation-4.68e-02

Pos logit contributions
 boy+0.083
 girl+0.078
 extingu+0.077
 Year+0.076
ksh+0.073
Neg logit contributions
aches-0.075
vern-0.070
 hardly-0.068
ons-0.066
ending-0.066
Token that
Token ID326
Feature activation+5.70e-02

Pos logit contributions
vern+0.073
aches+0.073
earned+0.067
imes+0.067
fters+0.067
Neg logit contributions
 boy-0.088
 girl-0.084
 Year-0.076
 extingu-0.076
 asleep-0.074
Token taking
Token ID2263
Feature activation+1.92e-02

Pos logit contributions
 boy+0.118
 extingu+0.114
 Year+0.112
 girl+0.112
ksh+0.112
Neg logit contributions
vern-0.073
aches-0.072
 achieve-0.066
ending-0.065
earned-0.064
Token risks
Token ID7476
Feature activation-4.68e-02

Pos logit contributions
 boy+0.046
 girl+0.043
 extingu+0.042
 Year+0.042
ksh+0.041
Neg logit contributions
aches-0.020
vern-0.020
earned-0.018
ag-0.018
ough-0.017
Token was
Token ID373
Feature activation+1.30e-02

Pos logit contributions
 boy+0.029
 girl+0.027
 Year+0.027
 extingu+0.027
ksh+0.026
Neg logit contributions
aches-0.021
vern-0.021
 accomplished-0.019
 hardly-0.019
earned-0.019
Token so
Token ID523
Feature activation-2.17e-02

Pos logit contributions
 boy+0.026
 girl+0.025
 extingu+0.024
 Year+0.024
ksh+0.022
Neg logit contributions
vern-0.019
aches-0.019
gh-0.017
earned-0.017
iable-0.017
Token thankful
Token ID25535
Feature activation+4.04e-02

Pos logit contributions
vern+0.034
aches+0.033
ending+0.030
earned+0.030
 accomplished+0.029
Neg logit contributions
 boy-0.041
 girl-0.039
 Year-0.038
 extingu-0.038
ksh-0.035
Token that
Token ID326
Feature activation+5.35e-02

Pos logit contributions
 boy+0.084
 girl+0.080
 Year+0.077
 extingu+0.075
ksh+0.072
Neg logit contributions
vern-0.055
aches-0.055
earned-0.049
gh-0.048
ending-0.048
Token the
Token ID262
Feature activation+1.52e-03

Pos logit contributions
 boy+0.126
 girl+0.122
 Year+0.121
 extingu+0.120
ksh+0.116
Neg logit contributions
aches-0.056
vern-0.053
gh-0.046
earned-0.046
imes-0.045
Token mer
Token ID4017
Feature activation+1.52e-01

Pos logit contributions
ksh+0.003
 extingu+0.003
ucks+0.002
 Year+0.002
ASH+0.002
Neg logit contributions
vern-0.002
aches-0.002
gh-0.002
 important-0.002
 extraordinary-0.002
Tokenmaid
Token ID23151
Feature activation+3.81e-02

Pos logit contributions
 extingu+0.166
 boy+0.164
 Sn+0.163
ASH+0.153
 girl+0.152
Neg logit contributions
aches-0.320
ag-0.315
gh-0.303
vern-0.299
 hardly-0.295
Token had
Token ID550
Feature activation-1.40e-02

Pos logit contributions
 boy+0.072
 girl+0.069
 Year+0.066
 extingu+0.066
ksh+0.062
Neg logit contributions
aches-0.057
vern-0.056
earned-0.052
ending-0.051
ons-0.050
Token forgiven
Token ID32350
Feature activation+1.75e-02

Pos logit contributions
aches+0.022
vern+0.022
imes+0.021
fters+0.021
affles+0.021
Neg logit contributions
 boy-0.026
 girl-0.025
 asleep-0.022
 Year-0.021
 extingu-0.021
Token him
Token ID683
Feature activation+4.73e-03

Pos logit contributions
 boy+0.039
 girl+0.037
 Year+0.036
 extingu+0.035
 asleep+0.033
Neg logit contributions
aches-0.021
vern-0.021
gh-0.019
earned-0.019
imes-0.018
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
 boy+0.009
 girl+0.009
 Year+0.008
 extingu+0.008
ksh+0.007
Neg logit contributions
vern-0.007
aches-0.007
earned-0.007
gh-0.007
 achieve-0.007
Token again
Token ID757
Feature activation+4.06e-02

Pos logit contributions
 boy+0.124
 girl+0.119
 Year+0.113
 extingu+0.112
 asleep+0.107
Neg logit contributions
vern-0.067
aches-0.067
earned-0.060
gh-0.058
ending-0.058
Token.
Token ID13
Feature activation+9.53e-03

Pos logit contributions
 boy+0.079
 girl+0.075
 Year+0.073
 extingu+0.071
ksh+0.068
Neg logit contributions
vern-0.058
aches-0.058
earned-0.053
 achieve-0.053
gh-0.052
Token He
Token ID679
Feature activation+1.62e-02

Pos logit contributions
 boy+0.017
 girl+0.015
 Year+0.014
 extingu+0.014
 asleep+0.013
Neg logit contributions
aches-0.017
vern-0.017
fters-0.016
earned-0.016
iable-0.015
Token said
Token ID531
Feature activation+1.13e-02

Pos logit contributions
 extingu+0.032
 boy+0.031
 Year+0.031
 girl+0.031
ksh+0.030
Neg logit contributions
aches-0.021
 accomplished-0.020
 hardly-0.020
vern-0.019
 achieved-0.019
Token the
Token ID262
Feature activation+5.62e-03

Pos logit contributions
 boy+0.022
 girl+0.021
 extingu+0.020
 Year+0.020
ksh+0.019
Neg logit contributions
vern-0.016
aches-0.016
gh-0.015
earned-0.015
ending-0.015
Token mer
Token ID4017
Feature activation+1.52e-01

Pos logit contributions
 extingu+0.012
ksh+0.011
ucks+0.011
cy+0.011
 boy+0.011
Neg logit contributions
vern-0.007
aches-0.007
gh-0.006
 achieve-0.006
 accomplished-0.006
Tokenmaid
Token ID23151
Feature activation+4.22e-02

Pos logit contributions
 boy+0.160
 Sn+0.142
 extingu+0.141
 girl+0.137
 Year+0.124
Neg logit contributions
aches-0.339
gh-0.334
ag-0.334
vern-0.320
ending-0.316
Token and
Token ID290
Feature activation+4.43e-03

Pos logit contributions
 boy+0.075
 girl+0.071
 Year+0.066
 extingu+0.065
 asleep+0.062
Neg logit contributions
vern-0.070
aches-0.070
earned-0.065
imes-0.064
ending-0.064
Token a
Token ID257
Feature activation+2.81e-02

Pos logit contributions
ksh+0.009
 Year+0.009
 extingu+0.009
 boy+0.008
cy+0.008
Neg logit contributions
aches-0.006
ons-0.005
 accomplished-0.005
 hardly-0.005
 achieved-0.005
Token dolphin
Token ID44136
Feature activation+4.40e-02

Pos logit contributions
 Year+0.052
ksh+0.051
ucks+0.050
 extingu+0.049
ASH+0.049
Neg logit contributions
vern-0.042
aches-0.037
 achieve-0.037
 accomplished-0.035
 capable-0.035
Token were
Token ID547
Feature activation+2.02e-02

Pos logit contributions
 boy+0.081
 Year+0.076
 girl+0.076
 extingu+0.073
ksh+0.072
Neg logit contributions
vern-0.066
aches-0.065
ending-0.060
ag-0.060
gh-0.059
Token.
Token ID13
Feature activation-1.14e-03

Pos logit contributions
 boy+0.005
 girl+0.004
 extingu+0.004
 Year+0.004
 asleep+0.004
Neg logit contributions
vern-0.003
aches-0.003
gh-0.003
iable-0.003
earned-0.003
Token The
Token ID383
Feature activation-1.50e-02

Pos logit contributions
ough+0.002
vern+0.002
earned+0.002
imes+0.002
ending+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 extingu-0.002
 asleep-0.002
 Year-0.002
Token more
Token ID517
Feature activation-2.72e-02

Pos logit contributions
aches+0.025
vern+0.024
 exercise+0.022
fters+0.022
imes+0.022
Neg logit contributions
ksh-0.022
ucks-0.022
 extingu-0.021
 asleep-0.020
cy-0.019
Token,
Token ID11
Feature activation-7.19e-03

Pos logit contributions
aches+0.045
vern+0.040
ons+0.040
ade+0.038
imes+0.038
Neg logit contributions
 extingu-0.048
ksh-0.048
 boy-0.046
 Year-0.044
 asleep-0.043
Token the
Token ID262
Feature activation-5.90e-03

Pos logit contributions
aches+0.010
fters+0.009
ough+0.009
imes+0.009
 achieve+0.009
Neg logit contributions
 extingu-0.013
 Year-0.013
ksh-0.013
 boy-0.013
ucks-0.012
Token mer
Token ID4017
Feature activation+1.52e-01

Pos logit contributions
aches+0.010
vern+0.009
 capable+0.008
 exercise+0.008
fters+0.008
Neg logit contributions
ucks-0.010
ksh-0.010
 extingu-0.010
 Year-0.009
eddy-0.008
Tokenrier
Token ID5277
Feature activation+7.84e-02

Pos logit contributions
 Sn+0.170
 extingu+0.168
 boy+0.166
 girl+0.144
 Smith+0.142
Neg logit contributions
aches-0.331
ag-0.316
gh-0.293
inations-0.293
ying-0.292
Token.
Token ID13
Feature activation+6.32e-03

Pos logit contributions
ksh+0.139
 Year+0.137
 boy+0.135
 extingu+0.130
 girl+0.128
Neg logit contributions
aches-0.124
vern-0.110
earned-0.106
gh-0.103
ons-0.102
Token Come
Token ID7911
Feature activation+4.62e-02

Pos logit contributions
 boy+0.012
 girl+0.012
 extingu+0.010
 Year+0.010
 asleep+0.010
Neg logit contributions
vern-0.009
ough-0.009
imes-0.009
 achieve-0.008
earned-0.008
Token to
Token ID284
Feature activation-9.52e-03

Pos logit contributions
 boy+0.084
 girl+0.080
 extingu+0.076
 Year+0.075
ksh+0.075
Neg logit contributions
aches-0.066
vern-0.065
 achieve-0.064
ough-0.064
gh-0.062
Token my
Token ID616
Feature activation-2.26e-03

Pos logit contributions
aches+0.014
vern+0.014
ag+0.013
 achieve+0.013
iable+0.012
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.016
ksh-0.016
Token telling
Token ID5149
Feature activation-1.30e-03

Pos logit contributions
 boy+0.005
 girl+0.004
 extingu+0.004
 Year+0.004
ksh+0.004
Neg logit contributions
aches-0.004
vern-0.004
 supposed-0.003
 accomplished-0.003
gh-0.003
Token a
Token ID257
Feature activation+1.74e-02

Pos logit contributions
vern+0.002
aches+0.002
earned+0.002
imes+0.002
ending+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 Year-0.002
 extingu-0.002
 asleep-0.002
Token story
Token ID1621
Feature activation+5.33e-02

Pos logit contributions
 boy+0.034
 girl+0.032
 extingu+0.030
 Year+0.030
 asleep+0.029
Neg logit contributions
vern-0.026
aches-0.026
earned-0.023
gh-0.023
ending-0.023
Token about
Token ID546
Feature activation+3.16e-02

Pos logit contributions
 boy+0.122
 girl+0.117
 extingu+0.108
 Year+0.106
 asleep+0.105
Neg logit contributions
aches-0.063
vern-0.062
earned-0.056
fters-0.055
imes-0.055
Token a
Token ID257
Feature activation+1.92e-02

Pos logit contributions
 boy+0.057
 girl+0.054
 extingu+0.050
 Year+0.050
ksh+0.048
Neg logit contributions
aches-0.052
vern-0.051
earned-0.047
imes-0.047
ons-0.046
Token mer
Token ID4017
Feature activation+1.51e-01

Pos logit contributions
 extingu+0.037
ucks+0.036
ksh+0.036
 boy+0.035
 Year+0.034
Neg logit contributions
vern-0.026
gh-0.024
aches-0.023
 achieve-0.023
 capable-0.022
Tokenmaid
Token ID23151
Feature activation+3.46e-02

Pos logit contributions
 boy+0.157
 Sn+0.152
 extingu+0.151
 girl+0.139
 Year+0.126
Neg logit contributions
ag-0.329
aches-0.327
gh-0.319
 hardly-0.308
vern-0.302
Token who
Token ID508
Feature activation+1.87e-02

Pos logit contributions
 boy+0.062
 girl+0.058
 Year+0.055
 extingu+0.054
ASH+0.051
Neg logit contributions
aches-0.055
vern-0.054
imes-0.051
ending-0.051
earned-0.051
Token lived
Token ID5615
Feature activation+1.06e-02

Pos logit contributions
 boy+0.036
 girl+0.034
 extingu+0.033
 Year+0.033
ksh+0.032
Neg logit contributions
aches-0.028
vern-0.027
ons-0.025
 accomplished-0.025
ending-0.025
Token in
Token ID287
Feature activation+1.59e-02

Pos logit contributions
 boy+0.018
 extingu+0.018
 girl+0.017
 Year+0.017
ksh+0.016
Neg logit contributions
vern-0.018
aches-0.018
gh-0.017
 accomplished-0.017
ag-0.017
Token the
Token ID262
Feature activation-1.09e-03

Pos logit contributions
 boy+0.032
 girl+0.031
ksh+0.031
 Year+0.029
 extingu+0.029
Neg logit contributions
vern-0.021
aches-0.019
 achieve-0.019
ons-0.019
 accomplished-0.019
Token in
Token ID287
Feature activation+1.91e-02

Pos logit contributions
ksh+0.002
 boy+0.002
ucks+0.002
 girl+0.002
 cash+0.002
Neg logit contributions
 accomplished-0.001
 achieved-0.001
aches-0.001
 achieve-0.001
ag-0.001
Token the
Token ID262
Feature activation+9.30e-04

Pos logit contributions
 boy+0.042
ksh+0.041
 girl+0.040
 Claus+0.037
 extingu+0.037
Neg logit contributions
aches-0.021
vern-0.019
 accomplished-0.019
ons-0.018
 achieved-0.018
Token sea
Token ID5417
Feature activation+3.29e-02

Pos logit contributions
 extingu+0.002
 boy+0.002
ksh+0.002
ucks+0.001
 girl+0.001
Neg logit contributions
aches-0.001
 accomplished-0.001
 achieve-0.001
vern-0.001
earned-0.001
Token that
Token ID326
Feature activation+5.30e-02

Pos logit contributions
 boy+0.065
 girl+0.062
 extingu+0.061
 Year+0.061
ksh+0.059
Neg logit contributions
aches-0.045
vern-0.044
 achieve-0.041
 accomplished-0.040
ough-0.040
Token the
Token ID262
Feature activation+1.80e-03

Pos logit contributions
 boy+0.095
 girl+0.092
 extingu+0.091
 Year+0.091
ksh+0.086
Neg logit contributions
aches-0.082
vern-0.076
 accomplished-0.075
gh-0.073
ons-0.072
Token mer
Token ID4017
Feature activation+1.51e-01

Pos logit contributions
 extingu+0.004
ksh+0.003
ucks+0.003
 Sn+0.003
 asleep+0.003
Neg logit contributions
aches-0.003
 accomplished-0.002
 extraordinary-0.002
 achieve-0.002
ough-0.002
Tokenmaid
Token ID23151
Feature activation+3.96e-02

Pos logit contributions
 extingu+0.167
 boy+0.166
 Sn+0.163
 girl+0.149
 cash+0.128
Neg logit contributions
aches-0.342
ag-0.324
 hardly-0.315
ade-0.314
gh-0.305
Token carefully
Token ID7773
Feature activation-1.32e-03

Pos logit contributions
 boy+0.079
 girl+0.075
 extingu+0.072
 Year+0.071
ksh+0.067
Neg logit contributions
aches-0.057
vern-0.055
ending-0.051
earned-0.050
ons-0.050
Token chose
Token ID7690
Feature activation-1.80e-02

Pos logit contributions
aches+0.002
vern+0.002
earned+0.002
gh+0.002
ag+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 Year-0.002
 extingu-0.002
ksh-0.002
Token.
Token ID13
Feature activation+8.52e-03

Pos logit contributions
aches+0.027
vern+0.026
earned+0.024
imes+0.023
gh+0.023
Neg logit contributions
 boy-0.036
 girl-0.034
 Year-0.032
 extingu-0.031
ksh-0.030
Token It
Token ID632
Feature activation-7.82e-04

Pos logit contributions
 boy+0.017
 girl+0.017
 extingu+0.016
 Year+0.016
maid+0.015
Neg logit contributions
imes-0.011
vern-0.011
ough-0.010
earned-0.010
aches-0.010
Token "
Token ID366
Feature activation+2.87e-02

Pos logit contributions
 boy+0.013
 extingu+0.013
 Year+0.013
 girl+0.013
ksh+0.013
Neg logit contributions
vern-0.009
 achieve-0.009
 hardly-0.008
 accomplished-0.008
iable-0.008
TokenI
Token ID40
Feature activation+1.37e-03

Pos logit contributions
 boy+0.053
 girl+0.049
 extingu+0.048
 tent+0.048
 Year+0.047
Neg logit contributions
ending-0.043
earned-0.043
vern-0.041
aches-0.041
 achieve-0.041
Token'm
Token ID1101
Feature activation+3.27e-02

Pos logit contributions
 boy+0.003
 girl+0.003
 Year+0.003
ksh+0.003
 extingu+0.003
Neg logit contributions
vern-0.001
aches-0.001
 expect-0.001
 hardly-0.001
earned-0.001
Token a
Token ID257
Feature activation+1.78e-02

Pos logit contributions
 boy+0.065
 girl+0.061
ksh+0.058
 Year+0.056
cy+0.056
Neg logit contributions
 supposed-0.048
vern-0.048
aches-0.046
 hardly-0.045
imes-0.044
Token secret
Token ID3200
Feature activation-7.01e-03

Pos logit contributions
ucks+0.038
ipt+0.033
ksh+0.033
ASH+0.032
ays+0.032
Neg logit contributions
vern-0.023
 daring-0.023
 else-0.021
 capable-0.021
gh-0.021
Token mer
Token ID4017
Feature activation+1.50e-01

Pos logit contributions
vern+0.011
aches+0.010
 supposed+0.010
ade+0.010
 else+0.010
Neg logit contributions
ksh-0.012
ASH-0.011
ucks-0.011
 Year-0.010
 boy-0.010
Tokenmaid
Token ID23151
Feature activation+3.87e-02

Pos logit contributions
 boy+0.169
 Sn+0.164
 girl+0.158
 Year+0.149
 asleep+0.139
Neg logit contributions
gh-0.305
ag-0.303
aches-0.294
vern-0.294
ovable-0.284
Token.
Token ID13
Feature activation+7.30e-03

Pos logit contributions
 boy+0.072
 Year+0.068
 extingu+0.067
 girl+0.066
ASH+0.065
Neg logit contributions
aches-0.055
vern-0.055
ending-0.053
imes-0.051
earned-0.051
Token Would
Token ID10928
Feature activation+1.49e-02

Pos logit contributions
 boy+0.014
 girl+0.013
 extingu+0.013
 Year+0.013
 asleep+0.012
Neg logit contributions
earned-0.010
ending-0.009
vern-0.009
ough-0.009
imes-0.009
Token you
Token ID345
Feature activation-1.25e-02

Pos logit contributions
 boy+0.031
 girl+0.029
 Year+0.027
 extingu+0.026
 asleep+0.026
Neg logit contributions
vern-0.021
aches-0.021
earned-0.019
imes-0.019
ending-0.018
Token like
Token ID588
Feature activation+1.75e-02

Pos logit contributions
vern+0.017
aches+0.017
earned+0.016
imes+0.015
ending+0.015
Neg logit contributions
 boy-0.026
 girl-0.025
 Year-0.023
 extingu-0.023
 asleep-0.022
Token was
Token ID373
Feature activation+1.83e-02

Pos logit contributions
 boy+0.074
 girl+0.073
 extingu+0.072
 Year+0.069
ksh+0.069
Neg logit contributions
aches-0.066
vern-0.063
 accomplished-0.059
 achieve-0.058
earned-0.058
Token happy
Token ID3772
Feature activation-1.13e-02

Pos logit contributions
 boy+0.037
 girl+0.036
 Year+0.033
 extingu+0.033
ksh+0.031
Neg logit contributions
vern-0.027
aches-0.027
ag-0.023
gh-0.023
earned-0.023
Token and
Token ID290
Feature activation+1.03e-02

Pos logit contributions
vern+0.016
aches+0.015
ending+0.014
 hardly+0.014
 accomplished+0.014
Neg logit contributions
 boy-0.021
 Year-0.021
 girl-0.021
 extingu-0.020
ksh-0.020
Token sailed
Token ID33835
Feature activation+6.01e-02

Pos logit contributions
 boy+0.019
 girl+0.019
 Year+0.018
 extingu+0.018
 asleep+0.016
Neg logit contributions
vern-0.016
aches-0.015
earned-0.014
 accomplished-0.014
ending-0.014
Token away
Token ID1497
Feature activation+6.86e-03

Pos logit contributions
 boy+0.105
 Year+0.102
 girl+0.101
 extingu+0.099
ksh+0.094
Neg logit contributions
vern-0.097
aches-0.095
ag-0.094
gh-0.092
 accomplished-0.088
Token mer
Token ID4017
Feature activation+1.50e-01

Pos logit contributions
 boy+0.013
 Year+0.013
 girl+0.013
ksh+0.012
 extingu+0.012
Neg logit contributions
vern-0.010
aches-0.009
 accomplished-0.009
 achieve-0.009
gh-0.008
Tokenrily
Token ID28904
Feature activation+3.32e-02

Pos logit contributions
 boy+0.192
 girl+0.187
 extingu+0.166
 Year+0.155
 Sn+0.151
Neg logit contributions
aches-0.322
ag-0.307
gh-0.298
vern-0.297
 hardly-0.294
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
 boy+0.061
 girl+0.058
 Year+0.056
 extingu+0.055
ksh+0.053
Neg logit contributions
aches-0.051
vern-0.050
gh-0.048
earned-0.046
ag-0.045
Token<|endoftext|>
Token ID50256
Feature activation+6.32e-02

Pos logit contributions
 boy+0.033
 girl+0.032
 Year+0.030
 extingu+0.030
 asleep+0.028
Neg logit contributions
vern-0.028
aches-0.027
earned-0.026
imes-0.025
ending-0.025
TokenOnce
Token ID7454
Feature activation+4.01e-02

Pos logit contributions
 boy+0.122
 girl+0.122
 extingu+0.121
 Year+0.116
ksh+0.113
Neg logit contributions
vern-0.079
ons-0.077
gh-0.076
aches-0.074
 accomplished-0.074
Token there
Token ID612
Feature activation+1.17e-02

Pos logit contributions
 boy+0.045
 girl+0.039
 asleep+0.029
cy+0.027
 tent+0.026
Neg logit contributions
aches-0.098
vern-0.097
earned-0.096
fters-0.095
ough-0.095
Token sun
Token ID4252
Feature activation+2.96e-02

