TOP ACTIVATIONS
MAX = 5.585

, he crawled under the leather and hid .
and put it under the plastic ball . Now , when
crawled out from under the leather and surprised Sammy . Sammy
ed out from under the leather and saw his friend Sammy
a man with a big leather ball . The man said
. He played with the leather ball until it was time
a man who wore a leather coat . He was very
toys back in the organized leather box . They were happy
find a use for the leather . Tom and
of fun playing with the leather ball and they were very
the man , grabbed the leather shape , and ran off
and - seek behind the old barn . While they were
had been hidden inside the plastic eggs . The
saw a man with a leather jacket and a shiny bike
he was wearing a blue leather jacket . " Go away
she reached into the old leather bag and pulled out a
to a tear in the leather . " Maybe
of the mel on in plastic and put it in the
The man was wearing a leather jacket . Alex thought it
excited to play on the velvet bed , that she hadn

MIN ACTIVATIONS
MIN = -5.398

girl who didn 't like av oc ados . She always
something new ! She thought av oc ados were the most
on , whenever they wanted av oc ados , they would
ongo didn 't like wet av oc ados , so he
to see where their cup cakes would go on the tour
Maybe they could grow more av oc ados and share them
tree could see lots of av oc ados that the supplier
happy that it produced more av oc ados than ever before
something new ! She thought av oc ados were the most
the tree if they were av oc ados , and they
want to leave her mud pies . " L
the store to get more av oc ados . Gary looked
away . She learned that av oc ados are good for
the tree knew that the av oc ados would be back
outside . When the cup cakes were done , they sat
his hands and make mud pies . One day , Tim
. Can we make cup cakes next time ?"
says , " They are av oc ados . My mom
sat down and enjoyed their pies together . From that day
dig holes and make mud pies . They saw a big

INTERVAL 2.839 - 5.585
CONTAINS 0.202%

He saw lots of shiny red apples hanging from its branches
metal sign that said " D anger : Do not cross
Tom walked slowly to the old sw an . He held
to only play with one toy at a time and put
The man was wearing an expensive suit and hat . He

INTERVAL 0.093 - 2.839
CONTAINS 43.459%

I will wait for your signal . Over ," the man
they saw the flower and they agreed with the message .
very proud of his shield , and all other knights were
meet you ." Lily was happy that her mom my liked
ila and Ben ," Sam said . " I saw your

INTERVAL -2.652 - 0.093
CONTAINS 56.202%

sm elly , but it â € ™ s good for
a pet . It is a wild animal . It does
wanted to play . They played for a little while ,
kept playing it every day . They would all join together
round and shiny . It looks like a balloon , but

INTERVAL -5.398 - -2.652
CONTAINS 0.138%

Max learned to sit , stay , and roll
angry . It was too early to take a bath !
. The family felt so much love and joy when the
at first , but if she kept looking , she would
as he did he suddenly sne ez ed .
Token,
Token ID11
Feature activation-2.65e-01

Pos logit contributions
 finished+0.012
 finally+0.009
 bra+0.008
 longer+0.008
 finish+0.008
Neg logit contributions
ucer-0.025
unny-0.024
 globe-0.024
fish-0.023
 Area-0.023
Token he
Token ID339
Feature activation-6.46e-02

Pos logit contributions
 finished+0.006
 finally+0.004
 bra+0.004
 finish+0.004
 longer+0.004
Neg logit contributions
ucer-0.011
 globe-0.011
unny-0.011
fish-0.011
 Area-0.010
Token crawled
Token ID45668
Feature activation-1.00e+00

Pos logit contributions
 finished+0.001
 finally+0.001
 even+0.001
 longer+0.001
 finish+0.001
Neg logit contributions
ucer-0.003
unny-0.003
 Area-0.003
 globe-0.003
fish-0.003
Token under
Token ID739
Feature activation+1.63e-01

Pos logit contributions
 finished+0.021
 finally+0.017
 longer+0.015
 even+0.014
 finish+0.013
Neg logit contributions
ucer-0.048
unny-0.047
 Area-0.045
fish-0.045
 globe-0.045
Token the
Token ID262
Feature activation+2.50e-01

Pos logit contributions
ucer+0.008
unny+0.008
 globe+0.008
 Area+0.008
fish+0.008
Neg logit contributions
 finished-0.003
 finally-0.002
 longer-0.002
 gust-0.001
 finish-0.001
Token leather
Token ID11620
Feature activation+5.59e+00

Pos logit contributions
ucer+0.009
unny+0.008
 Area+0.008
fish+0.008
 globe+0.008
Neg logit contributions
 finished-0.008
 finally-0.007
 longer-0.006
 finish-0.006
 less-0.006
Token and
Token ID290
Feature activation-1.81e-01

Pos logit contributions
ucer+0.205
unny+0.202
 Area+0.201
eway+0.192
fish+0.188
Neg logit contributions
 finished-0.161
 finally-0.139
 longer-0.130
 finish-0.129
 even-0.124
Token hid
Token ID24519
Feature activation+8.22e-01

Pos logit contributions
 finished+0.005
 anymore+0.004
 finally+0.004
 longer+0.004
 gust+0.003
Neg logit contributions
ucer-0.007
unny-0.007
 Area-0.007
fish-0.007
 globe-0.007
Token.
Token ID13
Feature activation-8.60e-01

Pos logit contributions
ucer+0.037
unny+0.036
 Area+0.035
fish+0.034
 globe+0.034
Neg logit contributions
 finished-0.019
 finally-0.016
 longer-0.014
 even-0.013
 less-0.013
Token
Token ID220
Feature activation+8.52e-02

Pos logit contributions
 finished+0.023
 finally+0.018
 longer+0.018
 anymore+0.016
 less+0.016
Neg logit contributions
ucer-0.035
unny-0.034
 Area-0.033
 globe-0.032
fish-0.032
Token
Token ID198
Feature activation-8.61e-01

Pos logit contributions
ucer+0.004
unny+0.003
 Area+0.003
fish+0.003
 globe+0.003
Neg logit contributions
 finished-0.002
 finally-0.002
 longer-0.002
 less-0.002
 finish-0.001
Token and
Token ID290
Feature activation-6.45e-01

Pos logit contributions
ucer+0.009
 globe+0.009
fish+0.009
 Area+0.009
unny+0.009
Neg logit contributions
 finished-0.006
 finally-0.005
 gust-0.004
 longer-0.004
 less-0.004
Token put
Token ID1234
Feature activation+4.25e-02

Pos logit contributions
 anymore+0.016
 finished+0.015
 finally+0.013
 longer+0.012
 rum+0.012
Neg logit contributions
ucer-0.025
unny-0.024
fish-0.023
 Area-0.023
 globe-0.022
Token it
Token ID340
Feature activation+4.04e-02

Pos logit contributions
ucer+0.002
unny+0.002
 Area+0.002
 globe+0.002
fish+0.002
Neg logit contributions
 finished-0.001
 finally-0.001
 longer-0.001
 gust-0.001
 finish-0.001
Token under
Token ID739
Feature activation+2.77e-01

Pos logit contributions
ucer+0.002
unny+0.002
fish+0.002
 globe+0.002
 Area+0.002
Neg logit contributions
 finished-0.001
 finally-0.001
 gust-0.001
 longer-0.001
 anymore-0.001
Token the
Token ID262
Feature activation+6.14e-01

Pos logit contributions
ucer+0.012
 globe+0.012
unny+0.012
 Area+0.012
fish+0.011
Neg logit contributions
 finished-0.006
 finally-0.004
 healthier-0.004
 gust-0.004
 longer-0.004
Token plastic
Token ID7309
Feature activation+5.45e+00

Pos logit contributions
ucer+0.018
unny+0.017
 Area+0.017
fish+0.016
 globe+0.016
Neg logit contributions
 finished-0.023
 finally-0.021
 longer-0.019
 finish-0.019
 less-0.019
Token ball
Token ID2613
Feature activation+2.18e+00

Pos logit contributions
unny+0.162
ucer+0.159
 Area+0.152
fish+0.145
eway+0.144
Neg logit contributions
 finished-0.191
 finish-0.164
 longer-0.161
 finally-0.161
 more-0.159
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
ucer+0.104
unny+0.100
 Area+0.098
fish+0.098
 globe+0.097
Neg logit contributions
 finished-0.043
 finally-0.033
 longer-0.028
 gust-0.026
 less-0.026
Token Now
Token ID2735
Feature activation+6.58e-01