Pos logit contributions
 accomplished+0.008
aches+0.008
ade+0.008
ag+0.008
earned+0.007
Neg logit contributions
 extingu-0.013
 Year-0.011
ksh-0.011
 Sn-0.011
 boy-0.011
Token.
Token ID13
Feature activation-7.09e-03

Pos logit contributions
 boy+0.063
 girl+0.061
 Year+0.059
 extingu+0.058
 cottage+0.054
Neg logit contributions
aches-0.033
ough-0.030
gh-0.029
ons-0.029
ag-0.029
Token
Token ID198
Feature activation-3.33e-02

Pos logit contributions
vern+0.009
aches+0.009
earned+0.009
ough+0.009
imes+0.009
Neg logit contributions
 boy-0.014
 girl-0.014
 extingu-0.013
 Year-0.013
maid-0.012
Token
Token ID198
Feature activation-3.23e-02

Pos logit contributions
aches+0.076
vern+0.073
imes+0.072
iable+0.072
earned+0.071
Neg logit contributions
 boy-0.044
 girl-0.039
 Year-0.033
 duck-0.029
 asleep-0.028
TokenA
Token ID32
Feature activation+1.31e-02

Pos logit contributions
aches+0.047
vern+0.046
imes+0.045
earned+0.042
iable+0.041
Neg logit contributions
 boy-0.069
 girl-0.065
 Year-0.058
 duck-0.055
 pengu-0.053
Token mer
Token ID4017
Feature activation+1.49e-01

Pos logit contributions
 extingu+0.018
 Year+0.017
 asleep+0.017
ksh+0.017
ASH+0.016
Neg logit contributions
vern-0.024
aches-0.024
ade-0.023
gh-0.022
ending-0.022
Tokenmaid
Token ID23151
Feature activation+3.90e-02

Pos logit contributions
 extingu+0.142
 Sn+0.140
 Year+0.134
 boy+0.132
 girl+0.128
Neg logit contributions
ag-0.322
aches-0.321
gh-0.319
 hardly-0.303
ending-0.299
Token that
Token ID326
Feature activation+5.60e-02

Pos logit contributions
 boy+0.071
 extingu+0.067
 girl+0.067
ksh+0.067
 Year+0.065
Neg logit contributions
aches-0.057
ons-0.055
ending-0.052
vern-0.051
imes-0.050
Token lived
Token ID5615
Feature activation+6.22e-03

Pos logit contributions
 boy+0.087
 girl+0.083
 extingu+0.080
 Year+0.079
ksh+0.074
Neg logit contributions
aches-0.101
vern-0.099
gh-0.092
ons-0.092
earned-0.092
Token in
Token ID287
Feature activation+1.68e-02

Pos logit contributions
 extingu+0.013
ksh+0.012
 Year+0.012
 boy+0.012
 girl+0.011
Neg logit contributions
aches-0.009
 accomplished-0.008
vern-0.008
ag-0.007
imes-0.007
Token the
Token ID262
Feature activation-4.10e-03

Pos logit contributions
ksh+0.036
 boy+0.036
 girl+0.035
 extingu+0.034
 Year+0.033
Neg logit contributions
vern-0.019
aches-0.018
ons-0.018
 accomplished-0.017
 achieve-0.017
Token bed
Token ID3996
Feature activation-5.82e-03

Pos logit contributions
vern+0.005
aches+0.005
 achieve+0.004
ag+0.004
fters+0.004
Neg logit contributions
 boy-0.005
 girl-0.005
 Year-0.004
 extingu-0.004
ksh-0.004
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
aches+0.009
vern+0.009
gh+0.009
ag+0.008
 achieve+0.008
Neg logit contributions
 boy-0.011
 girl-0.010
 extingu-0.010
cy-0.010
 Year-0.009
Token She
Token ID1375
Feature activation+8.40e-03

Pos logit contributions
 boy+0.030
 girl+0.028
 asleep+0.025
 Year+0.024
 extingu+0.024
Neg logit contributions
aches-0.035
vern-0.033
fters-0.031
earned-0.030
iable-0.030
Token dreamed
Token ID27947
Feature activation+1.53e-02

Pos logit contributions
 boy+0.015
 girl+0.015
 extingu+0.015
 Year+0.015
ksh+0.014
Neg logit contributions
aches-0.013
vern-0.012
 hardly-0.011
 accomplished-0.011
earned-0.011
Token of
Token ID286
Feature activation+4.59e-02

Pos logit contributions
 boy+0.034
 girl+0.033
 asleep+0.031
 Year+0.028
 tent+0.028
Neg logit contributions
aches-0.020
vern-0.019
earned-0.018
ough-0.018
iable-0.018
Token mer
Token ID4017
Feature activation+1.48e-01

Pos logit contributions
 boy+0.094
 girl+0.092
ksh+0.089
 extingu+0.087
cy+0.086
Neg logit contributions
aches-0.065
vern-0.064
ons-0.056
imes-0.055
fters-0.055
Tokenmaid
Token ID23151
Feature activation+4.39e-02

Pos logit contributions
 boy+0.157
 girl+0.146
 extingu+0.131
 Year+0.116
 Sn+0.104
Neg logit contributions
aches-0.352
ag-0.340
vern-0.334
gh-0.333
ending-0.327
Tokens
Token ID82
Feature activation+1.06e-02

Pos logit contributions
 boy+0.074
 girl+0.069
 extingu+0.066
 Year+0.066
ksh+0.060
Neg logit contributions
aches-0.076
vern-0.075
earned-0.070
imes-0.070
ending-0.069
Token and
Token ID290
Feature activation+1.35e-02

Pos logit contributions
 boy+0.017
 girl+0.017
 extingu+0.016
 Year+0.015
ksh+0.015
Neg logit contributions
aches-0.019
vern-0.019
gh-0.017
ag-0.017
imes-0.017
Token pirates
Token ID27516
Feature activation+1.66e-02

Pos logit contributions
 boy+0.026
 girl+0.025
 Year+0.024
 extingu+0.024
ksh+0.023
Neg logit contributions
aches-0.020
vern-0.019
earned-0.018
ons-0.018
imes-0.017
Token,
Token ID11
Feature activation+1.35e-03

Pos logit contributions
 boy+0.029
 girl+0.027
 extingu+0.027
 Year+0.027
ksh+0.025
Neg logit contributions
aches-0.028
vern-0.027
gh-0.025
ag-0.025
ons-0.025
Token.
Token ID13
Feature activation+3.42e-03

Pos logit contributions
aches+0.007
vern+0.007
 achieve+0.007
ons+0.006
 accomplished+0.006
Neg logit contributions
 boy-0.015
ksh-0.014
 Year-0.014
 girl-0.014
 extingu-0.014
Token It
Token ID632
Feature activation-2.99e-03

Pos logit contributions
 boy+0.007
 girl+0.007
 extingu+0.007
 Year+0.007
ksh+0.006
Neg logit contributions
vern-0.004
imes-0.004
earned-0.004
 hardly-0.004
ending-0.004
Token was
Token ID373
Feature activation+6.53e-03

Pos logit contributions
 hardly+0.004
aches+0.004
vern+0.004
 accomplished+0.004
 expect+0.004
Neg logit contributions
 boy-0.005
 Year-0.005
 extingu-0.005
ksh-0.005
 asleep-0.005
Token the
Token ID262
Feature activation-1.83e-05

Pos logit contributions
 boy+0.014
 girl+0.013
ksh+0.013
 Year+0.013
cy+0.013
Neg logit contributions
vern-0.008
aches-0.007
 supposed-0.007
 hardly-0.007
gh-0.007
Token magical
Token ID10883
Feature activation+1.87e-02

Pos logit contributions
aches+0.000
vern+0.000
 hardly+0.000
 capable+0.000
Days+0.000
Neg logit contributions
ucks-0.000
ksh-0.000
 extingu-0.000
cy-0.000
ASH-0.000
Token mer
Token ID4017
Feature activation+1.48e-01

Pos logit contributions
ksh+0.033
 extingu+0.029
 boy+0.029
ASH+0.029
cy+0.028
Neg logit contributions
aches-0.031
vern-0.030
earned-0.028
 expect-0.028
gh-0.028
Tokenmaid
Token ID23151
Feature activation+4.00e-02

Pos logit contributions
 boy+0.179
 extingu+0.158
 Sn+0.157
 girl+0.146
 pool+0.141
Neg logit contributions
aches-0.309
gh-0.296
ag-0.293
ending-0.291
 hardly-0.289
Token,
Token ID11
Feature activation-8.49e-03

Pos logit contributions
 boy+0.079
 girl+0.073
 Year+0.073
 extingu+0.071
ksh+0.069
Neg logit contributions
aches-0.056
vern-0.056
ending-0.054
ons-0.051
gh-0.051
Token who
Token ID508
Feature activation+2.22e-02

Pos logit contributions
aches+0.012
 hardly+0.012
vern+0.012
 achieve+0.012
 accomplished+0.011
Neg logit contributions
 boy-0.015
 Year-0.015
ksh-0.014
 extingu-0.014
 girl-0.014
Token thanked
Token ID26280
Feature activation+3.37e-02

Pos logit contributions
 boy+0.040
ksh+0.040
 extingu+0.040
 Year+0.040
 girl+0.039
Neg logit contributions
aches-0.033
ons-0.031
vern-0.031
 accomplished-0.031
 hardly-0.030
Token the
Token ID262
Feature activation-4.49e-06

Pos logit contributions
 boy+0.075
 girl+0.070
 extingu+0.069
ksh+0.068
 Year+0.067
Neg logit contributions
aches-0.039
vern-0.037
ag-0.033
ons-0.033
imes-0.033
Token yes
Token ID3763
Feature activation+5.06e-02

Pos logit contributions
 boy+0.006
 girl+0.005
 Year+0.005
 extingu+0.005
 asleep+0.005
Neg logit contributions
aches-0.006
vern-0.006
earned-0.005
imes-0.005
fters-0.005
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
 boy+0.089
 girl+0.084
 Year+0.074
 extingu+0.074
 asleep+0.071
Neg logit contributions
aches-0.088
vern-0.087
earned-0.081
imes-0.081
fters-0.080
Token She
Token ID1375
Feature activation+1.14e-03

Pos logit contributions
 boy+0.021
 girl+0.020
 Year+0.017
 extingu+0.017
 asleep+0.017
Neg logit contributions
aches-0.020
vern-0.020
earned-0.018
fters-0.018
gh-0.018
Token followed
Token ID3940
Feature activation-9.46e-03

Pos logit contributions
 boy+0.002
 girl+0.002
 Year+0.002
 extingu+0.002
 asleep+0.002
Neg logit contributions
aches-0.002
vern-0.002
 hardly-0.002
earned-0.002
 accomplished-0.001
Token the
Token ID262
Feature activation-2.03e-03

Pos logit contributions
vern+0.016
aches+0.016
earned+0.015
ending+0.014
imes+0.014
Neg logit contributions
 boy-0.017
 girl-0.016
 Year-0.015
 extingu-0.014
 asleep-0.014
Token mer
Token ID4017
Feature activation+1.47e-01

Pos logit contributions
vern+0.003
aches+0.003
 hardly+0.003
ag+0.003
 expect+0.003
Neg logit contributions
ksh-0.003
 extingu-0.003
 Year-0.003
ASH-0.003
ucks-0.003
Tokenmaid
Token ID23151
Feature activation+3.77e-02

Pos logit contributions
 boy+0.157
 Sn+0.154
 girl+0.148
 extingu+0.143
 asleep+0.142
Neg logit contributions
ag-0.310
aches-0.298
gh-0.292
ade-0.286
vern-0.283
Token through
Token ID832
Feature activation-3.24e-02

Pos logit contributions
 boy+0.066
 girl+0.061
 Year+0.059
 extingu+0.057
ksh+0.055
Neg logit contributions
aches-0.063
vern-0.061
earned-0.058
ending-0.058
ough-0.057
Token the
Token ID262
Feature activation-2.37e-03

Pos logit contributions
vern+0.035
aches+0.034
 achieve+0.032
ons+0.032
 accomplished+0.030
Neg logit contributions
 boy-0.071
ksh-0.070
 girl-0.066
 Year-0.066
 extingu-0.065
Token hidden
Token ID7104
Feature activation-5.84e-04

Pos logit contributions
 accomplished+0.004
ag+0.004
vern+0.003
 achieve+0.003
ade+0.003
Neg logit contributions
 extingu-0.004
ksh-0.004
 Year-0.003
 boy-0.003
work-0.003
Token door
Token ID3420
Feature activation+2.79e-02

Pos logit contributions
aches+0.001
vern+0.001
ag+0.001
ade+0.001
earned+0.001
Neg logit contributions
ksh-0.001
 boy-0.001
 girl-0.001
 Year-0.001
 extingu-0.001
Token
Token ID198
Feature activation-1.38e-02

Pos logit contributions
aches+0.031
vern+0.030
earned+0.029
imes+0.029
fters+0.028
Neg logit contributions
 boy-0.023
 girl-0.021
 Year-0.019
 extingu-0.018
 asleep-0.017
Token"
Token ID1
Feature activation+7.15e-03

Pos logit contributions
aches+0.017
vern+0.017
earned+0.015
imes+0.015
ending+0.014
Neg logit contributions
 boy-0.032
 girl-0.030
 Year-0.028
 extingu-0.028
 asleep-0.026
TokenI
Token ID40
Feature activation+8.42e-03

Pos logit contributions
 boy+0.013
 girl+0.012
 Year+0.011
 extingu+0.011
 asleep+0.011
Neg logit contributions
vern-0.012
aches-0.012
earned-0.011
ending-0.011
imes-0.011
Token am
Token ID716
Feature activation+2.12e-02

Pos logit contributions
 boy+0.017
 girl+0.017
 Year+0.016
 extingu+0.015
 asleep+0.015
Neg logit contributions
vern-0.012
aches-0.012
earned-0.011
ending-0.010
gh-0.010
Token a
Token ID257
Feature activation+2.90e-02

Pos logit contributions
 boy+0.038
 girl+0.036
 Year+0.033
 extingu+0.032
ksh+0.031
Neg logit contributions
aches-0.036
vern-0.036
imes-0.033
ough-0.032
fters-0.032
Token gen
Token ID2429
Feature activation+1.47e-01

Pos logit contributions
ksh+0.045
ASH+0.042
ucks+0.042
 Year+0.041
 asleep+0.041
Neg logit contributions
vern-0.051
aches-0.049
gh-0.048
iable-0.044
 else-0.043
Tokenie
Token ID494
Feature activation+3.49e-03

Pos logit contributions
 boy+0.308
 girl+0.291
 extingu+0.284
 Year+0.282
 asleep+0.275
Neg logit contributions
aches-0.205
vern-0.191
ag-0.177
ending-0.177
iable-0.175
Token,"
Token ID553
Feature activation+2.47e-02

Pos logit contributions
 extingu+0.007
 Year+0.007
ksh+0.007
 boy+0.007
ASH+0.006
Neg logit contributions
aches-0.004
vern-0.004
ending-0.004
ons-0.004
iable-0.004
Token the
Token ID262
Feature activation+9.94e-03

Pos logit contributions
 Year+0.049
ksh+0.049
 extingu+0.048
 boy+0.048
work+0.046
Neg logit contributions
aches-0.030
vern-0.028
ons-0.027
imes-0.027
iable-0.027
Token man
Token ID582
Feature activation+7.19e-02

Pos logit contributions
ksh+0.015
 asleep+0.014
cy+0.013
 extingu+0.012
 Year+0.012
Neg logit contributions
aches-0.021
vern-0.019
gh-0.017
 achieve-0.017
iable-0.017
Token said
Token ID531
Feature activation+1.05e-02

Pos logit contributions
 boy+0.136
 girl+0.133
 Year+0.131
 asleep+0.127
 extingu+0.124
Neg logit contributions
aches-0.107
vern-0.098
ons-0.095
ag-0.094
imes-0.093
Token sometimes
Token ID3360
Feature activation+5.45e-02

Pos logit contributions
aches+0.008
fters+0.007
vern+0.007
earned+0.007
 hardly+0.007
Neg logit contributions
 boy-0.012
 girl-0.012
 Year-0.011
 extingu-0.011
ksh-0.011
Token pretend
Token ID16614
Feature activation+6.57e-03

Pos logit contributions
 boy+0.108
 girl+0.103
 Year+0.091
 asleep+0.090
 extingu+0.089
Neg logit contributions
vern-0.086
aches-0.082
earned-0.078
imes-0.077
ending-0.076
Token to
Token ID284
Feature activation-7.78e-03

Pos logit contributions
 boy+0.012
 girl+0.011
 asleep+0.010
 Year+0.010
 extingu+0.009
Neg logit contributions
vern-0.012
aches-0.011
earned-0.011
iable-0.010
fters-0.010
Token be
Token ID307
Feature activation-2.84e-03

Pos logit contributions
aches+0.014
vern+0.013
ag+0.012
fters+0.012
earned+0.012
Neg logit contributions
 boy-0.013
 girl-0.013
 Year-0.012
 extingu-0.012
 asleep-0.011
Token a
Token ID257
Feature activation+1.31e-02

Pos logit contributions
aches+0.005
vern+0.005
imes+0.005
ag+0.005
earned+0.005
Neg logit contributions
 boy-0.005
 girl-0.005
 Year-0.004
 extingu-0.004
work-0.004
Token mer
Token ID4017
Feature activation+1.47e-01

Pos logit contributions
 extingu+0.022
 Year+0.021
ksh+0.021
ASH+0.021
work+0.021
Neg logit contributions
vern-0.019
Days-0.018
ade-0.018
 else-0.017
 hardly-0.017
Tokenmaid
Token ID23151
Feature activation+3.67e-02

Pos logit contributions
 boy+0.160
 girl+0.146
 extingu+0.140
 Sn+0.134
 Year+0.123
Neg logit contributions
aches-0.303
ag-0.303
gh-0.293
 hardly-0.282
ending-0.276
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
 boy+0.064
 girl+0.060
 Year+0.057
 extingu+0.056
ksh+0.052
Neg logit contributions
aches-0.060
vern-0.059
imes-0.056
ending-0.056
earned-0.055
Token
Token ID220
Feature activation-2.36e-02

Pos logit contributions
vern+0.020
aches+0.019
earned+0.018
imes+0.018
ending+0.018
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.016
 asleep-0.016
Token
Token ID198
Feature activation-3.63e-02

Pos logit contributions
aches+0.050
vern+0.049
earned+0.048
fters+0.047
iable+0.047
Neg logit contributions
 boy-0.033
 girl-0.030
 asleep-0.024
 Year-0.024
 extingu-0.024
Token
Token ID198
Feature activation-3.45e-02

Pos logit contributions
aches+0.074
vern+0.074
earned+0.070
imes+0.069
iable+0.069
Neg logit contributions
 boy-0.054
 girl-0.050
 Year-0.042
 asleep-0.040
 extingu-0.039
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
vern+0.017
aches+0.016
 achieve+0.016
gh+0.016
ag+0.015
Neg logit contributions
 boy-0.032
ksh-0.031
 Year-0.031
 girl-0.030
 extingu-0.030
Token she
Token ID673
Feature activation-5.80e-03

Pos logit contributions
aches+0.011
vern+0.011
earned+0.009
ending+0.009
iable+0.009
Neg logit contributions
 boy-0.034
 girl-0.032
 extingu-0.032
 Year-0.032
ksh-0.031
Token saw
Token ID2497
Feature activation-1.07e-02

Pos logit contributions
aches+0.010
vern+0.010
 accomplished+0.009
 hardly+0.009
iable+0.009
Neg logit contributions
 boy-0.010
 extingu-0.009
 girl-0.009
 Year-0.009
work-0.008
Token a
Token ID257
Feature activation+2.06e-02

Pos logit contributions
aches+0.017
vern+0.017
ons+0.016
earned+0.015
imes+0.015
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.017
 extingu-0.017
ksh-0.017
Token beautiful
Token ID4950
Feature activation+9.69e-04

Pos logit contributions
ucks+0.041
ksh+0.040
ASH+0.040
 Year+0.039
 extingu+0.038
Neg logit contributions
vern-0.026
 daring-0.023
 achieve-0.023
 else-0.023
ade-0.023
Token mer
Token ID4017
Feature activation+1.47e-01

Pos logit contributions
ksh+0.002
 extingu+0.002
ucks+0.002
ASH+0.002
 Claus+0.002
Neg logit contributions
ade-0.001
aches-0.001
 exercise-0.001
 amazing-0.001
gh-0.001
Tokenmaid
Token ID23151
Feature activation+3.90e-02

Pos logit contributions
 boy+0.178
 Sn+0.174
 girl+0.163
 cash+0.161
 Smith+0.154
Neg logit contributions
ag-0.290
gh-0.281
aches-0.267
 hardly-0.261
vern-0.257
Token swimming
Token ID14899
Feature activation+2.96e-02

Pos logit contributions
 boy+0.072
ASH+0.067
 Year+0.066
 girl+0.066
 extingu+0.065
Neg logit contributions
aches-0.056
ending-0.054
ons-0.054
vern-0.054
imes-0.052
Token around
Token ID1088
Feature activation-1.58e-02

Pos logit contributions
 Year+0.059
 boy+0.056
 girl+0.053
 extingu+0.053
ksh+0.052
Neg logit contributions
ag-0.042
ade-0.039
vern-0.037
aches-0.036
imes-0.036
Token her
Token ID607
Feature activation-1.55e-02

Pos logit contributions
aches+0.017
ons+0.016
gh+0.016
vern+0.016
ag+0.015
Neg logit contributions
 boy-0.034
ksh-0.033
 girl-0.032
 Year-0.031
 extingu-0.031
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
vern+0.021
aches+0.020
 achieve+0.020
ough+0.019
ag+0.018
Neg logit contributions
 boy-0.029
 girl-0.028
 extingu-0.028
 Year-0.027
ksh-0.026
Token Joe
Token ID5689
Feature activation-3.81e-02

Pos logit contributions
 boy+0.014
 girl+0.013
 Year+0.012
 extingu+0.012
 asleep+0.011
Neg logit contributions
vern-0.011
aches-0.011
earned-0.010
imes-0.010
ending-0.010
Token waved
Token ID26834
Feature activation+2.67e-02

Pos logit contributions
aches+0.057
earned+0.051
vern+0.051
ending+0.050
 hardly+0.049
Neg logit contributions
 extingu-0.070
 boy-0.069
 girl-0.066
 Year-0.066
ksh-0.064
Token goodbye
Token ID24829
Feature activation+5.35e-02

Pos logit contributions
 Year+0.056
 boy+0.053
 extingu+0.052
 girl+0.050
ksh+0.050
Neg logit contributions
ag-0.031
earned-0.030
vern-0.030
aches-0.028
ending-0.027
Token to
Token ID284
Feature activation-4.77e-03

Pos logit contributions
 boy+0.112
 Year+0.110
 girl+0.107
ucks+0.105
 extingu+0.104
Neg logit contributions
earned-0.059
vern-0.057
 hardly-0.057
ending-0.056
ag-0.055
Token the
Token ID262
Feature activation+2.52e-03

Pos logit contributions
aches+0.007
vern+0.007
earned+0.006
imes+0.006
ag+0.006
Neg logit contributions
 boy-0.010
 girl-0.009
 Year-0.009
 extingu-0.009
ksh-0.008
Token mer
Token ID4017
Feature activation+1.46e-01

Pos logit contributions
ksh+0.004
 extingu+0.004
ASH+0.003
 Year+0.003
ucks+0.003
Neg logit contributions
aches-0.005
vern-0.005
 else-0.005
 extraordinary-0.005
ade-0.004
Tokenmaid
Token ID23151
Feature activation+3.77e-02

Pos logit contributions
 boy+0.168
 extingu+0.165
 Sn+0.147
 girl+0.141
ksh+0.139
Neg logit contributions
aches-0.313
ag-0.302
gh-0.290
ade-0.283
 hardly-0.282
Token,
Token ID11
Feature activation-8.95e-03

Pos logit contributions
 boy+0.065
 girl+0.060
 Year+0.059
ASH+0.058
 extingu+0.058
Neg logit contributions
aches-0.060
ending-0.059
vern-0.058
earned-0.057
 hardly-0.055
Token and
Token ID290
Feature activation-5.29e-04

Pos logit contributions
aches+0.013
 hardly+0.013
vern+0.013
 accomplished+0.013
iable+0.013
Neg logit contributions
 boy-0.016
 Year-0.015
 extingu-0.015
 girl-0.015
ksh-0.014
Token hopped
Token ID45230
Feature activation-9.87e-03

Pos logit contributions
aches+0.001
 accomplished+0.001
 hardly+0.001
earned+0.001
 achieved+0.001
Neg logit contributions
 Year-0.001
 extingu-0.001
 boy-0.001
ksh-0.001
 girl-0.001
Token back
Token ID736
Feature activation+1.71e-02

Pos logit contributions
ag+0.014
vern+0.014
aches+0.013
gh+0.012
 accomplished+0.012
Neg logit contributions
 boy-0.020
 Year-0.019
 girl-0.018
 extingu-0.017
ksh-0.017
Token passport
Token ID17981
Feature activation+6.34e-03

Pos logit contributions
aches+0.019
vern+0.017
 exercise+0.017
imes+0.017
ade+0.017
Neg logit contributions
ksh-0.016
ucks-0.015
 extingu-0.015
ASH-0.014
 Year-0.013
Token belonged
Token ID19611
Feature activation-7.67e-03

Pos logit contributions
 extingu+0.011
ksh+0.011
 boy+0.010
 girl+0.010
 Year+0.010
Neg logit contributions
aches-0.011
ons-0.010
 accomplished-0.009
vern-0.009
 achieve-0.009
Token to
Token ID284
Feature activation-1.44e-02

Pos logit contributions
vern+0.010
aches+0.010
earned+0.009
gh+0.009
ending+0.009
Neg logit contributions
 boy-0.016
 girl-0.016
 Year-0.015
 extingu-0.015
ksh-0.014
Token a
Token ID257
Feature activation+1.14e-02

Pos logit contributions
vern+0.020
aches+0.020
gh+0.019
 achieve+0.018
earned+0.018
Neg logit contributions
 boy-0.028
 girl-0.027
 extingu-0.026
ksh-0.026
 Year-0.025
Token magical
Token ID10883
Feature activation+1.38e-02

Pos logit contributions
ucks+0.023
 extingu+0.022
ksh+0.022
ASH+0.021
 Year+0.020
Neg logit contributions
vern-0.015
 achieve-0.014
gh-0.014
 capable-0.014
 else-0.014
Token mer
Token ID4017
Feature activation+1.46e-01

Pos logit contributions
ksh+0.026
ucks+0.024
 extingu+0.024
ASH+0.023
 boy+0.022
Neg logit contributions
aches-0.019
vern-0.019
gh-0.018
ade-0.017
 achieve-0.017
Tokenmaid
Token ID23151
Feature activation+2.58e-02

Pos logit contributions
 extingu+0.163
 Sn+0.160
 boy+0.157
 girl+0.140
ASH+0.135
Neg logit contributions
aches-0.315
ag-0.305
gh-0.299
 hardly-0.294
vern-0.284
Token who
Token ID508
Feature activation+8.40e-03

Pos logit contributions
 boy+0.048
 girl+0.045
 extingu+0.043
 Year+0.043
ksh+0.041
Neg logit contributions
aches-0.040
vern-0.039
ending-0.037
earned-0.036
imes-0.036
Token had
Token ID550
Feature activation-2.65e-02

Pos logit contributions
 boy+0.016
 girl+0.016
 extingu+0.015
 Year+0.015
ksh+0.015
Neg logit contributions
aches-0.012
vern-0.012
 accomplished-0.011
ons-0.011
earned-0.011
Token been
Token ID587
Feature activation+2.64e-02

Pos logit contributions
vern+0.039
aches+0.039
earned+0.036
imes+0.036
iable+0.035
Neg logit contributions
 boy-0.052
 girl-0.050
 Year-0.045
 extingu-0.045
 asleep-0.044
Token visiting
Token ID10013
Feature activation+1.91e-02

Pos logit contributions
 boy+0.051
 girl+0.048
 extingu+0.045
 Year+0.045
ksh+0.043
Neg logit contributions
vern-0.040
aches-0.040
gh-0.036
earned-0.036
ag-0.036
Token man
Token ID582
Feature activation+6.47e-02

Pos logit contributions
aches+0.005
vern+0.005
 exercise+0.005
imes+0.005
gh+0.005
Neg logit contributions
ksh-0.005
ucks-0.005
 extingu-0.005
cy-0.005
 Year-0.004
Token watched
Token ID7342
Feature activation+3.72e-02

Pos logit contributions
ksh+0.127
 extingu+0.127
 Year+0.124
 girl+0.119
 boy+0.116
Neg logit contributions
aches-0.086
ons-0.079
 else-0.078
 hardly-0.077
 achieved-0.075
Token as
Token ID355
Feature activation-2.56e-02

Pos logit contributions
 boy+0.075
 girl+0.072
 Year+0.068
 extingu+0.067
cy+0.067
Neg logit contributions
aches-0.049
ag-0.047
imes-0.046
vern-0.046
ough-0.045
Token she
Token ID673
Feature activation-3.43e-03

Pos logit contributions
aches+0.027
vern+0.025
 hardly+0.024
 achieve+0.023
 accomplished+0.022
Neg logit contributions
ksh-0.057
 Year-0.056
 extingu-0.055
ASH-0.054
ucks-0.052
Token skipped
Token ID26684
Feature activation-2.19e-02

Pos logit contributions
aches+0.005
 accomplished+0.004
 achieved+0.004
ons+0.004
 hardly+0.004
Neg logit contributions
 boy-0.007
 girl-0.007
 extingu-0.006
 Year-0.006
ksh-0.006
Token mer
Token ID4017
Feature activation+1.46e-01

Pos logit contributions
ag+0.031
vern+0.029
aches+0.028
gh+0.028
ough+0.027
Neg logit contributions
 boy-0.042
 Year-0.041
 girl-0.040
 extingu-0.038
ksh-0.037
Tokenrily
Token ID28904
Feature activation+1.44e-02

Pos logit contributions
 boy+0.213
 girl+0.202
 extingu+0.183
 Year+0.175
 Sn+0.170
Neg logit contributions
aches-0.301
ag-0.281
 hardly-0.261
gh-0.260
vern-0.254
Token away
Token ID1497
Feature activation-6.51e-03

Pos logit contributions
 boy+0.026
 Year+0.025
 girl+0.025
ksh+0.024
 extingu+0.024
Neg logit contributions
aches-0.020
gh-0.019
ag-0.019
vern-0.018
imes-0.018
Token into
Token ID656
Feature activation-2.27e-02

Pos logit contributions
aches+0.008
vern+0.008
 hardly+0.007
gh+0.007
ag+0.007
Neg logit contributions
 boy-0.013
 Year-0.013
 girl-0.013
ksh-0.012
ASH-0.012
Token the
Token ID262
Feature activation-4.34e-03

Pos logit contributions
vern+0.023
aches+0.023
ons+0.021
 expect+0.020
 achieve+0.020
Neg logit contributions
ksh-0.050
 boy-0.049
 Year-0.047
 girl-0.047
 Claus-0.046
Token sunset
Token ID26428
Feature activation+1.52e-02

Pos logit contributions
 accomplished+0.006
ag+0.006
aches+0.005
ade+0.005
 exercise+0.005
Neg logit contributions
 extingu-0.008
ucks-0.007
ksh-0.007
maid-0.007
 Year-0.007
Token.
Token ID13
Feature activation+2.52e-03

Pos logit contributions
aches+0.001
vern+0.001
 achieve+0.001
ag+0.001
ons+0.001
Neg logit contributions
 boy-0.001
 girl-0.001
 Year-0.001
 extingu-0.001
ksh-0.001
Token He
Token ID679
Feature activation+8.71e-03

Pos logit contributions
 boy+0.005
 girl+0.004
 extingu+0.004
 Year+0.004
 asleep+0.004
Neg logit contributions
aches-0.004
vern-0.004
imes-0.004
earned-0.004
ough-0.004
Token even
Token ID772
Feature activation-7.37e-03

Pos logit contributions
 extingu+0.017
 girl+0.016
 boy+0.016
 Year+0.016
ksh+0.015
Neg logit contributions
aches-0.013
 hardly-0.011
 accomplished-0.011
 achieved-0.011
 achieve-0.011
Token saw
Token ID2497
Feature activation-9.00e-03

Pos logit contributions
aches+0.012
vern+0.010
earned+0.010
ons+0.010
 accomplished+0.010
Neg logit contributions
 boy-0.013
 girl-0.012
 Year-0.012
 extingu-0.012
ksh-0.011
Token a
Token ID257
Feature activation+1.89e-02

Pos logit contributions
aches+0.013
ons+0.013
vern+0.013
imes+0.012
earned+0.012
Neg logit contributions
 boy-0.016
 girl-0.016
 extingu-0.016
 Year-0.016
ksh-0.015
Token mer
Token ID4017
Feature activation+1.46e-01

Pos logit contributions
ucks+0.037
ASH+0.036
ksh+0.036
 extingu+0.035
 Year+0.033
Neg logit contributions
vern-0.023
aches-0.023
 achieve-0.023
ade-0.021
 else-0.021
Tokenmaid
Token ID23151
Feature activation+3.69e-02

Pos logit contributions
 Sn+0.170
 boy+0.161
 girl+0.151
 extingu+0.148
ASH+0.142
Neg logit contributions
ag-0.302
aches-0.295
gh-0.290
 hardly-0.289
vern-0.271
Token!
Token ID0
Feature activation-1.38e-02

Pos logit contributions
 boy+0.066
ASH+0.061
 girl+0.061
 extingu+0.061
ksh+0.060
Neg logit contributions
aches-0.057
ons-0.053
ending-0.052
imes-0.051
 achieve-0.051
Token
Token ID220
Feature activation-1.53e-02

Pos logit contributions
vern+0.020
aches+0.020
imes+0.020
earned+0.019
ough+0.019
Neg logit contributions
 boy-0.026
 girl-0.025
 extingu-0.024
 Year-0.024
 asleep-0.022
Token
Token ID198
Feature activation-2.26e-02

Pos logit contributions
vern+0.027
aches+0.027
earned+0.025
imes+0.024
fters+0.024
Neg logit contributions
 boy-0.026
 girl-0.025
 Year-0.022
 extingu-0.022
 asleep-0.021
Token
Token ID198
Feature activation-1.99e-02

Pos logit contributions
aches+0.044
vern+0.044
earned+0.042
ending+0.041
imes+0.041
Neg logit contributions
 boy-0.035
 girl-0.031
 Year-0.027
 extingu-0.025
 asleep-0.025
Token swimming
Token ID14899
Feature activation+2.96e-02

Pos logit contributions
 boy+0.072
ASH+0.067
 Year+0.066
 girl+0.066
 extingu+0.065
Neg logit contributions
aches-0.056
ending-0.054
ons-0.054
vern-0.054
imes-0.052
Token around
Token ID1088
Feature activation-1.58e-02

Pos logit contributions
 Year+0.059
 boy+0.056
 girl+0.053
 extingu+0.053
ksh+0.052
Neg logit contributions
ag-0.042
ade-0.039
vern-0.037
aches-0.036
imes-0.036
Token her
Token ID607
Feature activation-1.55e-02

Pos logit contributions
aches+0.017
ons+0.016
gh+0.016
vern+0.016
ag+0.015
Neg logit contributions
 boy-0.034
ksh-0.033
 girl-0.032
 Year-0.031
 extingu-0.031
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
vern+0.021
aches+0.020
 achieve+0.020
ough+0.019
ag+0.018
Neg logit contributions
 boy-0.029
 girl-0.028
 extingu-0.028
 Year-0.027
ksh-0.026
Token The
Token ID383
Feature activation-4.37e-03

Pos logit contributions
 boy+0.008
 girl+0.008
 Year+0.007
 extingu+0.007
 tent+0.007
Neg logit contributions
vern-0.005
earned-0.005
aches-0.005
ending-0.005
 hardly-0.005
Token mer
Token ID4017
Feature activation+1.46e-01

Pos logit contributions
aches+0.008
vern+0.008
ag+0.008
ade+0.008
 extraordinary+0.008
Neg logit contributions
 extingu-0.006
ksh-0.006
 Year-0.005
ASH-0.005
ucks-0.005
Tokenmaid
Token ID23151
Feature activation+3.80e-02

Pos logit contributions
 boy+0.162
 girl+0.140
 extingu+0.136
 Sn+0.132
 Year+0.124
Neg logit contributions
aches-0.317
ag-0.317
gh-0.303
 hardly-0.296
ending-0.292
Token smiled
Token ID13541
Feature activation+4.25e-02

Pos logit contributions
 boy+0.071
 girl+0.068
 extingu+0.068
 Year+0.067
ksh+0.064
Neg logit contributions
aches-0.056
 hardly-0.053
vern-0.052
ons-0.051
ending-0.050
Token and
Token ID290
Feature activation-3.98e-03

Pos logit contributions
 Year+0.085
 boy+0.077
 extingu+0.072
ASH+0.071
 poster+0.071
Neg logit contributions
vern-0.052
Her-0.050
ending-0.048
 hardly-0.047
 accomplished-0.046
Token said
Token ID531
Feature activation+6.45e-04

Pos logit contributions
aches+0.005
 hardly+0.005
 accomplished+0.005
vern+0.004
ons+0.004
Neg logit contributions
 boy-0.008
 Year-0.008
 extingu-0.008
 girl-0.008
ASH-0.007
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
 boy+0.001
 girl+0.001
 Year+0.001
 extingu+0.001
ksh+0.001
Neg logit contributions
vern-0.001
aches-0.001
gh-0.001
imes-0.001
ending-0.001
Token rings
Token ID13917
Feature activation-4.97e-02

Pos logit contributions
aches+0.034
imes+0.031
earned+0.029
fters+0.029
ons+0.029
Neg logit contributions
 boy-0.030
 girl-0.028
 Year-0.028
work-0.027
cy-0.026
Token,
Token ID11
Feature activation-2.26e-02

Pos logit contributions
aches+0.086
gh+0.075
vern+0.075
ons+0.073
ough+0.072
Neg logit contributions
 boy-0.090
 girl-0.087
 Year-0.079
 extingu-0.075
ksh-0.075
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
aches+0.041
imes+0.036
 hardly+0.034
fters+0.034
ons+0.034
Neg logit contributions
 boy-0.037
 girl-0.035
cy-0.035
ASH-0.032
maid-0.031
Token neck
Token ID7393
Feature activation-1.33e-01

Pos logit contributions
aches+0.019
imes+0.016
ons+0.016
 achieve+0.015
fters+0.015
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.018
ksh-0.018
 extingu-0.018
Tokenl
Token ID75
Feature activation+5.05e-03

Pos logit contributions
aches+0.213
vern+0.201
gh+0.185
imes+0.184
ag+0.183
Neg logit contributions
 boy-0.256
 girl-0.245
 Year-0.225
 extingu-0.223
 asleep-0.211
Tokenaces
Token ID2114
Feature activation-1.80e-01

Pos logit contributions
 boy+0.012
 girl+0.012
 Year+0.011
 extingu+0.011
 asleep+0.010
Neg logit contributions
aches-0.006
vern-0.005
imes-0.005
earned-0.005
ag-0.005
Token.
Token ID13
Feature activation-5.07e-03

Pos logit contributions
vern+0.319
aches+0.317
earned+0.295
imes+0.291
ending+0.288
Neg logit contributions
 boy-0.304
 girl-0.287
 Year-0.259
 extingu-0.257
 asleep-0.246
Token
Token ID198
Feature activation-2.23e-02

Pos logit contributions
imes+0.007
vern+0.007
aches+0.007
ough+0.007
earned+0.007
Neg logit contributions
 boy-0.009
 girl-0.009
 extingu-0.009
 Year-0.008
work-0.008
Token
Token ID198
Feature activation-1.72e-02

Pos logit contributions
aches+0.041
vern+0.041
earned+0.039
iable+0.038
ending+0.038
Neg logit contributions
 boy-0.036
 girl-0.034
 Year-0.030
 extingu-0.029
 asleep-0.028
Token"
Token ID1
Feature activation+2.18e-03

Pos logit contributions
vern+0.025
aches+0.025
earned+0.023
imes+0.022
ending+0.022
Neg logit contributions
 boy-0.035
 girl-0.034
 Year-0.031
 extingu-0.030
 asleep-0.029
TokenWow
Token ID22017
Feature activation+5.04e-03

Pos logit contributions
 boy+0.004
 asleep+0.003
 girl+0.003
maid+0.003
 extingu+0.003
Neg logit contributions
aches-0.004
vern-0.003
fters-0.003
earned-0.003
Days-0.003
Token saw
Token ID2497
Feature activation-2.34e-02

Pos logit contributions
 boy+0.027
 girl+0.026
 Year+0.025
 extingu+0.025
 asleep+0.024
Neg logit contributions
aches-0.021
vern-0.019
ag-0.018
earned-0.018
 achieve-0.018
Token rings
Token ID13917
Feature activation-3.67e-02

Pos logit contributions
aches+0.034
ons+0.032
ag+0.031
vern+0.031
imes+0.031
Neg logit contributions
 Year-0.042
 girl-0.042
 boy-0.041
ksh-0.041
 extingu-0.040
Token,
Token ID11
Feature activation-1.42e-02

Pos logit contributions
aches+0.061
gh+0.053
ag+0.053
vern+0.053
iable+0.052
Neg logit contributions
 boy-0.066
 Year-0.063
 girl-0.062
 extingu-0.062
ksh-0.060
Token neck
Token ID7393
Feature activation-1.32e-01

Pos logit contributions
aches+0.023
ons+0.020
ag+0.019
Her+0.018
imes+0.018
Neg logit contributions
 extingu-0.025
cy-0.024
ksh-0.024
 boy-0.024
ASH-0.024
Tokenl
Token ID75
Feature activation+7.01e-03

Pos logit contributions
aches+0.208
vern+0.189
ons+0.179
gh+0.176
ag+0.174
Neg logit contributions
 boy-0.261
 girl-0.250
 Year-0.232
 extingu-0.230
ksh-0.226
Tokenaces
Token ID2114
Feature activation-1.76e-01

Pos logit contributions
 boy+0.020
 girl+0.019
 extingu+0.018
 Year+0.018
 cottage+0.017
Neg logit contributions
aches-0.005
vern-0.005
imes-0.004
ag-0.004
ons-0.004
Token,
Token ID11
Feature activation-1.19e-02

Pos logit contributions
aches+0.328
vern+0.326
ending+0.298
earned+0.298
iable+0.297
Neg logit contributions
 boy-0.283
 girl-0.267
 Year-0.246
 extingu-0.239
ksh-0.222
Token brace
Token ID22581
Feature activation-7.27e-02

Pos logit contributions
aches+0.022
ons+0.018
fters+0.018
ag+0.018
imes+0.017
Neg logit contributions
 boy-0.020
 girl-0.019
 extingu-0.018
 Year-0.018
ksh-0.018
Tokenlets
Token ID5289
Feature activation-1.20e-01

Pos logit contributions
aches+0.117
vern+0.116
earned+0.107
gh+0.105
imes+0.105
Neg logit contributions
 boy-0.137
 girl-0.129
 Year-0.119
 extingu-0.117
 asleep-0.112
Token and
Token ID290
Feature activation-8.61e-03

Pos logit contributions
aches+0.221
vern+0.217
imes+0.200
gh+0.198
ons+0.198
Neg logit contributions
 boy-0.197
 girl-0.186
 Year-0.172
 extingu-0.166
ksh-0.159
Token ear
Token ID1027
Feature activation-4.77e-02

Pos logit contributions
aches+0.014
vern+0.013
earned+0.013
ons+0.012
gh+0.012
Neg logit contributions
 boy-0.015
 girl-0.014
 Year-0.014
 extingu-0.014
 asleep-0.013
TokenThese
Token ID4711
Feature activation-3.66e-02

Pos logit contributions
 tent+0.065
 boy+0.064
 asleep+0.064
 extingu+0.063
 girl+0.062
Neg logit contributions
earned-0.049
aches-0.048
vern-0.047
ending-0.047
iable-0.047
Token are
Token ID389
Feature activation+3.06e-02

Pos logit contributions
aches+0.059
vern+0.057
imes+0.054
ons+0.053
iable+0.053
Neg logit contributions
 boy-0.066
 girl-0.063
 Year-0.060
 extingu-0.059
 asleep-0.059
Token beautiful
Token ID4950
Feature activation-1.03e-02

Pos logit contributions
 boy+0.061
 girl+0.058
 Year+0.056
 extingu+0.055
 asleep+0.053
Neg logit contributions
aches-0.046
vern-0.044
imes-0.041
iable-0.040
ough-0.039
Token neck
Token ID7393
Feature activation-1.24e-01

Pos logit contributions
aches+0.015
ons+0.014
vern+0.013
ade+0.013
imes+0.013
Neg logit contributions
 extingu-0.019
 boy-0.018
ksh-0.018
ASH-0.017
 girl-0.017
Tokenl
Token ID75
Feature activation+1.14e-02

Pos logit contributions
aches+0.211
vern+0.208
earned+0.192
imes+0.190
ending+0.188
Neg logit contributions
 boy-0.221
 girl-0.209
 extingu-0.193
 Year-0.193
 asleep-0.183
Tokenaces
Token ID2114
Feature activation-1.75e-01

Pos logit contributions
 boy+0.026
 girl+0.025
 extingu+0.024
 Year+0.023
 cottage+0.022
Neg logit contributions
aches-0.014
vern-0.013
imes-0.012
ons-0.012
ag-0.012
Token and
Token ID290
Feature activation-5.77e-03

Pos logit contributions
vern+0.297
aches+0.297
earned+0.272
imes+0.270
iable+0.269
Neg logit contributions
 boy-0.307
 girl-0.291
 Year-0.271
 extingu-0.266
 asleep-0.249
Token brace
Token ID22581
Feature activation-6.92e-02

Pos logit contributions
aches+0.010
vern+0.009
earned+0.009
fters+0.009
imes+0.009
Neg logit contributions
 boy-0.010
 girl-0.009
 extingu-0.009
 Year-0.009
 asleep-0.008
Tokenlets
Token ID5289
Feature activation-1.16e-01

Pos logit contributions
aches+0.113
vern+0.112
earned+0.103
imes+0.101
ending+0.101
Neg logit contributions
 boy-0.128
 girl-0.121
 Year-0.112
 extingu-0.111
 asleep-0.105
Token.
Token ID13
Feature activation+1.19e-03