Pos logit contributions
 finished+0.003
 finally+0.003
 longer+0.002
 less+0.002
 finish+0.002
Neg logit contributions
ucer-0.004
unny-0.004
fish-0.004
 Area-0.004
 globe-0.004
Token,
Token ID11
Feature activation-9.44e-02

Pos logit contributions
ucer+0.031
unny+0.030
 Area+0.029
 globe+0.028
fish+0.028
Neg logit contributions
 finished-0.013
 finally-0.010
 longer-0.009
 gust-0.008
 finish-0.008
Token when
Token ID618
Feature activation-2.55e-02

Pos logit contributions
 finished+0.003
 finally+0.002
 longer+0.002
 gust+0.002
 anymore+0.002
Neg logit contributions
ucer-0.003
unny-0.003
 Area-0.003
 globe-0.003
fish-0.003
Token crawled
Token ID45668
Feature activation-9.82e-01

Pos logit contributions
ucer+0.047
unny+0.045
 Area+0.044
fish+0.044
 globe+0.043
Neg logit contributions
 finished-0.028
 finally-0.023
 longer-0.022
 anymore-0.021
 less-0.020
Token out
Token ID503
Feature activation+1.06e+00

Pos logit contributions
 finished+0.022
 finally+0.019
 longer+0.017
 even+0.015
 less+0.015
Neg logit contributions
ucer-0.045
unny-0.043
 Area-0.042
fish-0.041
 globe-0.041
Token from
Token ID422
Feature activation-8.01e-01

Pos logit contributions
ucer+0.044
unny+0.043
fish+0.042
 Area+0.042
 globe+0.041
Neg logit contributions
 finished-0.025
 finally-0.019
 gust-0.018
 finish-0.017
 longer-0.017
Token under
Token ID739
Feature activation-9.01e-02

Pos logit contributions
 finished+0.018
 finally+0.014
 longer+0.013
 less+0.011
 finish+0.011
Neg logit contributions
ucer-0.037
unny-0.036
 Area-0.035
fish-0.034
 globe-0.034
Token the
Token ID262
Feature activation+3.09e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 less+0.001
 finish+0.001
Neg logit contributions
ucer-0.005
unny-0.005
 Area-0.004
 globe-0.004
fish-0.004
Token leather
Token ID11620
Feature activation+5.29e+00

Pos logit contributions
ucer+0.011
unny+0.011
 Area+0.010
fish+0.010
 globe+0.010
Neg logit contributions
 finished-0.010
 finally-0.008
 longer-0.008
 less-0.007
 finish-0.007
Token and
Token ID290
Feature activation-5.41e-01

Pos logit contributions
ucer+0.177
unny+0.173
 Area+0.171
eway+0.164
 globe+0.160
Neg logit contributions
 finished-0.171
 finally-0.149
 longer-0.142
 finish-0.137
 even-0.134
Token surprised
Token ID6655
Feature activation+8.50e-01

Pos logit contributions
 finished+0.014
 finally+0.011
 longer+0.011
 anymore+0.010
 gust+0.010
Neg logit contributions
ucer-0.023
unny-0.021
 Area-0.021
fish-0.021
 globe-0.021
Token Sammy
Token ID44067
Feature activation+1.97e+00

Pos logit contributions
ucer+0.034
unny+0.033
fish+0.032
 Area+0.032
eway+0.031
Neg logit contributions
 finished-0.021
 finally-0.015
 finish-0.014
 healthier-0.014
 longer-0.013
Token.
Token ID13
Feature activation-8.05e-01

Pos logit contributions
ucer+0.091
unny+0.088
 Area+0.086
fish+0.084
 globe+0.084
Neg logit contributions
 finished-0.043
 finally-0.034
 longer-0.030
 less-0.027
 finish-0.027
Token Sammy
Token ID44067
Feature activation+1.60e+00

Pos logit contributions
 finished+0.019
 finally+0.014
 longer+0.014
 anymore+0.013
 less+0.013
Neg logit contributions
ucer-0.035
unny-0.035
 Area-0.034
 globe-0.032
fish-0.032
Tokened
Token ID276
Feature activation-1.26e+00