Pos logit contributions
aches+0.192
vern+0.190
earned+0.173
imes+0.173
ending+0.170
Neg logit contributions
 boy-0.211
 girl-0.200
 Year-0.186
 extingu-0.184
 asleep-0.172
Token You
Token ID921
Feature activation-8.32e-03

Pos logit contributions
 boy+0.002
 girl+0.002
 extingu+0.002
 Year+0.002
 asleep+0.002
Neg logit contributions
vern-0.002
ough-0.002
aches-0.002
imes-0.002
earned-0.002
Token fish
Token ID5916
Feature activation+4.95e-03

Pos logit contributions
ons+0.029
aches+0.028
ade+0.027
imes+0.025
vern+0.024
Neg logit contributions
ksh-0.034
 Amen-0.031
ASH-0.030
 extingu-0.030
 Year-0.030
Token,
Token ID11
Feature activation-3.53e-02

Pos logit contributions
 boy+0.009
 girl+0.008
 Year+0.008
 extingu+0.008
ksh+0.008
Neg logit contributions
aches-0.008
vern-0.008
imes-0.007
ons-0.007
gh-0.007
Token some
Token ID617
Feature activation-1.26e-02

Pos logit contributions
aches+0.056
imes+0.049
ons+0.048
vern+0.048
 hardly+0.047
Neg logit contributions
 boy-0.062
 Year-0.060
 girl-0.059
 extingu-0.058
ksh-0.058
Token l
Token ID300
Feature activation-1.38e-02

Pos logit contributions
aches+0.021
vern+0.020
imes+0.019
earned+0.019
ag+0.019
Neg logit contributions
 boy-0.022
 girl-0.021
 Year-0.020
 extingu-0.020
ksh-0.019
Tokenily
Token ID813
Feature activation-1.52e-02

Pos logit contributions
aches+0.015
vern+0.014
iable+0.014
earned+0.014
 achieve+0.014
Neg logit contributions
 boy-0.030
 girl-0.030
 extingu-0.028
 asleep-0.028
 duck-0.027
Token pads
Token ID21226
Feature activation-1.75e-01

Pos logit contributions
aches+0.026
vern+0.025
imes+0.024
ons+0.024
earned+0.023
Neg logit contributions
 boy-0.026
 girl-0.024
 extingu-0.023
 Year-0.023
ksh-0.021
Token and
Token ID290
Feature activation-1.70e-02

Pos logit contributions
vern+0.365
aches+0.363
earned+0.344
fters+0.338
ending+0.336
Neg logit contributions
 boy-0.239
 girl-0.223
 extingu-0.193
 Year-0.191
 asleep-0.186
Token even
Token ID772
Feature activation-2.23e-02

Pos logit contributions
aches+0.028
imes+0.026
earned+0.025
ons+0.024
ough+0.024
Neg logit contributions
 boy-0.028
 Year-0.027
 extingu-0.026
ksh-0.026
 girl-0.026
Token a
Token ID257
Feature activation+7.70e-03

Pos logit contributions
aches+0.038
earned+0.034
imes+0.034
ag+0.033
vern+0.033
Neg logit contributions
 boy-0.038
 Year-0.037
 girl-0.036
 extingu-0.036
work-0.033
Token frog
Token ID21264
Feature activation+2.25e-02

Pos logit contributions
ucks+0.013
 Year+0.013
 extingu+0.013
ksh+0.012
ASH+0.012
Neg logit contributions
vern-0.012
aches-0.012
gh-0.012
ade-0.011
 hardly-0.011
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
 boy+0.044
 girl+0.042
 Year+0.041
 extingu+0.040
ksh+0.038
Neg logit contributions
aches-0.033
vern-0.031
imes-0.030
gh-0.029
ons-0.029
Token want
Token ID765
Feature activation-2.83e-02

Pos logit contributions
 boy+0.005
 girl+0.005
 Year+0.005
 extingu+0.004
ksh+0.004
Neg logit contributions
aches-0.004
vern-0.004
 achieve-0.004
 hardly-0.004
 expect-0.003
Token to
Token ID284
Feature activation-1.90e-02

Pos logit contributions
aches+0.036
vern+0.035
earned+0.032
gh+0.031
imes+0.031
Neg logit contributions
 boy-0.061
 girl-0.059
 Year-0.055
 extingu-0.054
ksh-0.053
Token make
Token ID787
Feature activation-3.46e-02

Pos logit contributions
vern+0.035
imes+0.035
ending+0.034
aches+0.033
earned+0.033
Neg logit contributions
 boy-0.031
 girl-0.029
 extingu-0.027
 Year-0.026
 t-0.026
Token neck
Token ID7393
Feature activation-1.30e-01

Pos logit contributions
aches+0.053
vern+0.050
ons+0.048
ag+0.047
ough+0.046
Neg logit contributions
 boy-0.065
 girl-0.064
fly-0.059
cy-0.059
 Year-0.058
Tokenl
Token ID75
Feature activation+1.00e-02

Pos logit contributions
aches+0.174
vern+0.169
earned+0.151
fters+0.149
ag+0.148
Neg logit contributions
 boy-0.278
 girl-0.267
 Year-0.248
 extingu-0.248
 asleep-0.237
Tokenaces
Token ID2114
Feature activation-1.75e-01

Pos logit contributions
 boy+0.028
 girl+0.027
 Year+0.026
 asleep+0.025
 extingu+0.025
Neg logit contributions
vern-0.007
aches-0.006
earned-0.005
fters-0.005
iable-0.005
Token and
Token ID290
Feature activation-5.36e-03

Pos logit contributions
vern+0.309
aches+0.307
earned+0.284
imes+0.280
iable+0.279
Neg logit contributions
 boy-0.295
 girl-0.279
 Year-0.255
 extingu-0.251
 asleep-0.236
Token brace
Token ID22581
Feature activation-6.83e-02

Pos logit contributions
aches+0.009
vern+0.008
earned+0.008
fters+0.008
ons+0.008
Neg logit contributions
 boy-0.009
 girl-0.009
 Year-0.008
 extingu-0.008
ksh-0.008
Tokenlets
Token ID5289
Feature activation-1.18e-01

Pos logit contributions
aches+0.110
vern+0.109
earned+0.100
imes+0.098
ag+0.098
Neg logit contributions
 boy-0.128
 girl-0.121
 Year-0.111
 extingu-0.110
 asleep-0.105
Token with
Token ID351
Feature activation+1.49e-02

Pos logit contributions
aches+0.198
vern+0.196
imes+0.178
earned+0.178
ag+0.176
Neg logit contributions
 boy-0.212
 girl-0.201
 Year-0.188
 extingu-0.183
ksh-0.171
Token them
Token ID606
Feature activation-8.58e-03

Pos logit contributions
 boy+0.026
 girl+0.024
 Year+0.022
 extingu+0.022
 asleep+0.021
Neg logit contributions
aches-0.026
vern-0.026
earned-0.024
imes-0.023
ag-0.023
Token you
Token ID345
Feature activation-1.48e-02

Pos logit contributions
 boy+0.041
 girl+0.039
 extingu+0.036
 Year+0.035
 asleep+0.034
Neg logit contributions
vern-0.039
aches-0.039
earned-0.036
iable-0.035
imes-0.035
Token tie
Token ID9839
Feature activation-4.84e-02

Pos logit contributions
vern+0.021
aches+0.021
imes+0.019
earned+0.019
ending+0.019
Neg logit contributions
 boy-0.031
 girl-0.029
 Year-0.027
 extingu-0.027
 asleep-0.026
Token my
Token ID616
Feature activation-3.99e-04

Pos logit contributions
aches+0.078
vern+0.077
earned+0.071
imes+0.070
iable+0.070
Neg logit contributions
 boy-0.089
 girl-0.085
 Year-0.078
 extingu-0.078
 asleep-0.073
Token sho
Token ID7354
Feature activation-8.57e-02

Pos logit contributions
vern+0.001
aches+0.001
earned+0.001
gh+0.001
ag+0.001
Neg logit contributions
 boy-0.001
 girl-0.001
 extingu-0.001
 Year-0.001
work-0.001
Tokenel
Token ID417
Feature activation-3.22e-03

Pos logit contributions
vern+0.162
aches+0.161
fters+0.152
Days+0.150
 achieve+0.149
Neg logit contributions
 boy-0.132
 girl-0.124
cy-0.113
 Year-0.110
 extingu-0.108
Tokenaces
Token ID2114
Feature activation-1.65e-01

Pos logit contributions
vern+0.005
aches+0.005
fters+0.005
ending+0.005
iable+0.005
Neg logit contributions
 boy-0.006
 girl-0.005
 extingu-0.005
 Year-0.005
 asleep-0.005
Token for
Token ID329
Feature activation-1.99e-02

Pos logit contributions
vern+0.287
aches+0.285
earned+0.265
imes+0.261
ending+0.259
Neg logit contributions
 boy-0.285
 girl-0.270
 Year-0.243
 extingu-0.241
 asleep-0.232
Token me
Token ID502
Feature activation-1.69e-02

Pos logit contributions
vern+0.041
aches+0.040
earned+0.039
ending+0.038
imes+0.037
Neg logit contributions
 boy-0.027
 girl-0.025
 Year-0.023
 asleep-0.022
 extingu-0.021
Token?"
Token ID1701
Feature activation+1.86e-02

Pos logit contributions
vern+0.029
aches+0.028
fters+0.027
earned+0.026
Days+0.026
Neg logit contributions
 boy-0.029
 girl-0.027
 asleep-0.025
 Year-0.024
 extingu-0.024
Token
Token ID220
Feature activation-1.58e-02

Pos logit contributions
 boy+0.032
 girl+0.031
 extingu+0.029
 Year+0.028
 asleep+0.027
Neg logit contributions
aches-0.031
vern-0.031
earned-0.029
imes-0.029
ons-0.028
Token
Token ID198
Feature activation-1.76e-02

Pos logit contributions
aches+0.029
vern+0.029
earned+0.028
fters+0.027
gh+0.027
Neg logit contributions
 boy-0.025
 girl-0.024
 Year-0.021
 extingu-0.021
 asleep-0.020
Token he
Token ID339
Feature activation-1.91e-02

Pos logit contributions
aches+0.021
 hardly+0.017
 achieve+0.015
ons+0.014
gh+0.014
Neg logit contributions
ksh-0.093
 extingu-0.092
 Year-0.089
 boy-0.088
 girl-0.088
Token found
Token ID1043
Feature activation-6.26e-02

Pos logit contributions
aches+0.030
 hardly+0.027
 accomplished+0.027
gh+0.026
ons+0.026
Neg logit contributions
 extingu-0.035
 boy-0.034
 girl-0.033
 Year-0.032
ksh-0.031
Token two
Token ID734
Feature activation-3.35e-03

Pos logit contributions
vern+0.110
aches+0.109
earned+0.101
imes+0.100
ons+0.099
Neg logit contributions
 boy-0.105
 girl-0.100
 Year-0.094
 extingu-0.090
ksh-0.087
Token little
Token ID1310
Feature activation+4.25e-02

Pos logit contributions
aches+0.006
vern+0.006
imes+0.005
ons+0.005
earned+0.005
Neg logit contributions
 boy-0.006
 Year-0.005
 girl-0.005
 extingu-0.005
ksh-0.005
Token m
Token ID285
Feature activation-7.25e-03

Pos logit contributions
 Year+0.064
ksh+0.062
 extingu+0.061
 hyd+0.059
 Amen+0.059
Neg logit contributions
ons-0.067
imes-0.063
old-0.061
aches-0.061
 else-0.059
Tokenittens
Token ID34978
Feature activation-1.65e-01

Pos logit contributions
vern+0.009
aches+0.008
fters+0.007
earned+0.007
iable+0.007
Neg logit contributions
 boy-0.016
 girl-0.016
 extingu-0.015
 Year-0.015
 asleep-0.014
Token lying
Token ID9105
Feature activation+2.12e-02

Pos logit contributions
aches+0.274
vern+0.261
ons+0.257
imes+0.253
ending+0.249
Neg logit contributions
 boy-0.293
 girl-0.280
 Year-0.260
 extingu-0.252
ksh-0.240
Token in
Token ID287
Feature activation-4.03e-04

Pos logit contributions
 boy+0.039
 Year+0.037
 girl+0.037
 extingu+0.037
ksh+0.035
Neg logit contributions
aches-0.031
ons-0.029
imes-0.029
ag-0.028
gh-0.028
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
aches+0.000
vern+0.000
ons+0.000
Every+0.000
 hardly+0.000
Neg logit contributions
ksh-0.001
 boy-0.001
 girl-0.001
work-0.001
maid-0.001
Token snow
Token ID6729
Feature activation+2.37e-02

Pos logit contributions
aches+0.031
earned+0.029
ade+0.028
ag+0.028
ough+0.027
Neg logit contributions
 boy-0.033
maid-0.033
 extingu-0.032
work-0.032
 Year-0.032
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
 girl+0.044
 boy+0.044
 Year+0.040
Uh+0.040
ucks+0.039
Neg logit contributions
aches-0.035
ons-0.031
ade-0.031
gh-0.031
ough-0.029
Token seat
Token ID5852
Feature activation-7.11e-03

Pos logit contributions
 boy+0.103
 girl+0.103
 extingu+0.101
 Year+0.100
ksh+0.099
Neg logit contributions
aches-0.093
earned-0.084
ons-0.083
ag-0.082
iable-0.082
Token.
Token ID13
Feature activation+6.87e-03

Pos logit contributions
aches+0.010
ag+0.009
gh+0.009
ons+0.009
earned+0.009
Neg logit contributions
 boy-0.013
 girl-0.013
 Year-0.013
 extingu-0.012
ksh-0.012
Token After
Token ID2293
Feature activation-3.25e-02

Pos logit contributions
 boy+0.013
 girl+0.013
 extingu+0.012
 Year+0.012
work+0.012
Neg logit contributions
vern-0.009
imes-0.009
aches-0.009
earned-0.009
ough-0.009
Token a
Token ID257
Feature activation+9.62e-03

Pos logit contributions
aches+0.047
vern+0.044
gh+0.043
ons+0.041
 achieve+0.041
Neg logit contributions
 boy-0.066
 girl-0.064
 extingu-0.060
ksh-0.060
cy-0.058
Token few
Token ID1178
Feature activation-4.96e-03

Pos logit contributions
ucks+0.019
 extingu+0.019
 Year+0.018
ASH+0.018
 boy+0.017
Neg logit contributions
gh-0.012
Days-0.012
aches-0.012
vern-0.012
 hardly-0.011
Token attempts
Token ID6370
Feature activation-1.63e-01

Pos logit contributions
aches+0.008
vern+0.008
earned+0.007
gh+0.007
imes+0.007
Neg logit contributions
 boy-0.009
 girl-0.009
 extingu-0.008
 Year-0.008
 asleep-0.007
Token,
Token ID11
Feature activation-2.20e-02

Pos logit contributions
vern+0.268
aches+0.267
earned+0.246
imes+0.242
ending+0.241
Neg logit contributions
 boy-0.293
 girl-0.279
 Year-0.255
 extingu-0.253
 asleep-0.240
Token the
Token ID262
Feature activation-1.80e-02

Pos logit contributions
aches+0.026
 hardly+0.024
iable+0.022
imes+0.022
ons+0.022
Neg logit contributions
 extingu-0.045
ksh-0.045
 Year-0.044
ucks-0.043
 boy-0.043
Token engine
Token ID3113
Feature activation+1.26e-02

Pos logit contributions
aches+0.032
vern+0.029
 exercise+0.029
ag+0.028
earned+0.028
Neg logit contributions
ksh-0.025
 extingu-0.024
ucks-0.024
maid-0.024
cy-0.024
Token started
Token ID2067
Feature activation-3.09e-02

Pos logit contributions
 extingu+0.023
 girl+0.022
 Year+0.022
 boy+0.022
ksh+0.022
Neg logit contributions
aches-0.019
ending-0.017
 achieve-0.017
 accomplished-0.017
gh-0.017
Token and
Token ID290
Feature activation-1.86e-02

Pos logit contributions
vern+0.032
aches+0.032
gh+0.031
 hardly+0.030
ending+0.029
Neg logit contributions
 boy-0.072
 girl-0.071
 Year-0.067
cy-0.064
 extingu-0.063
Token some
Token ID617
Feature activation-1.02e-03

Pos logit contributions
vern+0.083
aches+0.083
earned+0.077
imes+0.076
ending+0.075
Neg logit contributions
 boy-0.075
 girl-0.070
 Year-0.064
 extingu-0.063
 asleep-0.060
Token spark
Token ID9009
Feature activation+1.49e-02

Pos logit contributions
vern+0.002
aches+0.002
earned+0.002
imes+0.002
fters+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 Year-0.002
 extingu-0.001
 asleep-0.001
Tokenly
Token ID306
Feature activation+3.32e-02

Pos logit contributions
 boy+0.028
 girl+0.026
 Year+0.025
 extingu+0.025
 asleep+0.023
Neg logit contributions
aches-0.024
vern-0.022
imes-0.021
ag-0.021
earned-0.021
Token neck
Token ID7393
Feature activation-1.12e-01

Pos logit contributions
 Year+0.059
 boy+0.059
ksh+0.058
 extingu+0.056
 Claus+0.055
Neg logit contributions
aches-0.052
ade-0.047
ons-0.046
imes-0.044
ough-0.043
Tokenl
Token ID75
Feature activation+2.02e-02

Pos logit contributions
aches+0.180
vern+0.178
earned+0.163
imes+0.162
ending+0.160
Neg logit contributions
 boy-0.211
 girl-0.200
 Year-0.185
 extingu-0.182
 asleep-0.174
Tokenaces
Token ID2114
Feature activation-1.62e-01

Pos logit contributions
 boy+0.055
 girl+0.053
 extingu+0.051
 asleep+0.050
 Year+0.050
Neg logit contributions
vern-0.014
aches-0.014
earned-0.012
fters-0.011
iable-0.011
Token and
Token ID290
Feature activation-1.07e-02

Pos logit contributions
vern+0.309
aches+0.307
earned+0.294
fters+0.285
imes+0.283
Neg logit contributions
 boy-0.244
 girl-0.232
 extingu-0.205
 asleep-0.204
 Year-0.194
Token sil
Token ID3313
Feature activation+1.97e-02

Pos logit contributions
aches+0.018
vern+0.017
ons+0.016
imes+0.016
earned+0.016
Neg logit contributions
 boy-0.018
 girl-0.017
 Year-0.017
 extingu-0.017
ksh-0.016
Tokenky
Token ID2584
Feature activation-8.90e-04

Pos logit contributions
 boy+0.021
 girl+0.020
 Year+0.019
 extingu+0.017
cy+0.016
Neg logit contributions
vern-0.047
aches-0.046
imes-0.044
earned-0.043
 achieve-0.043
Token scar
Token ID10153
Feature activation-8.56e-02

Pos logit contributions
aches+0.001
vern+0.001
gh+0.001
ons+0.001
ough+0.001
Neg logit contributions
 boy-0.002
 girl-0.001
 Year-0.001
 extingu-0.001
 asleep-0.001
Tokenves
Token ID1158
Feature activation-8.04e-02

Pos logit contributions
vern+0.083
earned+0.081
aches+0.080
imes+0.073
ending+0.072
Neg logit contributions
 boy-0.202
 girl-0.195
 extingu-0.183
 Year-0.181
 asleep-0.179
Token together
Token ID1978
Feature activation+1.25e-02

Pos logit contributions
aches+0.088
vern+0.086
gh+0.077
earned+0.076
iable+0.075
Neg logit contributions
 boy-0.131
 girl-0.127
 Year-0.120
 extingu-0.116
ksh-0.112
Token.
Token ID13
Feature activation-5.32e-04

Pos logit contributions
 boy+0.021
 girl+0.019
 extingu+0.017
 Year+0.017
 asleep+0.017
Neg logit contributions
vern-0.022
aches-0.022
earned-0.021
imes-0.021
fters-0.021
Token After
Token ID2293
Feature activation-3.24e-02

Pos logit contributions
imes+0.001
vern+0.001
ough+0.001
aches+0.001
earned+0.001
Neg logit contributions
 boy-0.001
 girl-0.001
 extingu-0.001
 Year-0.001
 asleep-0.001
Token a
Token ID257
Feature activation+1.20e-02

Pos logit contributions
aches+0.045
vern+0.044
gh+0.042
ons+0.041
 achieve+0.040
Neg logit contributions
 boy-0.067
 girl-0.065
 extingu-0.061
ksh-0.060
 Year-0.059
Token few
Token ID1178
Feature activation-5.69e-03

Pos logit contributions
 boy+0.021
 girl+0.020
 Year+0.020
 extingu+0.020
 asleep+0.019
Neg logit contributions
vern-0.019
aches-0.018
gh-0.018
fters-0.017
iable-0.017
Token attempts
Token ID6370
Feature activation-1.62e-01

Pos logit contributions
vern+0.009
aches+0.009
earned+0.009
iable+0.009
ending+0.009
Neg logit contributions
 boy-0.010
 girl-0.010
 Year-0.009
 extingu-0.009
 asleep-0.008
Token,
Token ID11
Feature activation-2.04e-02

Pos logit contributions
vern+0.267
aches+0.266
earned+0.245
imes+0.242
ending+0.240
Neg logit contributions
 boy-0.291
 girl-0.277
 Year-0.254
 extingu-0.251
 asleep-0.238
Token they
Token ID484
Feature activation-7.39e-04

Pos logit contributions
aches+0.025
 hardly+0.024
imes+0.023
iable+0.022
ons+0.021
Neg logit contributions
 extingu-0.040
ksh-0.039
 Year-0.039
 boy-0.039
ucks-0.039
Token finally
Token ID3443
Feature activation-2.27e-02

Pos logit contributions
aches+0.001
vern+0.001
iable+0.001
 accomplished+0.001
imes+0.001
Neg logit contributions
 boy-0.001
 girl-0.001
 Year-0.001
 extingu-0.001
 asleep-0.001
Token got
Token ID1392
Feature activation-2.15e-02

Pos logit contributions
vern+0.034
aches+0.033
earned+0.031
fters+0.030
ending+0.030
Neg logit contributions
 boy-0.046
 girl-0.043
 extingu-0.039
 Year-0.038
 asleep-0.038
Token the
Token ID262
Feature activation-1.23e-02

Pos logit contributions
aches+0.035
vern+0.035
imes+0.032
iable+0.032
earned+0.031
Neg logit contributions
 boy-0.039
 girl-0.037
 Year-0.035
 extingu-0.035
ksh-0.032
Token's
Token ID338
Feature activation-9.28e-03

Pos logit contributions
 boy+0.003
 girl+0.003
 Year+0.002
 extingu+0.002
 asleep+0.002
Neg logit contributions
vern-0.003
aches-0.003
earned-0.002
imes-0.002
ending-0.002
Token tie
Token ID9839
Feature activation-5.29e-02

Pos logit contributions
aches+0.013
vern+0.013
earned+0.012
 achieve+0.012
ough+0.012
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.017
 extingu-0.017
 asleep-0.016
Token your
Token ID534
Feature activation-9.00e-03

Pos logit contributions
aches+0.078
vern+0.077
ons+0.072
ag+0.070
iable+0.070
Neg logit contributions
 boy-0.104
 girl-0.101
 cottage-0.092
 extingu-0.092
 Year-0.092
Token sho
Token ID7354
Feature activation-8.70e-02