Pos logit contributions
 finished+0.005
 finally+0.005
 longer+0.004
 less+0.004
 finish+0.004
Neg logit contributions
ucer-0.006
unny-0.006
 Area-0.006
fish-0.006
 globe-0.006
Token out
Token ID503
Feature activation-7.03e-02

Pos logit contributions
 finished+0.033
 finally+0.027
 longer+0.024
 gust+0.023
 finish+0.023
Neg logit contributions
ucer-0.051
unny-0.049
 Area-0.048
 globe-0.048
fish-0.047
Token from
Token ID422
Feature activation-1.00e+00

Pos logit contributions
 finished+0.002
 finally+0.001
 healthier+0.001
 finish+0.001
 anymore+0.001
Neg logit contributions
ucer-0.003
unny-0.003
fish-0.003
 Area-0.003
 globe-0.003
Token under
Token ID739
Feature activation-2.06e-01

Pos logit contributions
 finished+0.023
 finally+0.020
 longer+0.017
 even+0.016
 less+0.016
Neg logit contributions
ucer-0.045
unny-0.044
 Area-0.042
fish-0.041
 globe-0.041
Token the
Token ID262
Feature activation+3.64e-01

Pos logit contributions
 finished+0.003
 finally+0.002
 longer+0.002
 less+0.001
 even+0.001
Neg logit contributions
ucer-0.011
unny-0.011
 Area-0.010
fish-0.010
 globe-0.010
Token leather
Token ID11620
Feature activation+5.17e+00

Pos logit contributions
ucer+0.013
unny+0.013
 Area+0.012
fish+0.012
 globe+0.011
Neg logit contributions
 finished-0.012
 finally-0.010
 longer-0.009
 finish-0.009
 less-0.009
Token and
Token ID290
Feature activation-7.03e-01

Pos logit contributions
ucer+0.155
 Area+0.154
unny+0.153
eway+0.144
utes+0.138
Neg logit contributions
 finished-0.178
 finally-0.156
 longer-0.150
 finish-0.145
 anymore-0.144
Token saw
Token ID2497
Feature activation-6.27e-01

Pos logit contributions
 finished+0.017
 finally+0.014
 longer+0.012
 less+0.011
 anymore+0.011
Neg logit contributions
ucer-0.031
unny-0.030
 Area-0.029
fish-0.029
 globe-0.028
Token his
Token ID465
Feature activation-1.49e+00

Pos logit contributions
 finished+0.014
 finally+0.010
 longer+0.009
 finish+0.009
 gust+0.008
Neg logit contributions
ucer-0.029
unny-0.027
 globe-0.027
 Area-0.027
fish-0.027
Token friend
Token ID1545
Feature activation+4.62e-01

Pos logit contributions
 finished+0.046
 finally+0.039
 longer+0.036
 less+0.034
 finish+0.034
Neg logit contributions
ucer-0.055
unny-0.053
 Area-0.051
fish-0.051
 globe-0.050
Token Sammy
Token ID44067
Feature activation+1.10e+00

Pos logit contributions
ucer+0.020
unny+0.020
 Area+0.019
fish+0.019
 globe+0.019
Neg logit contributions
 finished-0.010
 finally-0.008
 longer-0.007
 gust-0.007
 less-0.007
Token a
Token ID257
Feature activation-1.68e-01

Pos logit contributions
 finished+0.007
 finally+0.005
 longer+0.005
 finish+0.004
 anymore+0.004
Neg logit contributions
ucer-0.015
unny-0.015
 Area-0.014
fish-0.014
 globe-0.014
Token man
Token ID582
Feature activation-1.21e+00

Pos logit contributions
 finished+0.003
 finally+0.002
 gust+0.002
 longer+0.002
 finish+0.001
Neg logit contributions
ucer-0.009
unny-0.009
 Area-0.008
eway-0.008
fish-0.008
Token with
Token ID351
Feature activation+1.34e+00

Pos logit contributions
 finished+0.030
 finally+0.024
 longer+0.022
 less+0.020
 gust+0.020
Neg logit contributions
ucer-0.052
unny-0.050
 Area-0.049
fish-0.048
 globe-0.048
Token a
Token ID257
Feature activation+1.00e+00