Pos logit contributions
vern+0.017
aches+0.016
ending+0.015
earned+0.015
imes+0.015
Neg logit contributions
 boy-0.015
 girl-0.014
 Year-0.012
 extingu-0.012
 asleep-0.012
Tokenel
Token ID417
Feature activation-2.48e-03

Pos logit contributions
aches+0.174
vern+0.172
fters+0.165
Days+0.164
 achieve+0.164
Neg logit contributions
 boy-0.117
 girl-0.109
cy-0.107
 Year-0.100
 extingu-0.099
Tokenaces
Token ID2114
Feature activation-1.62e-01

Pos logit contributions
vern+0.002
aches+0.002
fters+0.002
iable+0.002
ending+0.002
Neg logit contributions
 boy-0.006
 girl-0.006
 extingu-0.006
 Year-0.006
 asleep-0.005
Token together
Token ID1978
Feature activation+1.28e-02

Pos logit contributions
vern+0.319
aches+0.318
earned+0.297
imes+0.294
ending+0.291
Neg logit contributions
 boy-0.241
 girl-0.226
 Year-0.202
 extingu-0.200
 asleep-0.187
Token so
Token ID523
Feature activation-3.17e-02

Pos logit contributions
 boy+0.022
 girl+0.021
 extingu+0.019
 Year+0.019
ksh+0.017
Neg logit contributions
aches-0.022
vern-0.022
ough-0.020
imes-0.020
earned-0.020
Token they
Token ID484
Feature activation-2.65e-03

Pos logit contributions
vern+0.055
aches+0.054
earned+0.051
imes+0.050
fters+0.049
Neg logit contributions
 boy-0.055
 girl-0.052
 Year-0.047
 extingu-0.047
 asleep-0.045
Token won
Token ID1839
Feature activation-3.88e-03

Pos logit contributions
aches+0.004
vern+0.004
earned+0.004
iable+0.004
imes+0.004
Neg logit contributions
 boy-0.005
 girl-0.004
 Year-0.004
 extingu-0.004
 asleep-0.004
Token't
Token ID470
Feature activation-6.35e-03

Pos logit contributions
vern+0.004
aches+0.004
earned+0.004
imes+0.004
ending+0.004
Neg logit contributions
 boy-0.009
 girl-0.009
 Year-0.008
 extingu-0.008
 asleep-0.008
Token Its
Token ID6363
Feature activation-9.10e-03

Pos logit contributions
vern+0.024
aches+0.024
ough+0.023
earned+0.022
ag+0.022
Neg logit contributions
 boy-0.027
 girl-0.027
 extingu-0.025
 Year-0.024
 asleep-0.024
Token bright
Token ID6016
Feature activation-5.39e-03

Pos logit contributions
vern+0.018
aches+0.017
earned+0.016
fters+0.016
ending+0.016
Neg logit contributions
 boy-0.015
 girl-0.014
 extingu-0.012
 Year-0.011
 asleep-0.011
Token colors
Token ID7577
Feature activation-7.04e-02

Pos logit contributions
aches+0.010
vern+0.010
earned+0.009
imes+0.009
ag+0.009
Neg logit contributions
 boy-0.008
 girl-0.008
 Year-0.007
 extingu-0.007
 asleep-0.007
Token and
Token ID290
Feature activation-1.23e-02

Pos logit contributions
vern+0.123
aches+0.120
earned+0.114
fters+0.112
imes+0.112
Neg logit contributions
 boy-0.123
 girl-0.116
 extingu-0.102
 Year-0.102
 asleep-0.099
Token l
Token ID300
Feature activation-3.65e-03

Pos logit contributions
aches+0.021
vern+0.020
ons+0.019
gh+0.019
earned+0.019
Neg logit contributions
 boy-0.021
 girl-0.020
 Year-0.019
 extingu-0.019
 asleep-0.018
Tokenaces
Token ID2114
Feature activation-1.61e-01

Pos logit contributions
fters+0.005
vern+0.005
earned+0.005
aches+0.005
iable+0.005
Neg logit contributions
 boy-0.007
 girl-0.007
cy-0.006
 extingu-0.006
 asleep-0.006
Token made
Token ID925
Feature activation+1.22e-02

Pos logit contributions
vern+0.287
aches+0.277
earned+0.270
fters+0.267
imes+0.266
Neg logit contributions
 boy-0.275
 girl-0.259
 asleep-0.225
work-0.223
 extingu-0.219
Token it
Token ID340
Feature activation-1.21e-02

Pos logit contributions
 boy+0.023
 girl+0.022
 extingu+0.022
 Year+0.022
ksh+0.021
Neg logit contributions
aches-0.019
vern-0.018
ag-0.017
ons-0.017
imes-0.016
Token look
Token ID804
Feature activation+2.66e-02

Pos logit contributions
aches+0.022
vern+0.022
earned+0.020
imes+0.020
ending+0.020
Neg logit contributions
 boy-0.020
 girl-0.019
 Year-0.017
 extingu-0.017
 asleep-0.016
Token very
Token ID845
Feature activation-3.60e-02

Pos logit contributions
 boy+0.052
 girl+0.049
 Year+0.047
 extingu+0.046
 asleep+0.043
Neg logit contributions
aches-0.040
vern-0.039
earned-0.036
iable-0.036
gh-0.035
Token nice
Token ID3621
Feature activation-3.77e-02

Pos logit contributions
vern+0.058
aches+0.057
earned+0.052
imes+0.051
iable+0.051
Neg logit contributions
 boy-0.067
 girl-0.064
 Year-0.059
 extingu-0.059
 asleep-0.056
Token brace
Token ID22581
Feature activation-5.51e-02

Pos logit contributions
aches+0.006
 achieve+0.005
vern+0.005
fters+0.005
 expect+0.005
Neg logit contributions
 boy-0.008
 Year-0.007
 girl-0.007
ksh-0.007
cy-0.007
Tokenlets
Token ID5289
Feature activation-1.08e-01

Pos logit contributions
aches+0.089
vern+0.089
earned+0.082
imes+0.080
ending+0.080
Neg logit contributions
 boy-0.102
 girl-0.096
 Year-0.089
 extingu-0.087
 asleep-0.084
Token and
Token ID290
Feature activation-4.74e-03

Pos logit contributions
aches+0.202
vern+0.199
imes+0.182
ag+0.182
gh+0.180
Neg logit contributions
 boy-0.172
 girl-0.162
 Year-0.152
 extingu-0.146
ksh-0.138
Token neck
Token ID7393
Feature activation-1.11e-01

Pos logit contributions
aches+0.008
vern+0.007
ons+0.006
earned+0.006
 achieve+0.006
Neg logit contributions
 boy-0.009
 Year-0.008
 girl-0.008
 asleep-0.008
ksh-0.008
Tokenl
Token ID75
Feature activation+2.06e-02

Pos logit contributions
aches+0.171
vern+0.170
earned+0.155
imes+0.153
gh+0.151
Neg logit contributions
 boy-0.214
 girl-0.204
 Year-0.188
 extingu-0.186
 asleep-0.179
Tokenaces
Token ID2114
Feature activation-1.61e-01

Pos logit contributions
 boy+0.057
 girl+0.054
 extingu+0.052
 asleep+0.052
 Year+0.051
Neg logit contributions
vern-0.014
aches-0.013
earned-0.012
fters-0.011
iable-0.011
Token with
Token ID351
Feature activation+2.34e-02

Pos logit contributions
vern+0.323
aches+0.321
earned+0.306
imes+0.300
fters+0.298
Neg logit contributions
 boy-0.232
 girl-0.217
 extingu-0.190
 Year-0.187
 asleep-0.182
Token copper
Token ID15317
Feature activation+2.42e-02

Pos logit contributions
 boy+0.040
 girl+0.038
 Year+0.036
 extingu+0.035
 asleep+0.033
Neg logit contributions
aches-0.041
vern-0.040
imes-0.037
earned-0.037
ag-0.036
Token.
Token ID13
Feature activation-8.40e-03

Pos logit contributions
 boy+0.042
 girl+0.040
 Year+0.038
 extingu+0.036
ksh+0.034
Neg logit contributions
aches-0.042
vern-0.040
imes-0.038
ons-0.037
earned-0.037
Token They
Token ID1119
Feature activation-1.67e-03

Pos logit contributions
aches+0.012
imes+0.012
ough+0.011
vern+0.011
earned+0.011
Neg logit contributions
 boy-0.015
 girl-0.015
work-0.015
 extingu-0.014
 Year-0.014
Token think
Token ID892
Feature activation-1.20e-02

Pos logit contributions
aches+0.003
vern+0.003
earned+0.002
imes+0.002
iable+0.002
Neg logit contributions
 boy-0.003
 girl-0.003
 Year-0.003
 extingu-0.003
 asleep-0.003
Token.
Token ID13
Feature activation-2.17e-03

Pos logit contributions
 boy+0.021
 girl+0.020
 Year+0.019
 extingu+0.019
ksh+0.018
Neg logit contributions
vern-0.015
aches-0.015
ons-0.014
ending-0.013
iable-0.013
Token There
Token ID1318
Feature activation+6.54e-03

Pos logit contributions
vern+0.004
aches+0.004
earned+0.003
gh+0.003
fters+0.003
Neg logit contributions
 boy-0.004
 girl-0.004
 Year-0.003
 extingu-0.003
 asleep-0.003
Token were
Token ID547
Feature activation+9.18e-03

Pos logit contributions
 boy+0.012
 girl+0.012
 Year+0.011
 extingu+0.011
 asleep+0.010
Neg logit contributions
aches-0.010
vern-0.010
earned-0.009
imes-0.009
gh-0.009
Token neck
Token ID7393
Feature activation-1.08e-01

Pos logit contributions
 boy+0.018
 extingu+0.018
 girl+0.017
 Year+0.017
ksh+0.017
Neg logit contributions
aches-0.013
vern-0.011
ons-0.011
imes-0.011
gh-0.011
Tokenl
Token ID75
Feature activation+2.43e-02

Pos logit contributions
aches+0.156
vern+0.139
ons+0.134
gh+0.128
ade+0.127
Neg logit contributions
 boy-0.227
 girl-0.216
 extingu-0.209
 Year-0.204
ksh-0.198
Tokenaces
Token ID2114
Feature activation-1.61e-01

Pos logit contributions
 boy+0.071
 girl+0.068
 Year+0.064
 extingu+0.064
 asleep+0.061
Neg logit contributions
aches-0.014
vern-0.013
earned-0.011
ending-0.011
imes-0.011
Token and
Token ID290
Feature activation-5.61e-03

Pos logit contributions
aches+0.315
vern+0.313
earned+0.292
ending+0.290
iable+0.289
Neg logit contributions
 boy-0.242
 girl-0.226
 Year-0.208
 extingu-0.204
ksh-0.187
Token rings
Token ID13917
Feature activation-1.95e-02

Pos logit contributions
aches+0.010
vern+0.009
ons+0.009
earned+0.009
gh+0.008
Neg logit contributions
 boy-0.010
 extingu-0.009
 girl-0.009
 Year-0.009
ksh-0.008
Token with
Token ID351
Feature activation+2.88e-02

Pos logit contributions
aches+0.034
vern+0.032
gh+0.030
iable+0.030
ag+0.030
Neg logit contributions
 boy-0.034
 girl-0.032
 Year-0.031
 extingu-0.030
ksh-0.028
Token spark
Token ID9009
Feature activation+2.09e-02

Pos logit contributions
 boy+0.053
 girl+0.050
 Year+0.048
 extingu+0.047
ksh+0.045
Neg logit contributions
aches-0.046
vern-0.044
imes-0.042
ons-0.041
earned-0.041
Tokenles
Token ID829
Feature activation-1.97e-02

Pos logit contributions
 boy+0.039
 girl+0.037
 Year+0.035
 extingu+0.035
 cottage+0.033
Neg logit contributions
aches-0.033
vern-0.030
ag-0.030
ons-0.030
imes-0.029
Token quickly
Token ID2952
Feature activation-9.46e-03

Pos logit contributions
aches+0.009
vern+0.009
ons+0.008
ending+0.008
ade+0.008
Neg logit contributions
 boy-0.012
 girl-0.012
 Year-0.011
 extingu-0.011
 asleep-0.011
Token tied
Token ID8165
Feature activation-3.10e-02

Pos logit contributions
vern+0.018
aches+0.017
earned+0.017
imes+0.016
ag+0.016
Neg logit contributions
 boy-0.015
 girl-0.014
 extingu-0.013
 Year-0.012
 asleep-0.012
Token her
Token ID607
Feature activation-1.61e-02

Pos logit contributions
aches+0.045
vern+0.045
imes+0.042
ons+0.041
gh+0.041
Neg logit contributions
 boy-0.060
 girl-0.058
 Year-0.056
 extingu-0.054
 cottage-0.052
Token sho
Token ID7354
Feature activation-8.19e-02

Pos logit contributions
aches+0.031
vern+0.031
ending+0.029
iable+0.029
earned+0.029
Neg logit contributions
 boy-0.025
 girl-0.024
 asleep-0.020
 extingu-0.019
 t-0.019
Tokenel
Token ID417
Feature activation+3.23e-03

Pos logit contributions
aches+0.183
vern+0.179
 achieve+0.176
fters+0.175
 accomplished+0.170
Neg logit contributions
 boy-0.094
cy-0.092
 girl-0.088
 extingu-0.078
eddy-0.076
Tokenaces
Token ID2114
Feature activation-1.61e-01

Pos logit contributions
 boy+0.007
 girl+0.007
 extingu+0.007
 asleep+0.007
 t+0.006
Neg logit contributions
vern-0.003
aches-0.003
 achieve-0.003
fters-0.003
iable-0.003
Token and
Token ID290
Feature activation-6.98e-03

Pos logit contributions
aches+0.374
vern+0.368
affles+0.360
earned+0.355
fters+0.354
Neg logit contributions
 boy-0.173
 girl-0.160
 asleep-0.138
 extingu-0.128
work-0.119
Token ran
Token ID4966
Feature activation-2.54e-02

Pos logit contributions
vern+0.012
aches+0.012
earned+0.011
imes+0.011
ending+0.011
Neg logit contributions
 boy-0.012
 girl-0.012
 extingu-0.010
 Year-0.010
 asleep-0.010
Token away
Token ID1497
Feature activation-1.19e-03

Pos logit contributions
vern+0.042
aches+0.041
ag+0.039
gh+0.038
earned+0.038
Neg logit contributions
 boy-0.046
 girl-0.043
 Year-0.041
 extingu-0.040
work-0.037
Token from
Token ID422
Feature activation+1.63e-02

Pos logit contributions
vern+0.002
aches+0.002
 achieve+0.002
gh+0.002
ag+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 Year-0.002
ksh-0.002
 extingu-0.002
Token the
Token ID262
Feature activation-3.60e-03

Pos logit contributions
 boy+0.032
 girl+0.031
 extingu+0.029
 Year+0.029
ksh+0.028
Neg logit contributions
aches-0.024
vern-0.022
imes-0.021
fters-0.021
earned-0.021
Token her
Token ID607
Feature activation-2.07e-02

Pos logit contributions
vern+0.080
aches+0.080
earned+0.073
imes+0.072
fters+0.071
Neg logit contributions
 boy-0.091
 girl-0.086
 Year-0.080
 extingu-0.079
 asleep-0.074
Token mum
Token ID25682
Feature activation-2.05e-03

Pos logit contributions
vern+0.036
aches+0.036
earned+0.033
gh+0.032
imes+0.032
Neg logit contributions
 boy-0.036
 girl-0.034
 Year-0.031
 extingu-0.031
 asleep-0.029
Token's
Token ID338
Feature activation-7.42e-03

Pos logit contributions
vern+0.004
aches+0.003
earned+0.003
fters+0.003
imes+0.003
Neg logit contributions
 boy-0.004
 girl-0.004
 extingu-0.003
 Year-0.003
 asleep-0.003
Token shoe
Token ID17292
Feature activation-5.38e-02

Pos logit contributions
vern+0.012
aches+0.012
earned+0.011
ough+0.011
gh+0.011
Neg logit contributions
 boy-0.013
 girl-0.012
 Year-0.012
 extingu-0.011
ksh-0.011
Token l
Token ID300
Feature activation+3.18e-04

Pos logit contributions
vern+0.098
aches+0.097
earned+0.090
imes+0.089
fters+0.089
Neg logit contributions
 boy-0.089
 girl-0.084
 Year-0.074
 extingu-0.074
 asleep-0.073
Tokenaces
Token ID2114
Feature activation-1.60e-01

Pos logit contributions
 boy+0.001
 girl+0.001
 asleep+0.001
 extingu+0.001
work+0.001
Neg logit contributions
aches-0.000
vern-0.000
earned-0.000
 hardly-0.000
iable-0.000
Token together
Token ID1978
Feature activation+1.67e-02

Pos logit contributions
aches+0.314
vern+0.310
earned+0.294
affles+0.292
fters+0.290
Neg logit contributions
 boy-0.230
 girl-0.219
 asleep-0.205
work-0.187
 extingu-0.185
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
 boy+0.025
 girl+0.024
 asleep+0.021
 extingu+0.020
 Year+0.020
Neg logit contributions
vern-0.033
aches-0.032
earned-0.031
fters-0.030
ending-0.030
Token One
Token ID1881
Feature activation+1.16e-02

Pos logit contributions
aches+0.026
vern+0.025
fters+0.023
gh+0.023
ending+0.023
Neg logit contributions
 boy-0.019
 girl-0.017
 Year-0.015
 asleep-0.014
 extingu-0.013
Token day
Token ID1110
Feature activation+2.15e-02

Pos logit contributions
 boy+0.022
 girl+0.021
 Year+0.017
cy+0.017
 asleep+0.016
Neg logit contributions
vern-0.021
aches-0.020
fters-0.019
iable-0.019
imes-0.018
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
 boy+0.032
 girl+0.031
 Year+0.023
 asleep+0.022
 tent+0.021
Neg logit contributions
vern-0.047
aches-0.046
earned-0.043
fters-0.042
ag-0.042
Tokenpped
Token ID1496
Feature activation-2.82e-02

Pos logit contributions
vern+0.002
aches+0.002
earned+0.002
iable+0.002
imes+0.002
Neg logit contributions
 boy-0.006
 girl-0.006
 extingu-0.006
 asleep-0.006
 Year-0.005
Token on
Token ID319
Feature activation-5.57e-02

Pos logit contributions
vern+0.058
aches+0.057
earned+0.054
imes+0.053
ending+0.053
Neg logit contributions
 boy-0.041
 girl-0.038
 extingu-0.033
 Year-0.033
 asleep-0.032
Token her
Token ID607
Feature activation-2.38e-02

Pos logit contributions
vern+0.084
aches+0.084
gh+0.076
earned+0.076
fters+0.075
Neg logit contributions
 boy-0.107
 girl-0.102
 Year-0.095
 extingu-0.094
work-0.090
Token sho
Token ID7354
Feature activation-8.46e-02

Pos logit contributions
vern+0.054
aches+0.052
ending+0.052
imes+0.051
fters+0.050
Neg logit contributions
 boy-0.031
 girl-0.029
 t-0.027
 asleep-0.025
 tent-0.022
Tokenel
Token ID417
Feature activation+3.45e-04

Pos logit contributions
vern+0.197
aches+0.195
 achieve+0.189
fters+0.188
Days+0.187
Neg logit contributions
cy-0.090
 boy-0.085
 girl-0.080
ASH-0.076
ucks-0.072
Tokenaces
Token ID2114
Feature activation-1.60e-01

Pos logit contributions
 boy+0.001
 girl+0.001
 t+0.001
 asleep+0.001
 extingu+0.001
Neg logit contributions
vern-0.000
fters-0.000
 achieve-0.000
iable-0.000
 accomplished-0.000
Token and
Token ID290
Feature activation-1.28e-02

Pos logit contributions
aches+0.451
affles+0.451
vern+0.439
earned+0.432
fters+0.425
Neg logit contributions
 boy-0.098
 girl-0.083
 asleep-0.081
 t-0.060
 extingu-0.045
Token dropped
Token ID5710
Feature activation+8.93e-03

Pos logit contributions
vern+0.024
aches+0.022
earned+0.022
ending+0.021
imes+0.021
Neg logit contributions
 boy-0.022
 girl-0.021
 asleep-0.018
 t-0.018
 extingu-0.017
Token her
Token ID607
Feature activation-2.49e-02

Pos logit contributions
 boy+0.022
 Year+0.021
 girl+0.021
 cottage+0.020
 Claus+0.020
Neg logit contributions
aches-0.008
imes-0.007
vern-0.007
ons-0.007
ag-0.006
Token pencil
Token ID21613
Feature activation-4.69e-02

Pos logit contributions
vern+0.047
aches+0.046
ending+0.044
earned+0.043
fters+0.043
Neg logit contributions
 boy-0.040
 girl-0.038
 asleep-0.032
 Year-0.032
 extingu-0.032
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
vern+0.090
aches+0.090
earned+0.085
fters+0.083
imes+0.083
Neg logit contributions
 boy-0.072
 girl-0.067
 extingu-0.060
 asleep-0.059
 Year-0.056
Token like
Token ID588
Feature activation+1.02e-02

Pos logit contributions
aches+0.028
vern+0.027
imes+0.025
earned+0.025
ons+0.025
Neg logit contributions
 boy-0.026
 girl-0.024
 Year-0.022
 extingu-0.022
 asleep-0.021
Token bright
Token ID6016
Feature activation-4.34e-03

Pos logit contributions
 boy+0.018
 girl+0.017
 extingu+0.016
 Year+0.015
ksh+0.015
Neg logit contributions
aches-0.017
vern-0.017
imes-0.016
ons-0.016
gh-0.015
Token yellow
Token ID7872
Feature activation-2.15e-02

Pos logit contributions
aches+0.008
vern+0.008
ons+0.008
imes+0.008
earned+0.008
Neg logit contributions
 boy-0.007
 girl-0.006
 extingu-0.006
 Year-0.005
ksh-0.005
Token neck
Token ID7393
Feature activation-1.11e-01

Pos logit contributions
aches+0.039
vern+0.038
earned+0.036
imes+0.036
ons+0.036
Neg logit contributions
 boy-0.035
 girl-0.033
 extingu-0.030
 Year-0.030
 asleep-0.028
Tokenl
Token ID75
Feature activation+2.02e-02

Pos logit contributions
aches+0.195
vern+0.194
earned+0.180
imes+0.177
ending+0.176
Neg logit contributions
 boy-0.189
 girl-0.179
 Year-0.162
 extingu-0.161
 asleep-0.153
Tokenaces
Token ID2114
Feature activation-1.60e-01

Pos logit contributions
 boy+0.037
 girl+0.036
 Year+0.033
 extingu+0.033
 asleep+0.032
Neg logit contributions
vern-0.032
aches-0.032
earned-0.029
iable-0.029
fters-0.029
Token and
Token ID290
Feature activation-1.27e-02

Pos logit contributions
vern+0.327
aches+0.324
earned+0.310
gh+0.303
fters+0.303
Neg logit contributions
 boy-0.217
 girl-0.206
 asleep-0.183
 extingu-0.175
work-0.174
Token flower
Token ID15061
Feature activation-3.53e-03