Pos logit contributions
ucer+0.048
 globe+0.045
 telescope+0.044
 appearances+0.044
 fossil+0.043
Neg logit contributions
 finished-0.037
 finally-0.031
 longer-0.031
 anymore-0.031
 finish-0.028
Token big
Token ID1263
Feature activation+4.88e-01

Pos logit contributions
ucer+0.043
unny+0.042
 Area+0.041
 globe+0.040
fish+0.040
Neg logit contributions
 finished-0.024
 finally-0.020
 longer-0.018
 anymore-0.017
 less-0.017
Token leather
Token ID11620
Feature activation+5.15e+00

Pos logit contributions
ucer+0.015
 globe+0.015
unny+0.014
 Area+0.014
fish+0.014
Neg logit contributions
 finished-0.017
 finally-0.015
 longer-0.014
 less-0.013
 anymore-0.013
Token ball
Token ID2613
Feature activation+1.14e+00

Pos logit contributions
ucer+0.169
unny+0.168
 Area+0.167
eway+0.163
eways+0.154
Neg logit contributions
 finished-0.165
 finally-0.138
 at-0.137
 longer-0.135
 tum-0.131
Token.
Token ID13
Feature activation-2.79e-01

Pos logit contributions
ucer+0.058
unny+0.056
 Area+0.055
fish+0.054
 globe+0.054
Neg logit contributions
 finished-0.019
 finally-0.014
 longer-0.012
 less-0.011
 finish-0.011
Token The
Token ID383
Feature activation-1.98e-02

Pos logit contributions
 finished+0.006
 longer+0.006
 finally+0.005
 even+0.005
 extra+0.005
Neg logit contributions
 globe-0.011
ucer-0.011
 Area-0.011
unny-0.011
 fossil-0.010
Token man
Token ID582
Feature activation-3.41e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 less+0.001
 finish+0.001
Neg logit contributions
ucer-0.001
unny-0.001
 Area-0.001
fish-0.001
 globe-0.001
Token said
Token ID531
Feature activation+2.00e+00

Pos logit contributions
 finished+0.009
 longer+0.008
 finally+0.008
 gust+0.007
 anymore+0.007
Neg logit contributions
ucer-0.013
fish-0.013
 globe-0.012
unny-0.012
 Area-0.012
Token.
Token ID13
Feature activation-5.97e-01

Pos logit contributions
ucer+0.017
fish+0.016
unny+0.016
 Area+0.016
 globe+0.016
Neg logit contributions
 finished-0.008
 finally-0.006
 gust-0.006
 longer-0.005
 healthier-0.005
Token He
Token ID679
Feature activation+1.32e+00

Pos logit contributions
 finished+0.019
 longer+0.017
 finally+0.016
 gust+0.015
 bra+0.015
Neg logit contributions
 Area-0.018
 globe-0.018
unny-0.018
 fossil-0.018
ucer-0.017
Token played
Token ID2826
Feature activation-4.86e-01

Pos logit contributions
ucer+0.056
unny+0.054
fish+0.054
 Area+0.053
 globe+0.052
Neg logit contributions
 finished-0.031
 finally-0.026
 longer-0.024
 anymore-0.023
 gust-0.023
Token with
Token ID351
Feature activation+9.54e-01

Pos logit contributions
 finished+0.012
 finally+0.010
 gust+0.009
 rum+0.009
 longer+0.009
Neg logit contributions
ucer-0.019
 Area-0.019
fish-0.019
 globe-0.019
unny-0.019
Token the
Token ID262
Feature activation+5.62e-01

Pos logit contributions
fish+0.035
 globe+0.034
ucer+0.034
 fossil+0.033
unny+0.032
Neg logit contributions
 finished-0.024
 rum-0.018
 finally-0.018
 gust-0.017
 finish-0.017
Token leather
Token ID11620
Feature activation+5.13e+00

Pos logit contributions
ucer+0.017
unny+0.016
 Area+0.016
 globe+0.016
fish+0.016
Neg logit contributions
 finished-0.021
 finally-0.018
 longer-0.017
 anymore-0.017
 less-0.017
Token ball
Token ID2613
Feature activation+1.22e+00

Pos logit contributions
ucer+0.159
unny+0.151
 Area+0.147
 globe+0.139
fish+0.139
Neg logit contributions
 finished-0.187
 finally-0.165
 longer-0.156
 anymore-0.150
 less-0.149
Token until
Token ID1566
Feature activation-9.70e-01

Pos logit contributions
fish+0.051
ucer+0.050
 globe+0.050
unny+0.049
 Area+0.048
Neg logit contributions
 finished-0.027
 finally-0.021
 gust-0.020
 rum-0.019
 sweaty-0.019
Token it
Token ID340
Feature activation-1.78e+00

Pos logit contributions
 scr+0.029
whe+0.028
 finished+0.028
 bra+0.028
hy+0.028
Neg logit contributions
fish-0.027
ucer-0.026
 globe-0.024
 telescope-0.022
 Area-0.022
Token was
Token ID373
Feature activation-4.43e-01

Pos logit contributions
 finished+0.045
 healthier+0.040
 longer+0.040
 less+0.039
 gust+0.039
Neg logit contributions
fish-0.063
ucer-0.063
unny-0.059
 Area-0.059
 globe-0.057
Token time
Token ID640
Feature activation+1.45e+00

Pos logit contributions
 finished+0.008
whe+0.008
hy+0.007
vious+0.007
 finally+0.007
Neg logit contributions
ucer-0.017
fish-0.016
 Area-0.016
 globe-0.016
aby-0.015
Token a
Token ID257
Feature activation-1.02e+00

Pos logit contributions
ucer+0.003
unny+0.003
 Area+0.003
 globe+0.003
fish+0.003
Neg logit contributions
 finished-0.002
 finally-0.001
 longer-0.001
 finish-0.001
 anymore-0.001
Token man
Token ID582
Feature activation-9.81e-01

Pos logit contributions
 finished+0.025
 finally+0.021
 longer+0.019
 finish+0.017
 less+0.017
Neg logit contributions
ucer-0.044
unny-0.043
 Area-0.041
fish-0.041
 globe-0.040
Token who
Token ID508
Feature activation+5.64e-01

Pos logit contributions
 finished+0.029
 finally+0.025
 longer+0.023
 less+0.022
 finish+0.022
Neg logit contributions
ucer-0.037
unny-0.036
 Area-0.035
 globe-0.034
fish-0.034
Token wore
Token ID12408
Feature activation+1.53e+00

Pos logit contributions
ucer+0.020
 globe+0.019
unny+0.019
fish+0.019
 Area+0.018
Neg logit contributions
 finished-0.017
 longer-0.015
 finally-0.014
 gust-0.014
 anymore-0.013
Token a
Token ID257
Feature activation+8.82e-01

Pos logit contributions
ucer+0.067
 globe+0.063
 Area+0.063
unny+0.062
fish+0.062
Neg logit contributions
 finished-0.034
 finally-0.027
 longer-0.026
 anymore-0.025
 finish-0.024
Token leather
Token ID11620
Feature activation+5.07e+00

Pos logit contributions
ucer+0.036
unny+0.035
 Area+0.034
fish+0.034
 globe+0.033
Neg logit contributions
 finished-0.023
 finally-0.019
 longer-0.018
 anymore-0.017
 less-0.017
Token coat
Token ID13209
Feature activation-2.28e-01

Pos logit contributions
ucer+0.169
 Area+0.165
eway+0.163
unny+0.163
eways+0.152
Neg logit contributions
 finished-0.153
 longer-0.136
 finally-0.130
 at-0.130
 tum-0.130
Token.
Token ID13
Feature activation-6.96e-01

Pos logit contributions
 finished+0.006
 finally+0.005
 gust+0.004
 healthier+0.004
 longer+0.004
Neg logit contributions
ucer-0.009
 globe-0.009
fish-0.009
unny-0.009
 Area-0.009
Token He
Token ID679
Feature activation+7.49e-01

Pos logit contributions
 finished+0.022
 longer+0.017
 finally+0.017
 gust+0.015
 done+0.015
Neg logit contributions
 globe-0.024
unny-0.023
 Area-0.023
ucer-0.022
 fossil-0.022
Token was
Token ID373
Feature activation-3.57e-01