Pos logit contributions
aches+0.022
vern+0.020
imes+0.019
earned+0.019
ons+0.019
Neg logit contributions
 boy-0.022
 girl-0.020
 extingu-0.020
 Year-0.020
work-0.018
Token crown
Token ID12389
Feature activation-1.15e-02

Pos logit contributions
aches+0.006
vern+0.006
imes+0.006
earned+0.005
ons+0.005
Neg logit contributions
 boy-0.006
 girl-0.006
 Year-0.005
 extingu-0.005
 asleep-0.005
Tokens
Token ID82
Feature activation-7.36e-03

Pos logit contributions
vern+0.020
aches+0.020
earned+0.019
imes+0.018
ending+0.018
Neg logit contributions
 boy-0.020
 girl-0.019
 Year-0.017
 extingu-0.017
 asleep-0.016
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
aches+0.012
vern+0.012
imes+0.011
gh+0.011
earned+0.010
Neg logit contributions
 boy-0.014
 girl-0.013
 Year-0.012
 extingu-0.012
ksh-0.011
Token her
Token ID607
Feature activation-2.35e-02

Pos logit contributions
vern+0.032
aches+0.031
earned+0.030
ending+0.029
imes+0.028
Neg logit contributions
 boy-0.037
 girl-0.036
 Year-0.032
 asleep-0.032
 extingu-0.030
Token to
Token ID284
Feature activation-1.16e-02

Pos logit contributions
aches+0.049
vern+0.048
iable+0.046
imes+0.046
fters+0.046
Neg logit contributions
 boy-0.035
 girl-0.034
 asleep-0.028
 t-0.027
 Year-0.025
Token tie
Token ID9839
Feature activation-5.03e-02

Pos logit contributions
imes+0.021
earned+0.020
vern+0.020
affles+0.020
ending+0.020
Neg logit contributions
 boy-0.018
 girl-0.018
 t-0.016
 Sn-0.014
 duck-0.014
Token the
Token ID262
Feature activation-9.27e-03

Pos logit contributions
vern+0.089
aches+0.087
earned+0.083
ending+0.082
imes+0.081
Neg logit contributions
 boy-0.085
 girl-0.081
 asleep-0.071
 extingu-0.070
 Year-0.068
Token l
Token ID300
Feature activation-3.50e-04

Pos logit contributions
aches+0.017
vern+0.017
earned+0.015
fters+0.015
imes+0.015
Neg logit contributions
 boy-0.015
 girl-0.014
 Year-0.013
 extingu-0.013
 asleep-0.012
Tokenaces
Token ID2114
Feature activation-1.59e-01

Pos logit contributions
iable+0.000
 achieve+0.000
vern+0.000
aches+0.000
earned+0.000
Neg logit contributions
 girl-0.001
 boy-0.001
 asleep-0.001
 tent-0.001
 te-0.001
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
affles+0.333
aches+0.327
vern+0.319
fters+0.315
earned+0.312
Neg logit contributions
 boy-0.210
 girl-0.198
 asleep-0.181
work-0.158
 t-0.155
Token She
Token ID1375
Feature activation-1.61e-02

Pos logit contributions
vern+0.028
aches+0.027
earned+0.025
fters+0.025
ending+0.025
Neg logit contributions
 boy-0.024
 girl-0.023
 Year-0.019
 asleep-0.019
 extingu-0.018
Token thought
Token ID1807
Feature activation-5.33e-03

Pos logit contributions
vern+0.029
aches+0.028
earned+0.026
imes+0.026
ending+0.026
Neg logit contributions
 boy-0.028
 girl-0.027
 Year-0.023
 extingu-0.023
 asleep-0.022
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
vern+0.010
earned+0.010
aches+0.010
iable+0.009
 achieve+0.009
Neg logit contributions
 boy-0.008
 girl-0.008
 asleep-0.008
 t-0.007
 de-0.007
Token thought
Token ID1807
Feature activation-6.34e-03

Pos logit contributions
vern+0.022
aches+0.021
earned+0.020
imes+0.020
ending+0.020
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.015
 asleep-0.015
Token to
Token ID284
Feature activation-8.70e-03

Pos logit contributions
vern+0.124
aches+0.122
earned+0.114
imes+0.112
fters+0.112
Neg logit contributions
 boy-0.120
 girl-0.114
 extingu-0.102
 Year-0.102
 asleep-0.099
Token your
Token ID534
Feature activation+1.81e-04

Pos logit contributions
vern+0.014
aches+0.013
earned+0.012
imes+0.012
ending+0.012
Neg logit contributions
 boy-0.016
 girl-0.016
 Year-0.014
 extingu-0.014
 asleep-0.014
Token feet
Token ID3625
Feature activation-9.02e-02

Pos logit contributions
 boy+0.000
 extingu+0.000
 girl+0.000
 Year+0.000
work+0.000
Neg logit contributions
aches-0.000
vern-0.000
gh-0.000
earned-0.000
ough-0.000
Token with
Token ID351
Feature activation+2.94e-02

Pos logit contributions
vern+0.162
aches+0.162
earned+0.150
imes+0.148
iable+0.147
Neg logit contributions
 boy-0.149
 girl-0.141
 Year-0.128
 extingu-0.126
 asleep-0.119
Token l
Token ID300
Feature activation+4.13e-03

Pos logit contributions
 boy+0.053
 girl+0.051
 Year+0.046
 extingu+0.046
 asleep+0.044
Neg logit contributions
vern-0.048
aches-0.048
earned-0.045
imes-0.044
ending-0.043
Tokenaces
Token ID2114
Feature activation-1.59e-01

Pos logit contributions
 boy+0.010
 girl+0.009
 asleep+0.009
 extingu+0.009
 Year+0.009
Neg logit contributions
aches-0.003
iable-0.003
earned-0.003
vern-0.003
gh-0.003
Token."
Token ID526
Feature activation+2.08e-02

Pos logit contributions
aches+0.304
vern+0.303
earned+0.286
imes+0.282
fters+0.282
Neg logit contributions
 boy-0.239
 girl-0.225
 asleep-0.199
 extingu-0.195
 Year-0.193
Token Her
Token ID2332
Feature activation-1.66e-03

Pos logit contributions
 boy+0.041
 girl+0.039
 extingu+0.038
 Year+0.037
work+0.036
Neg logit contributions
vern-0.026
ons-0.025
aches-0.025
imes-0.025
earned-0.024
Token son
Token ID3367
Feature activation+1.55e-02

Pos logit contributions
gh+0.002
vern+0.002
 hardly+0.002
ittens+0.002
odi+0.002
Neg logit contributions
 Year-0.003
 extingu-0.003
ucks-0.003
ksh-0.003
 hyd-0.003
Token nodded
Token ID14464
Feature activation+2.61e-02

Pos logit contributions
 boy+0.025
 girl+0.025
 Year+0.024
 extingu+0.024
 asleep+0.023
Neg logit contributions
aches-0.027
vern-0.025
gh-0.024
 hardly-0.024
ending-0.024
Token and
Token ID290
Feature activation-2.59e-03

Pos logit contributions
 boy+0.047
 Year+0.047
 girl+0.044
ksh+0.043
 tent+0.042
Neg logit contributions
gh-0.037
Her-0.036
vern-0.036
ag-0.035
 hardly-0.033
Token are
Token ID389
Feature activation+4.22e-02

Pos logit contributions
vern+0.013
aches+0.012
earned+0.012
imes+0.011
fters+0.011
Neg logit contributions
 boy-0.015
 girl-0.014
 extingu-0.012
 Year-0.012
 asleep-0.012
Token a
Token ID257
Feature activation+2.32e-02

Pos logit contributions
 boy+0.074
 girl+0.070
 Year+0.065
 extingu+0.065
 asleep+0.060
Neg logit contributions
vern-0.072
aches-0.072
iable-0.064
fters-0.064
earned-0.064
Token good
Token ID922
Feature activation-2.94e-02

Pos logit contributions
 Year+0.045
ksh+0.044
 boy+0.044
 extingu+0.044
ucks+0.043
Neg logit contributions
vern-0.030
gh-0.025
aches-0.025
 capable-0.024
 supposed-0.024
Token friend
Token ID1545
Feature activation-1.60e-02

Pos logit contributions
vern+0.049
ending+0.046
aches+0.046
ough+0.046
ag+0.045
Neg logit contributions
ksh-0.045
 Year-0.043
fly-0.039
work-0.039
ASH-0.038
Token for
Token ID329
Feature activation-1.26e-02

Pos logit contributions
vern+0.028
aches+0.027
earned+0.026
imes+0.025
ending+0.025
Neg logit contributions
 boy-0.027
 girl-0.026
 Year-0.024
 extingu-0.024
 asleep-0.022
Token whist
Token ID32262
Feature activation+8.29e-02

Pos logit contributions
aches+0.019
vern+0.018
fters+0.017
iable+0.017
gh+0.017
Neg logit contributions
 boy-0.025
 girl-0.024
 extingu-0.023
 Year-0.022
cy-0.021
Tokenling
Token ID1359
Feature activation+1.60e-02

Pos logit contributions
 boy+0.127
 girl+0.119
 Year+0.106
 extingu+0.106
 asleep+0.100
Neg logit contributions
vern-0.161
aches-0.161
earned-0.150
imes-0.148
ending-0.147
Token."
Token ID526
Feature activation+1.87e-02

Pos logit contributions
 boy+0.029
 girl+0.028
 Year+0.027
 extingu+0.026
 cottage+0.025
Neg logit contributions
aches-0.025
vern-0.025
ag-0.023
gh-0.023
earned-0.023
Token
Token ID198
Feature activation-2.22e-02

Pos logit contributions
 boy+0.032
 girl+0.031
 Year+0.028
 extingu+0.028
 asleep+0.026
Neg logit contributions
vern-0.033
aches-0.033
earned-0.030
imes-0.030
ending-0.030
Token
Token ID198
Feature activation-2.09e-02

Pos logit contributions
aches+0.042
vern+0.042
earned+0.040
iable+0.039
fters+0.039
Neg logit contributions
 boy-0.036
 girl-0.033
 Year-0.029
 extingu-0.029
 asleep-0.028
TokenThey
Token ID2990
Feature activation+1.09e-02

Pos logit contributions
vern+0.027
aches+0.027
imes+0.026
fters+0.025
earned+0.025
Neg logit contributions
 boy-0.047
 girl-0.044
 Year-0.039
 extingu-0.039
 duck-0.037
Token We
Token ID775
Feature activation+2.37e-02

Pos logit contributions
 boy+0.031
 girl+0.031
 asleep+0.029
maid+0.028
 cottage+0.027
Neg logit contributions
ough-0.035
earned-0.035
vern-0.034
imes-0.033
adders-0.032
Token want
Token ID765
Feature activation-4.50e-03

Pos logit contributions
 boy+0.046
 girl+0.044
 Year+0.041
 extingu+0.040
 asleep+0.039
Neg logit contributions
vern-0.036
aches-0.036
earned-0.033
imes-0.032
fters-0.032
Token to
Token ID284
Feature activation-5.22e-04

Pos logit contributions
vern+0.005
aches+0.005
earned+0.005
ons+0.004
ag+0.004
Neg logit contributions
 boy-0.010
 girl-0.010
 extingu-0.009
 Year-0.009
ksh-0.009
Token see
Token ID766
Feature activation-3.32e-02

Pos logit contributions
aches+0.001
vern+0.001
earned+0.001
gh+0.001
fters+0.001
Neg logit contributions
 boy-0.001
 girl-0.001
 Year-0.001
 extingu-0.001
 asleep-0.001
Token the
Token ID262
Feature activation+6.58e-03

Pos logit contributions
aches+0.045
vern+0.044
iable+0.041
ons+0.041
ag+0.039
Neg logit contributions
 boy-0.066
 girl-0.063
 extingu-0.061
ksh-0.060
 Year-0.059
Token movie
Token ID3807
Feature activation+8.18e-02

Pos logit contributions
 extingu+0.011
ksh+0.011
cy+0.010
ucks+0.010
ipt+0.010
Neg logit contributions
aches-0.011
vern-0.010
fters-0.010
 achieve-0.009
iable-0.009
Token."
Token ID526
Feature activation+2.52e-02

Pos logit contributions
 extingu+0.140
 boy+0.137
 girl+0.136
 Year+0.130
ksh+0.125
Neg logit contributions
aches-0.129
vern-0.123
 achieve-0.122
iable-0.117
 accomplished-0.117
Token
Token ID198
Feature activation-1.46e-02

Pos logit contributions
 boy+0.045
 girl+0.044
 extingu+0.042
 Year+0.041
work+0.040
Neg logit contributions
vern-0.038
aches-0.037
imes-0.036
earned-0.034
 achieve-0.034
Token
Token ID198
Feature activation-1.23e-02

Pos logit contributions
vern+0.026
aches+0.026
earned+0.024
imes+0.024
ending+0.023
Neg logit contributions
 boy-0.025
 girl-0.023
 Year-0.021
 extingu-0.021
 asleep-0.020
TokenMom
Token ID29252
Feature activation+1.59e-02

Pos logit contributions
vern+0.016
aches+0.015
 achieve+0.013
earned+0.013
fters+0.013
Neg logit contributions
 boy-0.027
 girl-0.026
 extingu-0.024
 asleep-0.024
 Year-0.024
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
 boy+0.025
 girl+0.024
ksh+0.023
 Year+0.023
 hyd+0.023
Neg logit contributions
ons-0.026
aches-0.025
vern-0.025
old-0.024
ag-0.024
Token "
Token ID366
Feature activation+2.80e-02

Pos logit contributions
 boy+0.013
 girl+0.012
 extingu+0.012
 Year+0.012
 cottage+0.011
Neg logit contributions
aches-0.013
vern-0.013
 achieve-0.012
imes-0.012
fters-0.012
Tokendog
Token ID9703
Feature activation+2.58e-02

Pos logit contributions
 boy+0.054
 girl+0.052
 extingu+0.049
 Year+0.048
 asleep+0.046
Neg logit contributions
aches-0.042
vern-0.041
earned-0.039
imes-0.038
ending-0.038
Token"
Token ID1
Feature activation-1.60e-03

Pos logit contributions
 boy+0.051
 girl+0.049
 Year+0.045
 extingu+0.045
 asleep+0.043
Neg logit contributions
aches-0.038
vern-0.038
earned-0.035
imes-0.034
ending-0.034
Token and
Token ID290
Feature activation+5.65e-03

Pos logit contributions
aches+0.003
vern+0.003
imes+0.003
iable+0.003
earned+0.003
Neg logit contributions
 boy-0.003
 girl-0.002
 extingu-0.002
 Year-0.002
 asleep-0.002
Token "
Token ID366
Feature activation+2.68e-02

Pos logit contributions
 boy+0.009
 girl+0.009
 extingu+0.008
 Year+0.008
 cottage+0.008
Neg logit contributions
aches-0.010
vern-0.010
imes-0.009
fters-0.009
earned-0.009
Tokenstar
Token ID7364
Feature activation+7.20e-02

Pos logit contributions
 boy+0.052
 girl+0.049
 extingu+0.047
 Year+0.046
 asleep+0.045
Neg logit contributions
aches-0.040
vern-0.038
earned-0.037
ough-0.036
imes-0.036
Token"
Token ID1
Feature activation-3.36e-03

Pos logit contributions
 boy+0.146
 girl+0.140
 extingu+0.132
 Year+0.131
 asleep+0.129
Neg logit contributions
aches-0.099
vern-0.097
imes-0.090
ough-0.089
earned-0.089
Token and
Token ID290
Feature activation+2.55e-03

Pos logit contributions
aches+0.006
vern+0.006
imes+0.006
iable+0.006
earned+0.005
Neg logit contributions
 boy-0.005
 extingu-0.005
 Year-0.005
 girl-0.005
 cottage-0.004
Token "
Token ID366
Feature activation+2.50e-02

Pos logit contributions
 boy+0.005
 girl+0.004
 extingu+0.004
 Year+0.004
 cottage+0.004
Neg logit contributions
aches-0.004
 achieve-0.004
fters-0.004
vern-0.004
ough-0.004
Tokencake
Token ID30560
Feature activation+6.43e-02

Pos logit contributions
 boy+0.049
 girl+0.046
 extingu+0.044
 Year+0.043
 asleep+0.042
Neg logit contributions
aches-0.037
vern-0.036
earned-0.034
imes-0.034
ending-0.034
Token".
Token ID1911
Feature activation+1.62e-02

Pos logit contributions
 boy+0.120
 girl+0.114
 extingu+0.106
 Year+0.106
 asleep+0.102
Neg logit contributions
aches-0.102
vern-0.099
imes-0.091
earned-0.091
iable-0.091
Token care
Token ID1337
Feature activation-6.57e-02

Pos logit contributions
aches+0.006
vern+0.006
ons+0.006
gh+0.006
ag+0.006
Neg logit contributions
 boy-0.009
 extingu-0.008
 girl-0.008
 Year-0.008
ksh-0.008
Token of
Token ID286
Feature activation+2.88e-02

Pos logit contributions
aches+0.072
vern+0.071
earned+0.064
fters+0.062
iable+0.062
Neg logit contributions
 boy-0.156
 girl-0.150
 extingu-0.138
 Year-0.137
 asleep-0.135
Token it
Token ID340
Feature activation-1.62e-02

Pos logit contributions
 boy+0.057
 girl+0.054
 extingu+0.052
 Year+0.050
ksh+0.049
Neg logit contributions
aches-0.043
vern-0.042
iable-0.038
ons-0.038
gh-0.038
Token.
Token ID13
Feature activation+4.35e-03

Pos logit contributions
aches+0.027
vern+0.026
iable+0.024
ag+0.024
gh+0.024
Neg logit contributions
 boy-0.029
 girl-0.028
 extingu-0.026
 Year-0.026
 cottage-0.024
Token Happy
Token ID14628
Feature activation+6.46e-02

Pos logit contributions
 boy+0.008
 girl+0.007
 extingu+0.007
 Year+0.007
 asleep+0.007
Neg logit contributions
vern-0.007
aches-0.007
earned-0.007
imes-0.007
ough-0.007
Token birthday
Token ID10955
Feature activation+7.55e-02

Pos logit contributions
 extingu+0.120
ksh+0.114
 boy+0.108
 grizz+0.108
 polar+0.106
Neg logit contributions
aches-0.095
gh-0.089
 achieve-0.089
vern-0.088
ough-0.084
Token,
Token ID11
Feature activation-8.81e-03

Pos logit contributions
 extingu+0.155
 boy+0.149
ksh+0.148
 Year+0.144
 cottage+0.142
Neg logit contributions
aches-0.090
vern-0.084
ons-0.084
gh-0.083
imes-0.078
Token sweet
Token ID6029
Feature activation-4.45e-03

Pos logit contributions
aches+0.011
 achieve+0.011
vern+0.010
 hardly+0.010
imes+0.010
Neg logit contributions
 extingu-0.018
ksh-0.017
ASH-0.017
 boy-0.016
 Year-0.016
Tokenie
Token ID494
Feature activation-1.79e-02

Pos logit contributions
aches+0.005
ons+0.005
ade+0.005
affles+0.004
isi+0.004
Neg logit contributions
 extingu-0.010
ksh-0.009
ASH-0.009
ses-0.009
 hyd-0.009
Token."
Token ID526
Feature activation+1.16e-02

Pos logit contributions
aches+0.026
ons+0.023
vern+0.023
 accomplished+0.023
 achieve+0.022
Neg logit contributions
 extingu-0.035
 boy-0.033
ksh-0.033
 girl-0.031
 Year-0.031
Token Mom
Token ID11254
Feature activation+1.71e-02

Pos logit contributions
 extingu+0.021
ksh+0.020
 boy+0.020
 Year+0.020
 girl+0.019
Neg logit contributions
vern-0.015
Her-0.015
imes-0.014
ons-0.014
aches-0.014
Token.
Token ID13
Feature activation+5.92e-03

Pos logit contributions
 boy+0.048
 girl+0.045
 Year+0.043
 extingu+0.041
 asleep+0.040
Neg logit contributions
aches-0.041
vern-0.041
imes-0.038
gh-0.037
earned-0.037
Token John
Token ID1757
Feature activation+1.80e-02

Pos logit contributions
 boy+0.012
 girl+0.011
 extingu+0.011
work+0.011
 Year+0.010
Neg logit contributions
vern-0.008
imes-0.007
earned-0.007
ough-0.007
odi-0.007
Token said
Token ID531
Feature activation+6.26e-03

Pos logit contributions
 boy+0.033
 extingu+0.033
 Year+0.033
 girl+0.032
 asleep+0.030
Neg logit contributions
aches-0.026
ending-0.024
iable-0.024
vern-0.023
 hardly-0.023
Token,
Token ID11
Feature activation-3.80e-03

Pos logit contributions
 boy+0.012
 girl+0.011
 Year+0.011
 extingu+0.010
 asleep+0.010
Neg logit contributions
vern-0.010
aches-0.010
gh-0.009
earned-0.009
imes-0.009
Token �
Token ID6184
Feature activation+4.81e-02

Pos logit contributions
 hardly+0.005
vern+0.005
gh+0.005
ending+0.004
aches+0.004
Neg logit contributions
 boy-0.007
 Year-0.007
cy-0.007
 girl-0.007
 extingu-0.007
Token�
Token ID95
Feature activation+8.98e-02

Pos logit contributions
 boy+0.089
 girl+0.084
 Year+0.078
 extingu+0.077
 asleep+0.073
Neg logit contributions
aches-0.077
vern-0.077
earned-0.071
imes-0.070
fters-0.069
Token€
Token ID26391
Feature activation-2.09e-02

Pos logit contributions
 boy+0.173
 girl+0.163
 Year+0.156
 extingu+0.151
ksh+0.145
Neg logit contributions
aches-0.141
vern-0.136
imes-0.128
ons-0.121
earned-0.121
Token�
Token ID129
Feature activation+3.63e-02

Pos logit contributions
vern+0.033
aches+0.033
earned+0.030
imes+0.030
fters+0.030
Neg logit contributions
 boy-0.039
 girl-0.037
 Year-0.034
 extingu-0.034
 asleep-0.032
Token�
Token ID241
Feature activation+2.14e-03

Pos logit contributions
 boy+0.068
 Year+0.065
 girl+0.063
ksh+0.062
 extingu+0.059
Neg logit contributions
vern-0.051
aches-0.051
ons-0.049
imes-0.048
earned-0.047
TokenLet
Token ID5756
Feature activation+1.52e-02

Pos logit contributions
 boy+0.004
 girl+0.004
 Year+0.003
 extingu+0.003
 asleep+0.003
Neg logit contributions
vern-0.003
aches-0.003
earned-0.003
ending-0.003
gh-0.003
Tokenâ
Token ID22940
Feature activation+6.97e-02

Pos logit contributions
 boy+0.029
 girl+0.027
 Year+0.024
 extingu+0.024
 asleep+0.022
Neg logit contributions
vern-0.025
aches-0.025
imes-0.023
earned-0.022
fters-0.022
Token appeared
Token ID4120
Feature activation+2.81e-02

Pos logit contributions
 boy+0.069
 girl+0.067
ksh+0.066
 extingu+0.065
 Year+0.065
Neg logit contributions
aches-0.062
ons-0.057
ending-0.057
vern-0.057
 accomplished-0.056
Token near
Token ID1474
Feature activation-2.18e-02

Pos logit contributions
 boy+0.048
 girl+0.044
 Year+0.043
 extingu+0.040
ksh+0.039
Neg logit contributions
vern-0.049
aches-0.047
gh-0.045
ending-0.044
ag-0.044
Token the
Token ID262
Feature activation-3.31e-03

Pos logit contributions
aches+0.023
vern+0.023
ons+0.022
imes+0.021
gh+0.021
Neg logit contributions
 boy-0.047
ksh-0.045
 girl-0.045
 Year-0.043
 extingu-0.043
Token island
Token ID7022
Feature activation+4.03e-02

Pos logit contributions
 accomplished+0.004
 amazing+0.004
aches+0.004
 extraordinary+0.004
 belong+0.004
Neg logit contributions
ksh-0.006
ucks-0.006
 extingu-0.006
 asleep-0.006
 Lee-0.005
Token.
Token ID13
Feature activation+1.10e-03

Pos logit contributions
 boy+0.074
 girl+0.072
 extingu+0.071
ksh+0.071
 Year+0.070
Neg logit contributions
aches-0.062
vern-0.057
 achieve-0.056
 accomplished-0.054
ons-0.054
Token Out
Token ID3806
Feature activation+2.20e-02

Pos logit contributions
 boy+0.002
 girl+0.002
 Year+0.002
 extingu+0.002
maid+0.002
Neg logit contributions
earned-0.001
imes-0.001
ough-0.001
vern-0.001
 hardly-0.001
Token stepped
Token ID10764
Feature activation+3.25e-02

Pos logit contributions
 boy+0.047
 girl+0.044
 Year+0.042
 extingu+0.041
ksh+0.040
Neg logit contributions
vern-0.028
aches-0.028
ending-0.026
ons-0.026
earned-0.025
Token a
Token ID257
Feature activation+1.79e-02

Pos logit contributions
 boy+0.058
 girl+0.054
 Year+0.050
 extingu+0.047
ksh+0.046
Neg logit contributions
vern-0.055
imes-0.053
aches-0.053
ag-0.051
ough-0.050
Token tall
Token ID7331
Feature activation-3.44e-02

Pos logit contributions
ucks+0.035
ASH+0.034
ksh+0.034
 Year+0.034
cy+0.033
Neg logit contributions
vern-0.024
aches-0.023
 achieve-0.022
fters-0.021
 else-0.021
Token and
Token ID290
Feature activation-3.04e-03

Pos logit contributions
aches+0.054
ons+0.046
fters+0.045
ade+0.044
 expect+0.044
Neg logit contributions
ksh-0.065
ucks-0.060
 Sn-0.057
 asleep-0.056
ASH-0.056
Token wise
Token ID10787
Feature activation-1.65e-02

Pos logit contributions
 accomplished+0.004
aches+0.004
vern+0.003
iable+0.003
 else+0.003
Neg logit contributions
 Year-0.006
 extingu-0.006
ucks-0.006
maid-0.006
ASH-0.006
Token
Token ID198
Feature activation-1.90e-02

Pos logit contributions
vern+0.019
aches+0.019
earned+0.018
imes+0.018
fters+0.018
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.016
 asleep-0.015
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
aches+0.034
vern+0.034
earned+0.032
imes+0.031
iable+0.031
Neg logit contributions
 boy-0.032
 girl-0.030
 Year-0.027
 extingu-0.026
 asleep-0.025
TokenThe
Token ID464
Feature activation+1.13e-02

Pos logit contributions
aches+0.018
vern+0.018
earned+0.016
imes+0.016
ag+0.016
Neg logit contributions
 boy-0.037
 girl-0.035
 Year-0.033
 extingu-0.031
 asleep-0.031
Token little
Token ID1310
Feature activation+7.09e-02

Pos logit contributions
ucks+0.022
ksh+0.022
 extingu+0.021
 asleep+0.020
ASH+0.019
Neg logit contributions
Days-0.016
aches-0.016
vern-0.015
isy-0.014
Every-0.014
Token girl
Token ID2576
Feature activation+4.38e-02

Pos logit contributions
ksh+0.088
ucks+0.079
 extingu+0.079
 projector+0.073
 Claus+0.073
Neg logit contributions
aches-0.128
 belong-0.126
Every-0.125
earned-0.122
ade-0.120
Token was
Token ID373
Feature activation+1.37e-02

Pos logit contributions
 boy+0.078
 extingu+0.076
 girl+0.075
 Year+0.071
ksh+0.070
Neg logit contributions
aches-0.067
vern-0.063
ons-0.062
 hardly-0.062
 achieve-0.062
Token sad
Token ID6507
Feature activation+9.96e-03

Pos logit contributions
 boy+0.029
 girl+0.028
 extingu+0.028
 Year+0.027
ksh+0.026
Neg logit contributions
aches-0.018
vern-0.017
 hardly-0.016
 accomplished-0.016
 supposed-0.016
Token when
Token ID618
Feature activation+7.03e-03

Pos logit contributions
 Year+0.019
 boy+0.019
 girl+0.018
 extingu+0.018
ksh+0.018
Neg logit contributions
vern-0.013
aches-0.013
ending-0.012
 achieve-0.012
iable-0.012
Token it
Token ID340
Feature activation+4.72e-03

Pos logit contributions
 boy+0.017
 girl+0.016
 extingu+0.016
 Year+0.015
ksh+0.015
Neg logit contributions
aches-0.007
vern-0.007
earned-0.006
gh-0.006
imes-0.006
Token was
Token ID373
Feature activation+1.24e-02

Pos logit contributions
 extingu+0.008
 boy+0.008
 girl+0.008
 Year+0.008
ksh+0.007
Neg logit contributions
aches-0.007
 accomplished-0.007
gh-0.007
 achieved-0.007
 achieve-0.007
Token time
Token ID640
Feature activation+6.15e-03

Pos logit contributions
 boy+0.030
 girl+0.029
 extingu+0.027
 Year+0.027
ksh+0.026
Neg logit contributions
aches-0.014
vern-0.013
ag-0.012
gh-0.012
 accomplished-0.012
Token Then
Token ID3244
Feature activation-3.36e-02

Pos logit contributions
vern+0.024
aches+0.023
earned+0.022
imes+0.022
ough+0.022
Neg logit contributions
 boy-0.021
 girl-0.021
 Year-0.019
 extingu-0.018
 asleep-0.018
Token,
Token ID11
Feature activation-2.21e-02

Pos logit contributions
vern+0.065
aches+0.063
fters+0.059
earned+0.059
imes+0.059
Neg logit contributions
 boy-0.056
 girl-0.052
 Year-0.044
 extingu-0.044
 duck-0.042
Token Tim
Token ID5045
Feature activation-4.70e-02

Pos logit contributions
vern+0.039
aches+0.039
earned+0.036
imes+0.036
ending+0.035
Neg logit contributions
 boy-0.038
 girl-0.036
 Year-0.032
 extingu-0.032
 asleep-0.030
Token saw
Token ID2497
Feature activation-1.67e-02

Pos logit contributions
aches+0.075
vern+0.074
earned+0.069
iable+0.068
gh+0.068
Neg logit contributions
 boy-0.084
 girl-0.080
 extingu-0.077
 Year-0.076
 asleep-0.071
Token a
Token ID257
Feature activation+1.06e-02

Pos logit contributions
vern+0.030
aches+0.029
earned+0.028
fters+0.027
ending+0.027
Neg logit contributions
 boy-0.029
 girl-0.027
 extingu-0.025
 Year-0.024
 asleep-0.023
Token man
Token ID582
Feature activation+5.15e-02

Pos logit contributions
 Year+0.021
ksh+0.021
work+0.020
ucks+0.020
ASH+0.019
Neg logit contributions
vern-0.015
aches-0.013
ade-0.013
gh-0.013
 achieve-0.013
Token with
Token ID351
Feature activation+2.24e-02

Pos logit contributions
 boy+0.089
 girl+0.086
ksh+0.085
 Year+0.082
 extingu+0.079
Neg logit contributions
aches-0.079
ag-0.079
ons-0.078
vern-0.077
 achieve-0.077
Token a
Token ID257
Feature activation+1.09e-02

Pos logit contributions
 boy+0.036
 girl+0.034
 Year+0.032
 extingu+0.031
ksh+0.029
Neg logit contributions
vern-0.041
aches-0.040
earned-0.038
gh-0.037
imes-0.037
Token club
Token ID3430
Feature activation-1.41e-02

Pos logit contributions
 Year+0.019
 boy+0.018
ksh+0.018
 girl+0.018
 extingu+0.017
Neg logit contributions
vern-0.018
aches-0.017
gh-0.016
earned-0.015
iable-0.015
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
vern+0.024
aches+0.023
earned+0.022
ag+0.022
gh+0.021
Neg logit contributions
 boy-0.024
 girl-0.023
 Year-0.022
 extingu-0.021
ksh-0.021
Token He
Token ID679
Feature activation-4.44e-03

Pos logit contributions
vern+0.019
aches+0.019
earned+0.018
imes+0.018
ending+0.017
Neg logit contributions
 boy-0.021
 girl-0.020
 Year-0.018
 extingu-0.018
 asleep-0.017
Token To
Token ID1675
Feature activation+5.44e-03

Pos logit contributions
vern+0.012
aches+0.012
earned+0.011
imes+0.011
ending+0.011
Neg logit contributions
 boy-0.016
 girl-0.015
 extingu-0.014
 Year-0.014
 asleep-0.013
Token her
Token ID607
Feature activation-2.22e-02

Pos logit contributions
 boy+0.009
 girl+0.009
 t+0.008
 extingu+0.008
 Year+0.007
Neg logit contributions
vern-0.010
ending-0.010
earned-0.009
imes-0.009
affles-0.009
Token surprise
Token ID5975
Feature activation+3.43e-02

Pos logit contributions
vern+0.044
aches+0.044
earned+0.042
ending+0.041
gh+0.041
Neg logit contributions
 boy-0.032
 girl-0.030
 Year-0.027
 extingu-0.027
 asleep-0.026
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
 boy+0.053
 girl+0.050
 Year+0.040
 asleep+0.039
 tent+0.039
Neg logit contributions
vern-0.070
aches-0.068
earned-0.067
ending-0.065
fters-0.064
Token the
Token ID262
Feature activation-1.09e-02

Pos logit contributions
aches+0.022
vern+0.020
ons+0.019
imes+0.018
earned+0.018
Neg logit contributions
 boy-0.041
 extingu-0.041
 Year-0.041
ksh-0.040
 girl-0.039
Token chest
Token ID7721
Feature activation+2.40e-03

Pos logit contributions
vern+0.020
 accomplished+0.019
earned+0.019
aches+0.019
 expect+0.019
Neg logit contributions
 extingu-0.015
ksh-0.014
 Year-0.014
work-0.014
cy-0.013
Token was
Token ID373
Feature activation-5.45e-03

Pos logit contributions
 boy+0.004
 Year+0.004
 extingu+0.004
 girl+0.004
ksh+0.004
Neg logit contributions
aches-0.004
vern-0.004
gh-0.004
ons-0.004
 accomplished-0.004
Token not
Token ID407
Feature activation-8.73e-03

Pos logit contributions
vern+0.010
aches+0.010
earned+0.010
ending+0.010
imes+0.010
Neg logit contributions
 boy-0.009
 girl-0.008
 extingu-0.007
 asleep-0.007
 Year-0.007
Token empty
Token ID6565
Feature activation-4.08e-03

Pos logit contributions
vern+0.015
aches+0.015
earned+0.014
imes+0.014
iable+0.014
Neg logit contributions
 boy-0.015
 girl-0.014
 Year-0.013
 extingu-0.013
 asleep-0.012
Token!
Token ID0
Feature activation-2.81e-02

Pos logit contributions
vern+0.006
aches+0.006
gh+0.005
earned+0.005
imes+0.005
Neg logit contributions
 boy-0.008
 girl-0.008
 Year-0.007
 extingu-0.007
ksh-0.007
Token Inside
Token ID14384
Feature activation-1.83e-02

Pos logit contributions
vern+0.048
aches+0.048
earned+0.044
fters+0.043
iable+0.043
Neg logit contributions
 boy-0.050
 girl-0.048
 Year-0.043
 extingu-0.042
 asleep-0.041
Token hug
Token ID16225
Feature activation+2.03e-02

Pos logit contributions
vern+0.003
aches+0.002
ade+0.002
gh+0.002
ag+0.002
Neg logit contributions
ksh-0.003
 Year-0.003
 boy-0.003
 extingu-0.003
ucks-0.003
Token.
Token ID13
Feature activation-1.43e-03

Pos logit contributions
 boy+0.036
 Year+0.035
 girl+0.034
 extingu+0.033
ksh+0.031
Neg logit contributions
vern-0.030
aches-0.030
gh-0.029
earned-0.029
ending-0.028
Token She
Token ID1375
Feature activation-5.18e-03

Pos logit contributions
vern+0.002
aches+0.002
imes+0.002
ough+0.002
earned+0.002
Neg logit contributions
 boy-0.003
 girl-0.003
 extingu-0.003
 Year-0.002
work-0.002
Token said
Token ID531
Feature activation+2.22e-03

Pos logit contributions
aches+0.008
vern+0.007
 hardly+0.007
 accomplished+0.007
ons+0.007
Neg logit contributions
 boy-0.010
 girl-0.009
 extingu-0.009
 Year-0.009
ksh-0.009
Token "
Token ID366
Feature activation+3.06e-02

Pos logit contributions
 boy+0.004
 girl+0.004
 extingu+0.004
 Year+0.004
ksh+0.004
Neg logit contributions
vern-0.003
aches-0.003
gh-0.003
imes-0.003
ending-0.003
TokenThank
Token ID10449
Feature activation+3.68e-02

Pos logit contributions
 boy+0.060
 girl+0.056
 extingu+0.055
 tent+0.054
 Year+0.054
Neg logit contributions
aches-0.042
earned-0.042
vern-0.042
ending-0.042
iable-0.041
Token you
Token ID345
Feature activation-1.06e-02

Pos logit contributions
 boy+0.082
 girl+0.078
 extingu+0.074
 Year+0.072
 asleep+0.071
Neg logit contributions
vern-0.046
aches-0.045
earned-0.041
imes-0.040
gh-0.040
Token for
Token ID329
Feature activation-1.46e-02

Pos logit contributions
vern+0.016
aches+0.015
gh+0.015
iable+0.014
imes+0.014
Neg logit contributions
 boy-0.020
 girl-0.019
 extingu-0.019
 Year-0.018
cy-0.017
Token being
Token ID852
Feature activation+1.07e-02

Pos logit contributions
aches+0.021
vern+0.021
gh+0.019
fters+0.019
iable+0.019
Neg logit contributions
 boy-0.030
 girl-0.028
 extingu-0.026
 Year-0.026
ksh-0.025
Token so
Token ID523
Feature activation-2.49e-02

Pos logit contributions
 boy+0.020
 girl+0.019
 Year+0.018
 extingu+0.018
 asleep+0.017
Neg logit contributions
vern-0.017
aches-0.016
earned-0.015
imes-0.015
iable-0.015
Token fair
Token ID3148
Feature activation-1.56e-02

Pos logit contributions
vern+0.037
aches+0.036
earned+0.033
ending+0.033
imes+0.032
Neg logit contributions
 boy-0.050
 girl-0.047
 Year-0.044
 extingu-0.044
 asleep-0.042
Token chase
Token ID15505
Feature activation-4.91e-02

Pos logit contributions
 extingu+0.007
 boy+0.007
 Year+0.007
 girl+0.007
ksh+0.007
Neg logit contributions
aches-0.006
imes-0.005
ons-0.005
vern-0.005
earned-0.005
Token the
Token ID262
Feature activation-2.05e-02

Pos logit contributions
aches+0.085
vern+0.082
imes+0.079
earned+0.078
ag+0.078
Neg logit contributions
 boy-0.082
 girl-0.078
 Year-0.074
 extingu-0.073
 asleep-0.069
Token butterflies
Token ID44571
Feature activation-7.27e-02

Pos logit contributions
aches+0.035
vern+0.032
ade+0.032
imes+0.031
ons+0.031
Neg logit contributions
 Year-0.031
ksh-0.030
ucks-0.030
 extingu-0.029
cy-0.029
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
aches+0.120
vern+0.119
ag+0.109
imes+0.108
earned+0.108
Neg logit contributions
 boy-0.131
 girl-0.124
 Year-0.116
 extingu-0.115
ksh-0.105
Token
Token ID198
Feature activation-2.35e-02

Pos logit contributions
imes+0.011
vern+0.011
aches+0.011
ough+0.011
earned+0.011
Neg logit contributions
 boy-0.014
 girl-0.014
 extingu-0.014
 Year-0.013
work-0.013
Token
Token ID198
Feature activation-1.77e-02

Pos logit contributions
aches+0.045
vern+0.044
earned+0.042
iable+0.042
ending+0.042
Neg logit contributions
 boy-0.037
 girl-0.034
 Year-0.030
 extingu-0.029
 asleep-0.028
Token"
Token ID1
Feature activation+4.07e-04

Pos logit contributions
aches+0.025
vern+0.025
earned+0.023
imes+0.022
ending+0.022
Neg logit contributions
 boy-0.036
 girl-0.035
 Year-0.032
 extingu-0.031
 asleep-0.029
TokenLook
Token ID8567
Feature activation+2.92e-02

Pos logit contributions
 boy+0.001
 asleep+0.001
 girl+0.001
 extingu+0.001
 cottage+0.001
Neg logit contributions
aches-0.001
Days-0.001
fters-0.001
vern-0.001
iable-0.001
Token,
Token ID11
Feature activation+3.70e-04

Pos logit contributions
 boy+0.053
 girl+0.051
 Year+0.047
 extingu+0.046
 asleep+0.044
Neg logit contributions
aches-0.047
vern-0.047
imes-0.043
iable-0.043
earned-0.043
Token Ben
Token ID3932
Feature activation-3.23e-02

Pos logit contributions
ksh+0.001
 Year+0.001
 extingu+0.001
ucks+0.001
 boy+0.001
Neg logit contributions
aches-0.001
imes-0.001
vern-0.001
iable-0.001
 expect-0.000
Token,
Token ID11
Feature activation+2.37e-03

Pos logit contributions
aches+0.032
gh+0.031
vern+0.031
ons+0.029
 done+0.028
Neg logit contributions
 Year-0.071
ksh-0.071
 extingu-0.069
 boy-0.069
 asleep-0.069
Token flew
Token ID13112
Feature activation+1.29e-03

Pos logit contributions
vern+0.047
aches+0.046
earned+0.043
imes+0.043
fters+0.042
Neg logit contributions
 boy-0.046
 girl-0.043
 Year-0.038
 extingu-0.038
 asleep-0.037
Token away
Token ID1497
Feature activation-7.53e-03

Pos logit contributions
 boy+0.002
 girl+0.002
 Year+0.002
 extingu+0.002
 cottage+0.002
Neg logit contributions
aches-0.002
ag-0.002
vern-0.002
gh-0.002
iable-0.002
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
vern+0.009
aches+0.008
 accomplished+0.008
gh+0.007
 achieve+0.007
Neg logit contributions
 boy-0.017
 Year-0.016
 girl-0.016
ksh-0.015
 extingu-0.014
Token Lily
Token ID20037
Feature activation-2.45e-02

Pos logit contributions
vern+0.017
imes+0.017
aches+0.017
earned+0.016
ough+0.016
Neg logit contributions
 boy-0.016
 extingu-0.015
 girl-0.015
 Year-0.015
work-0.014
Token felt
Token ID2936
Feature activation-4.47e-02

Pos logit contributions
aches+0.045
vern+0.045
earned+0.042
ending+0.041
imes+0.041
Neg logit contributions
 boy-0.039
 girl-0.037
 extingu-0.034
 Year-0.034
 asleep-0.032
Token very
Token ID845
Feature activation-3.27e-02

Pos logit contributions
aches+0.098
vern+0.097
earned+0.096
ending+0.095
gh+0.094
Neg logit contributions
 boy-0.059
 girl-0.055
 asleep-0.046
 duck-0.043
 t-0.042
Token sad
Token ID6507
Feature activation-6.42e-03

Pos logit contributions
vern+0.070
aches+0.069
earned+0.068
iable+0.066
ons+0.066
Neg logit contributions
 boy-0.044
 girl-0.041
 duck-0.032
 asleep-0.032
 hyd-0.030
Token and
Token ID290
Feature activation-1.09e-02

Pos logit contributions
vern+0.012
aches+0.011
ending+0.011
earned+0.011
imes+0.011
Neg logit contributions
 boy-0.010
 girl-0.009
 Year-0.009
 extingu-0.009
ksh-0.008
Token scared
Token ID12008
Feature activation-7.42e-03

Pos logit contributions
vern+0.019
aches+0.019
earned+0.017
imes+0.017
ending+0.017
Neg logit contributions
 boy-0.019
 girl-0.018
 Year-0.016
 extingu-0.016
 asleep-0.016
Token because
Token ID780
Feature activation-3.44e-02

Pos logit contributions
vern+0.014
aches+0.013
earned+0.012
fters+0.012
imes+0.012
Neg logit contributions
 boy-0.013
 girl-0.012
 extingu-0.010
 Year-0.010
 asleep-0.010
Token she
Token ID673
Feature activation-1.62e-02

Pos logit contributions
vern+0.046
aches+0.045
earned+0.041
ag+0.040
imes+0.040
Neg logit contributions
 boy-0.076
 girl-0.073
 Year-0.065
 asleep-0.064
 extingu-0.063
Token!
Token ID0
Feature activation-2.43e-02

Pos logit contributions
vern+0.018
aches+0.018
earned+0.016
imes+0.016
fters+0.016
Neg logit contributions
 boy-0.017
 girl-0.016
 extingu-0.015
 Year-0.014
 asleep-0.014
Token<|endoftext|>
Token ID50256
Feature activation+4.57e-02

Pos logit contributions
vern+0.037
aches+0.035
earned+0.034
imes+0.033
ending+0.033
Neg logit contributions
 boy-0.047
 girl-0.045
 Year-0.041
 extingu-0.041
 asleep-0.039
TokenOnce
Token ID7454
Feature activation+2.16e-02

Pos logit contributions
 boy+0.075
 girl+0.073
 extingu+0.070
 Year+0.068
work+0.064
Neg logit contributions
vern-0.075
aches-0.073
imes-0.072
ons-0.071
gh-0.070
Token upon
Token ID2402
Feature activation+1.82e-02

Pos logit contributions
 boy+0.022
 girl+0.019
 asleep+0.014
cy+0.013
 tent+0.012
Neg logit contributions
aches-0.055
vern-0.055
earned-0.055
fters-0.054
ough-0.054
Token a
Token ID257
Feature activation-4.26e-03

Pos logit contributions
 boy+0.028
 girl+0.027
 Year+0.025
 extingu+0.025
 asleep+0.023
Neg logit contributions
vern-0.034
aches-0.034
earned-0.032
gh-0.031
ag-0.031
Token time
Token ID640
Feature activation-1.67e-02

Pos logit contributions
aches+0.005
vern+0.005
earned+0.005
imes+0.004
fters+0.004
Neg logit contributions
 boy-0.010
 girl-0.009
 Year-0.009
 extingu-0.009
 asleep-0.008
Token there
Token ID612
Feature activation-6.18e-03