Pos logit contributions
ucer+0.027
fish+0.027
unny+0.027
 globe+0.026
 Area+0.025
Neg logit contributions
 finished-0.021
 anymore-0.018
 longer-0.017
 finally-0.017
 gust-0.017
Token very
Token ID845
Feature activation+3.31e-02

Pos logit contributions
 finished+0.008
 anymore+0.008
 gust+0.007
 finally+0.006
 longer+0.006
Neg logit contributions
ucer-0.013
 Area-0.013
unny-0.013
fish-0.012
 globe-0.012
Token toys
Token ID14958
Feature activation-5.38e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.012
 less+0.012
 anymore+0.012
Neg logit contributions
ucer-0.014
unny-0.014
 Area-0.013
fish-0.013
 globe-0.012
Token back
Token ID736
Feature activation-4.12e-01

Pos logit contributions
 finished+0.013
 gust+0.011
 finally+0.010
 rum+0.010
 longer+0.009
Neg logit contributions
ucer-0.023
fish-0.021
 globe-0.021
unny-0.021
 Area-0.021
Token in
Token ID287
Feature activation+5.42e-01

Pos logit contributions
 finished+0.011
 finally+0.009
 gust+0.009
 longer+0.009
 finish+0.008
Neg logit contributions
ucer-0.017
unny-0.016
 globe-0.015
fish-0.015
 Area-0.015
Token the
Token ID262
Feature activation+6.28e-01

Pos logit contributions
ucer+0.027
 globe+0.026
unny+0.025
 Area+0.025
fish+0.024
Neg logit contributions
 finished-0.009
 finally-0.007
 longer-0.006
 gust-0.006
 bra-0.005
Token organized
Token ID8389
Feature activation+2.32e+00

Pos logit contributions
unny+0.016
ucer+0.015
fish+0.015
 Area+0.014
ark+0.014
Neg logit contributions
 finished-0.028
 finally-0.024
 finish-0.023
 less-0.023
 more-0.023
Token leather
Token ID11620
Feature activation+5.07e+00

Pos logit contributions
ucer+0.065
unny+0.060
 Area+0.058
 globe+0.057
fish+0.057
Neg logit contributions
 finished-0.092
 finally-0.082
 longer-0.077
 less-0.074
 gust-0.074
Token box
Token ID3091
Feature activation+1.29e+00

Pos logit contributions
ucer+0.156
unny+0.153
 Area+0.148
fish+0.141
 globe+0.136
Neg logit contributions
 finished-0.182
 finally-0.159
 longer-0.150
 anymore-0.148
 finish-0.144
Token.
Token ID13
Feature activation-4.73e-01

Pos logit contributions
ucer+0.057
fish+0.054
 globe+0.053
unny+0.053
 Area+0.051
Neg logit contributions
 finished-0.029
 finally-0.023
 gust-0.023
 rum-0.021
 bra-0.020
Token They
Token ID1119
Feature activation+1.04e+00

Pos logit contributions
 finished+0.012
 finally+0.010
 longer+0.009
 anymore+0.009
 less+0.008
Neg logit contributions
ucer-0.020
unny-0.019
 Area-0.019
 globe-0.018
fish-0.018
Token were
Token ID547
Feature activation-7.78e-01

Pos logit contributions
ucer+0.044
unny+0.041
 globe+0.040
fish+0.040
 Area+0.039
Neg logit contributions
 finished-0.021
 anymore-0.020
 less-0.019
 gust-0.018
 healthier-0.018
Token happy
Token ID3772
Feature activation+5.03e-01

Pos logit contributions
 gust+0.017
 finished+0.015
obb+0.015
vious+0.015
 anymore+0.015
Neg logit contributions
ucer-0.025
 globe-0.024
unny-0.023
 Area-0.022
aby-0.022
Token find
Token ID1064
Feature activation+3.25e-01

Pos logit contributions
ucer+0.006
fish+0.005
unny+0.005
 appearances+0.005
ox+0.005
Neg logit contributions
 finished-0.004
 gust-0.004
 finally-0.004
 anymore-0.004
 longer-0.003
Token a
Token ID257
Feature activation+9.53e-02