Pos logit contributions
vern+0.026
aches+0.025
gh+0.024
imes+0.024
earned+0.023
Neg logit contributions
 boy-0.032
 girl-0.030
 Year-0.028
 extingu-0.028
 asleep-0.026
Token was
Token ID373
Feature activation-1.78e-02

Pos logit contributions
aches+0.012
vern+0.012
earned+0.012
gh+0.012
imes+0.011
Neg logit contributions
 boy-0.009
 girl-0.008
 Year-0.007
 extingu-0.007
 asleep-0.007
Token a
Token ID257
Feature activation-3.19e-03

Pos logit contributions
vern+0.032
aches+0.032
imes+0.030
earned+0.030
ough+0.029
Neg logit contributions
 boy-0.029
 girl-0.027
 extingu-0.025
 Year-0.025
 asleep-0.023
Token little
Token ID1310
Feature activation+4.30e-02

Pos logit contributions
vern+0.005
aches+0.005
Days+0.005
 daring+0.004
ittens+0.004
Neg logit contributions
ASH-0.005
 extingu-0.005
work-0.005
 asleep-0.005
ksh-0.005
Token girl
Token ID2576
Feature activation+1.50e-02

Pos logit contributions
ASH+0.045
ksh+0.042
 Year+0.042
 asleep+0.036
ucks+0.036
Neg logit contributions
ittens-0.082
 exercise-0.082
ade-0.082
imes-0.080
ons-0.078
Token the
Token ID262
Feature activation-2.06e-02

Pos logit contributions
aches+0.053
vern+0.051
imes+0.049
ons+0.048
ag+0.048
Neg logit contributions
 boy-0.073
 girl-0.070
 Year-0.068
 extingu-0.067
ksh-0.066
Token floor
Token ID4314
Feature activation-3.90e-02

Pos logit contributions
aches+0.035
ade+0.033
ons+0.032
vern+0.032
 achieve+0.031
Neg logit contributions
 extingu-0.032
ksh-0.031
 boy-0.031
 Year-0.030
ucks-0.030
Token!
Token ID0
Feature activation-3.68e-02

Pos logit contributions
vern+0.063
aches+0.062
gh+0.057
ough+0.057
ag+0.056
Neg logit contributions
 boy-0.071
 girl-0.068
 Year-0.065
 extingu-0.062
ksh-0.059
Token Tim
Token ID5045
Feature activation-4.98e-02

Pos logit contributions
vern+0.049
imes+0.049
aches+0.048
earned+0.047
ough+0.047
Neg logit contributions
 boy-0.073
 girl-0.071
 extingu-0.067
 Year-0.066
work-0.063
Tokenmy
Token ID1820
Feature activation-1.43e-02

Pos logit contributions
aches+0.091
vern+0.090
earned+0.084
ending+0.083
iable+0.083
Neg logit contributions
 boy-0.080
 girl-0.075
 extingu-0.069
 Year-0.069
 asleep-0.065
Token's
Token ID338
Feature activation-2.16e-02

Pos logit contributions
aches+0.024
vern+0.023
ons+0.022
earned+0.022
ending+0.022
Neg logit contributions
 boy-0.024
 girl-0.023
 extingu-0.023
 Year-0.022
 asleep-0.021
Token mom
Token ID1995
Feature activation+1.54e-02

Pos logit contributions
aches+0.038
vern+0.035
imes+0.034
gh+0.034
earned+0.034
Neg logit contributions
 extingu-0.032
 Year-0.031
ksh-0.031
 boy-0.031
 girl-0.030
Token was
Token ID373
Feature activation-6.26e-03

Pos logit contributions
 boy+0.027
 girl+0.026
 Year+0.025
 extingu+0.025
 asleep+0.023
Neg logit contributions
aches-0.025
ons-0.024
iable-0.023
ending-0.023
vern-0.023
Token not
Token ID407
Feature activation-1.48e-02

Pos logit contributions
aches+0.009
vern+0.009
fters+0.008
 supposed+0.008
 achieve+0.008
Neg logit contributions
 boy-0.013
 girl-0.012
 extingu-0.012
 Year-0.012
ksh-0.011
Token happy
Token ID3772
Feature activation-2.35e-02

Pos logit contributions
aches+0.023
vern+0.023
iable+0.021
 supposed+0.021
ag+0.020
Neg logit contributions
 boy-0.028
 girl-0.026
 Year-0.026
 extingu-0.025
work-0.024
Token,
Token ID11
Feature activation-1.23e-02

Pos logit contributions
vern+0.038
aches+0.038
earned+0.035
imes+0.034
fters+0.034
Neg logit contributions
 boy-0.044
 girl-0.042
 Year-0.038
 extingu-0.038
 asleep-0.036
Token believe
Token ID1975
Feature activation-1.22e-03

Pos logit contributions
 boy+0.018
 girl+0.017
 extingu+0.016
 Year+0.016
 asleep+0.015
Neg logit contributions
vern-0.009
aches-0.008
imes-0.008
earned-0.008
ending-0.007
Token his
Token ID465
Feature activation-8.67e-03

Pos logit contributions
vern+0.002
aches+0.002
earned+0.002
imes+0.002
ending+0.002
Neg logit contributions
 boy-0.002
 girl-0.002
 Year-0.002
 extingu-0.002
 asleep-0.002
Token eyes
Token ID2951
Feature activation-5.24e-02

Pos logit contributions
vern+0.018
aches+0.016
gh+0.015
ag+0.015
ending+0.015
Neg logit contributions
 boy-0.013
 girl-0.012
 Year-0.012
ksh-0.011
cy-0.011
Token.
Token ID13
Feature activation+5.81e-03

Pos logit contributions
aches+0.082
vern+0.081
earned+0.074
iable+0.074
gh+0.074
Neg logit contributions
 boy-0.100
 girl-0.095
 Year-0.088
 extingu-0.086
 asleep-0.080
Token
Token ID220
Feature activation-1.33e-02

Pos logit contributions
 boy+0.011
 girl+0.011
 extingu+0.011
 Year+0.011
work+0.010
Neg logit contributions
vern-0.008
imes-0.007
aches-0.007
earned-0.007
ough-0.007
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
aches+0.024
vern+0.024
earned+0.023
fters+0.022
gh+0.022
Neg logit contributions
 boy-0.022
 girl-0.020
 Year-0.018
 extingu-0.018
 asleep-0.017
Token
Token ID198
Feature activation-1.75e-02

Pos logit contributions
aches+0.042
vern+0.040
earned+0.039
imes+0.039
iable+0.038
Neg logit contributions
 boy-0.029
 girl-0.026
 Year-0.023
 extingu-0.020
 asleep-0.020
TokenThe
Token ID464
Feature activation+6.23e-03

Pos logit contributions
aches+0.026
vern+0.024
imes+0.023
ag+0.022
earned+0.022
Neg logit contributions
 boy-0.036
 girl-0.034
 Year-0.030
 extingu-0.028
 cottage-0.028
Token man
Token ID582
Feature activation+6.80e-02

Pos logit contributions
 asleep+0.010
ucks+0.010
ksh+0.010
cy+0.010
 extingu+0.009
Neg logit contributions
vern-0.009
aches-0.009
Days-0.009
ade-0.009
gh-0.009
Token smiled
Token ID13541
Feature activation+4.97e-02

Pos logit contributions
ksh+0.128
 extingu+0.127
 boy+0.125
 asleep+0.124
 girl+0.124
Neg logit contributions
aches-0.095
ons-0.090
 else-0.084
ending-0.083
 accomplished-0.083
Token and
Token ID290
Feature activation+2.05e-03

Pos logit contributions
 Year+0.104
 boy+0.090
ASH+0.090
 extingu+0.087
 pret+0.085
Neg logit contributions
vern-0.057
ag-0.054
Her-0.053
;-0.052
ending-0.052
Token and
Token ID290
Feature activation-1.47e-02

Pos logit contributions
aches+0.018
ons+0.016
imes+0.016
vern+0.016
ade+0.015
Neg logit contributions
 boy-0.019
 extingu-0.019
 girl-0.018
 Year-0.018
ksh-0.017
Token put
Token ID1234
Feature activation-1.88e-02

Pos logit contributions
aches+0.024
ons+0.020
imes+0.019
 achieve+0.019
 hardly+0.019
Neg logit contributions
 boy-0.027
 extingu-0.027
 Year-0.026
 girl-0.025
ksh-0.025
Token it
Token ID340
Feature activation-3.16e-02

Pos logit contributions
aches+0.026
ons+0.024
imes+0.023
ag+0.021
ade+0.020
Neg logit contributions
 boy-0.040
 extingu-0.038
 Year-0.037
 girl-0.037
ksh-0.036
Token in
Token ID287
Feature activation-4.73e-03

Pos logit contributions
aches+0.058
vern+0.054
ag+0.052
gh+0.050
imes+0.049
Neg logit contributions
 boy-0.055
 girl-0.051
 Year-0.049
 extingu-0.049
ksh-0.045
Token her
Token ID607
Feature activation-3.68e-02

Pos logit contributions
aches+0.006
vern+0.006
gh+0.005
ons+0.005
imes+0.005
Neg logit contributions
 boy-0.010
 girl-0.010
ksh-0.009
 Year-0.009
 extingu-0.009
Token mouth
Token ID5422
Feature activation-9.96e-02

Pos logit contributions
aches+0.069
vern+0.066
earned+0.064
ons+0.062
imes+0.061
Neg logit contributions
 boy-0.055
 extingu-0.050
 girl-0.050
ksh-0.049
 Year-0.046
Token.
Token ID13
Feature activation-1.12e-03

Pos logit contributions
aches+0.162
vern+0.161
earned+0.149
imes+0.147
ough+0.145
Neg logit contributions
 boy-0.181
 girl-0.172
 Year-0.160
 extingu-0.156
 asleep-0.145
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
vern+0.001
imes+0.001
aches+0.001
earned+0.001
ough+0.001
Neg logit contributions
 boy-0.002
 girl-0.002
 extingu-0.002
 Year-0.002
work-0.002
Token
Token ID198
Feature activation-1.43e-02

Pos logit contributions
aches+0.036
vern+0.036
earned+0.034
iable+0.034
ending+0.033
Neg logit contributions
 boy-0.031
 girl-0.029
 Year-0.025
 extingu-0.024
 asleep-0.024
TokenThe
Token ID464
Feature activation+1.47e-03

Pos logit contributions
vern+0.020
aches+0.020
earned+0.018
imes+0.018
gh+0.017
Neg logit contributions
 boy-0.030
 girl-0.029
 Year-0.026
 extingu-0.026
 asleep-0.025
Token flower
Token ID15061
Feature activation+7.56e-03

Pos logit contributions
ksh+0.002
 extingu+0.002
ucks+0.002
ASH+0.002
 Year+0.002
Neg logit contributions
aches-0.003
imes-0.002
vern-0.002
ade-0.002
fters-0.002
Token.
Token ID13
Feature activation+1.62e-02

Pos logit contributions
 boy+0.090
 girl+0.085
 Year+0.084
 extingu+0.080
work+0.074
Neg logit contributions
vern-0.089
aches-0.087
ending-0.081
gh-0.080
earned-0.080
Token
Token ID220
Feature activation-9.34e-03

Pos logit contributions
 boy+0.031
 girl+0.029
 Year+0.027
 extingu+0.027
 asleep+0.025
Neg logit contributions
vern-0.025
aches-0.025
earned-0.023
imes-0.023
ending-0.023
Token
Token ID198
Feature activation-1.48e-02

Pos logit contributions
aches+0.019
vern+0.018
earned+0.018
fters+0.017
gh+0.017
Neg logit contributions
 boy-0.013
 girl-0.012
 extingu-0.011
 asleep-0.011
 Year-0.011
Token
Token ID198
Feature activation-1.34e-02

Pos logit contributions
aches+0.033
vern+0.032
earned+0.031
iable+0.031
ag+0.031
Neg logit contributions
 boy-0.018
 girl-0.016
 duck-0.013
 Sn-0.013
 extingu-0.013
TokenM
Token ID44
Feature activation+3.14e-02

Pos logit contributions
aches+0.019
vern+0.019
ag+0.019
 supposed+0.018
earned+0.018
Neg logit contributions
 boy-0.026
 girl-0.025
 duck-0.023
 Sn-0.022
 Year-0.022
Tokenittens
Token ID34978
Feature activation-1.27e-01

Pos logit contributions
 boy+0.084
 girl+0.081
 Year+0.075
 extingu+0.074
 duck+0.072
Neg logit contributions
aches-0.024
vern-0.024
earned-0.020
iable-0.020
imes-0.020
Token went
Token ID1816
Feature activation-3.22e-03

Pos logit contributions
aches+0.199
vern+0.178
ons+0.174
 achieve+0.172
iable+0.171
Neg logit contributions
 extingu-0.230
 boy-0.225
ksh-0.222
 girl-0.218
 Year-0.218
Token home
Token ID1363
Feature activation-5.72e-03

Pos logit contributions
aches+0.005
vern+0.005
ag+0.005
gh+0.005
earned+0.005
Neg logit contributions
 boy-0.006
 girl-0.005
ksh-0.005
 Year-0.005
 extingu-0.005
Token feeling
Token ID4203
Feature activation+4.39e-03

Pos logit contributions
vern+0.009
aches+0.009
 hardly+0.008
 achieve+0.008
 accomplished+0.008
Neg logit contributions
ksh-0.010
 Year-0.010
 boy-0.010
 girl-0.009
 extingu-0.009
Token down
Token ID866
Feature activation-1.57e-02

Pos logit contributions
 boy+0.008
 girl+0.008
 Year+0.007
 extingu+0.007
 asleep+0.007
Neg logit contributions
vern-0.007
aches-0.007
earned-0.006
imes-0.006
ending-0.006
Token.
Token ID13
Feature activation+1.47e-02

Pos logit contributions
vern+0.026
aches+0.026
earned+0.024
imes+0.024
ag+0.024
Neg logit contributions
 boy-0.027
 girl-0.026
 Year-0.025
 extingu-0.024
ksh-0.023
Token Here
Token ID3423
Feature activation-5.30e-03

Pos logit contributions
 boy+0.042
 girl+0.039
 Year+0.036
 extingu+0.035
 asleep+0.034
Neg logit contributions
vern-0.043
aches-0.042
earned-0.040
imes-0.040
ough-0.039
Token are
Token ID389
Feature activation+5.05e-02

Pos logit contributions
vern+0.010
aches+0.010
earned+0.010
ending+0.010
fters+0.010
Neg logit contributions
 boy-0.008
 girl-0.008
 Year-0.007
 duck-0.006
 extingu-0.006
Token Lily
Token ID20037
Feature activation-8.10e-03

Pos logit contributions
 boy+0.099
 girl+0.095
 Year+0.085
 extingu+0.084
 asleep+0.082
Neg logit contributions
vern-0.077
aches-0.075
earned-0.070
ending-0.069
fters-0.068
Token's
Token ID338
Feature activation+9.39e-03

Pos logit contributions
vern+0.014
aches+0.014
earned+0.013
imes+0.012
iable+0.012
Neg logit contributions
 boy-0.014
 girl-0.013
 Year-0.013
 extingu-0.012
 asleep-0.012
Token m
Token ID285
Feature activation+2.24e-02

Pos logit contributions
work+0.015
 Year+0.014
 boy+0.014
fly+0.014
ksh+0.014
Neg logit contributions
aches-0.015
vern-0.015
ag-0.014
ittens-0.014
gh-0.014
Tokenittens
Token ID34978
Feature activation-1.27e-01

Pos logit contributions
 boy+0.060
 girl+0.058
 Year+0.054
 extingu+0.054
 asleep+0.053
Neg logit contributions
vern-0.018
aches-0.017
earned-0.015
imes-0.014
ending-0.014
Token.
Token ID13
Feature activation+2.33e-02

Pos logit contributions
aches+0.216
vern+0.215
earned+0.198
imes+0.196
fters+0.194
Neg logit contributions
 boy-0.223
 girl-0.212
 Year-0.193
 extingu-0.191
 asleep-0.182
Token They
Token ID1119
Feature activation+1.22e-02

Pos logit contributions
 boy+0.043
 girl+0.041
 Year+0.038
maid+0.037
work+0.037
Neg logit contributions
earned-0.034
vern-0.033
imes-0.033
ough-0.032
aches-0.032
Token are
Token ID389
Feature activation+5.04e-02

Pos logit contributions
 boy+0.025
 girl+0.024
 Year+0.023
 extingu+0.022
ksh+0.021
Neg logit contributions
aches-0.017
vern-0.017
earned-0.015
iable-0.015
fters-0.015
Token warm
Token ID5814
Feature activation-1.01e-02

Pos logit contributions
 boy+0.096
 girl+0.090
 Year+0.086
 extingu+0.086
work+0.083
Neg logit contributions
aches-0.081
vern-0.076
imes-0.069
ag-0.069
 supposed-0.068
Token and
Token ID290
Feature activation+1.53e-02

Pos logit contributions
ons+0.010
ag+0.009
aces+0.009
ough+0.009
earned+0.009
Neg logit contributions
Uh-0.019
 extingu-0.019
 poster-0.018
fly-0.018
work-0.018
Token named
Token ID3706
Feature activation-3.95e-03

Pos logit contributions
 boy+0.049
 girl+0.047
 Year+0.044
 extingu+0.043
 asleep+0.041
Neg logit contributions
aches-0.042
vern-0.041
earned-0.038
ag-0.037
gh-0.037
Token Mitt
Token ID16627
Feature activation-8.71e-02

Pos logit contributions
vern+0.008
aches+0.008
earned+0.008
imes+0.008
ending+0.008
Neg logit contributions
 boy-0.005
 girl-0.005
 Year-0.004
 extingu-0.004
 asleep-0.004
Tokenens
Token ID641
Feature activation-1.02e-01

Pos logit contributions
vern+0.141
aches+0.138
earned+0.126
 achieve+0.124
fters+0.123
Neg logit contributions
 boy-0.175
 girl-0.170
 extingu-0.143
 duck-0.142
 asleep-0.140
Token.
Token ID13
Feature activation-1.84e-02

Pos logit contributions
vern+0.199
aches+0.196
earned+0.189
fters+0.187
ending+0.186
Neg logit contributions
 boy-0.162
 girl-0.152
 extingu-0.134
 Year-0.130
 asleep-0.125
Token Mitt
Token ID16627
Feature activation-8.41e-02

Pos logit contributions
vern+0.039
aches+0.038
iable+0.035
ending+0.035
fters+0.034
Neg logit contributions
 boy-0.029
 girl-0.027
 extingu-0.023
 Sn-0.023
 asleep-0.023
Tokenens
Token ID641
Feature activation-9.97e-02

Pos logit contributions
vern+0.140
aches+0.136
earned+0.126
 achieve+0.124
fters+0.122
Neg logit contributions
 boy-0.168
 girl-0.162
cy-0.133
 duck-0.132
 extingu-0.130
Token liked
Token ID8288
Feature activation-1.12e-02

Pos logit contributions
vern+0.171
aches+0.168
earned+0.158
imes+0.156
fters+0.156
Neg logit contributions
 boy-0.179
 girl-0.169
 Year-0.151
 extingu-0.147
 asleep-0.141
Token to
Token ID284
Feature activation-9.00e-03

Pos logit contributions
vern+0.019
aches+0.018
iable+0.017
earned+0.017
fters+0.017
Neg logit contributions
 boy-0.021
 girl-0.020
 asleep-0.018
 Year-0.018
 extingu-0.017
Token play
Token ID711
Feature activation-1.24e-02

Pos logit contributions
vern+0.016
ending+0.015
aches+0.015
iable+0.015
imes+0.015
Neg logit contributions
 boy-0.015
 girl-0.014
 extingu-0.013
 Year-0.013
 duck-0.012
Token with
Token ID351
Feature activation+2.27e-02

Pos logit contributions
vern+0.028
aches+0.028
earned+0.027
ending+0.026
imes+0.026
Neg logit contributions
 boy-0.016
 girl-0.014
 Year-0.012
 extingu-0.012
 asleep-0.012
Token toys
Token ID14958
Feature activation-5.39e-02

Pos logit contributions
 boy+0.039
 girl+0.036
 t+0.033
 duck+0.032
 extingu+0.032
Neg logit contributions
vern-0.044
ending-0.041
iable-0.041
 achieve-0.041
earned-0.040
Token join
Token ID4654
Feature activation+4.07e-02

Pos logit contributions
vern+0.003
aches+0.003
imes+0.003
earned+0.003
iable+0.003
Neg logit contributions
 boy-0.003
 girl-0.003
 duck-0.003
 t-0.003
 asleep-0.003
Token them
Token ID606
Feature activation+6.69e-03

Pos logit contributions
 boy+0.086
 girl+0.080
 extingu+0.080
 Year+0.076
ksh+0.075
Neg logit contributions
aches-0.052
vern-0.050
ag-0.050
imes-0.049
gh-0.047
Token,
Token ID11
Feature activation-8.70e-04

Pos logit contributions
 boy+0.012
 girl+0.011
 Year+0.010
 extingu+0.010
ksh+0.009
Neg logit contributions
vern-0.011
aches-0.011
imes-0.010
earned-0.010
ag-0.010
Token but
Token ID475
Feature activation-2.98e-02

Pos logit contributions
aches+0.001
 hardly+0.001
vern+0.001
imes+0.001
 achieve+0.001
Neg logit contributions
 Year-0.002
 boy-0.002
 extingu-0.002
 girl-0.002
cy-0.002
Token she
Token ID673
Feature activation-1.16e-04

Pos logit contributions
aches+0.035
vern+0.035
imes+0.031
earned+0.031
iable+0.030
Neg logit contributions
 boy-0.067
 girl-0.065
 extingu-0.062
 Year-0.062
 asleep-0.058
Token forgot
Token ID16453
Feature activation-1.02e-01

Pos logit contributions
aches+0.000
vern+0.000
imes+0.000
ending+0.000
gh+0.000
Neg logit contributions
 boy-0.000
 girl-0.000
 extingu-0.000
 Year-0.000
 asleep-0.000
Token something
Token ID1223
Feature activation-3.63e-03

Pos logit contributions
vern+0.154
aches+0.151
earned+0.145
fters+0.142
ough+0.139
Neg logit contributions
 boy-0.200
 girl-0.190
 asleep-0.176
 extingu-0.168
 t-0.165
Token.
Token ID13
Feature activation+9.97e-03

Pos logit contributions
earned+0.006
vern+0.006
aches+0.006
ough+0.006
fters+0.006
Neg logit contributions
 boy-0.007
 girl-0.006
 duck-0.005
 extingu-0.005
 asleep-0.005
Token She
Token ID1375
Feature activation+6.76e-03

Pos logit contributions
 boy+0.019
 girl+0.018
 extingu+0.017
 Year+0.017
work+0.016
Neg logit contributions
vern-0.015
aches-0.014
imes-0.014
earned-0.013
ending-0.013
Token forgot
Token ID16453
Feature activation-9.86e-02

Pos logit contributions
 extingu+0.013
 Year+0.012
 boy+0.012
 girl+0.012
work+0.012
Neg logit contributions
aches-0.010
 hardly-0.009
imes-0.008
 accomplished-0.008
gh-0.008
Token to
Token ID284
Feature activation-2.01e-03

Pos logit contributions
vern+0.144
aches+0.141
earned+0.136
fters+0.132
ough+0.129
Neg logit contributions
 boy-0.199
 girl-0.189
 asleep-0.177
 t-0.166
 extingu-0.166