Pos logit contributions
ucer+0.014
unny+0.013
 Area+0.012
fish+0.012
 globe+0.012
Neg logit contributions
 finished-0.007
 finally-0.006
 gust-0.006
 rum-0.005
 longer-0.005
Token use
Token ID779
Feature activation+1.26e+00

Pos logit contributions
ucer+0.004
unny+0.003
 Area+0.003
 globe+0.003
fish+0.003
Neg logit contributions
 finished-0.003
 finally-0.002
 longer-0.002
 anymore-0.002
 gust-0.002
Token for
Token ID329
Feature activation-5.75e-01

Pos logit contributions
ucer+0.052
unny+0.049
fish+0.049
 Area+0.047
 globe+0.047
Neg logit contributions
 finished-0.031
 finally-0.026
 gust-0.025
 rum-0.023
 longer-0.021
Token the
Token ID262
Feature activation+3.50e-01

Pos logit contributions
 finished+0.014
 finally+0.012
 gust+0.011
 rum+0.010
 finish+0.010
Neg logit contributions
ucer-0.022
fish-0.020
 Area-0.020
 appearances-0.020
unny-0.020
Token leather
Token ID11620
Feature activation+4.98e+00

Pos logit contributions
ucer+0.011
 globe+0.010
fish+0.010
unny+0.010
 Area+0.010
Neg logit contributions
 finished-0.012
 finally-0.010
 gust-0.009
 anymore-0.009
 longer-0.009
Token.
Token ID13
Feature activation+5.70e-01

Pos logit contributions
ucer+0.177
unny+0.168
fish+0.162
 Area+0.161
 globe+0.161
Neg logit contributions
 finished-0.162
 finally-0.139
 longer-0.127
 gust-0.123
 finish-0.121
Token
Token ID198
Feature activation+9.85e-01

Pos logit contributions
unny+0.021
ucer+0.021
 Area+0.021
 globe+0.019
oris+0.018
Neg logit contributions
 finished-0.016
 finally-0.013
 longer-0.013
 gust-0.012
 even-0.012
Token
Token ID198
Feature activation+1.36e+00

Pos logit contributions
ucer+0.043
unny+0.041
 Area+0.040
fish+0.040
 globe+0.040
Neg logit contributions
 finished-0.024
 finally-0.020
 longer-0.017
 less-0.016
 finish-0.016
TokenTom
Token ID13787
Feature activation+3.92e-01

Pos logit contributions
ucer+0.053
unny+0.051
 Area+0.050
fish+0.049
 globe+0.049
Neg logit contributions
 finished-0.040
 finally-0.033
 longer-0.031
 less-0.029
 finish-0.029
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
unny+0.015
ucer+0.015
fish+0.014
 globe+0.014
ox+0.014
Neg logit contributions
 finished-0.009
 longer-0.008
 gust-0.008
 anymore-0.008
 healthier-0.008
Token of
Token ID286
Feature activation-8.11e-01

Pos logit contributions
fish+0.037
ucer+0.036
unny+0.036
 Area+0.034
 globe+0.033
Neg logit contributions
 finished-0.022
 finally-0.021
 rum-0.019
 gust-0.019
 sweaty-0.017
Token fun
Token ID1257
Feature activation+7.35e-01

Pos logit contributions
 finished+0.013
 finally+0.010
 longer+0.008
 anymore+0.007
 gust+0.007
Neg logit contributions
ucer-0.040
unny-0.039
 Area-0.039
fish-0.038
 globe-0.038
Token playing
Token ID2712
Feature activation+5.46e-01

Pos logit contributions
ucer+0.037
unny+0.036
 Area+0.035
 globe+0.034
fish+0.034
Neg logit contributions
 finished-0.014
 finally-0.010
 longer-0.009
 anymore-0.008
 even-0.008
Token with
Token ID351
Feature activation+1.29e+00

Pos logit contributions
ucer+0.022
 Area+0.021
unny+0.021
fish+0.021
 globe+0.021
Neg logit contributions
 finished-0.015
 finally-0.012
 longer-0.011
 gust-0.011
 rum-0.010
Token the
Token ID262
Feature activation+5.10e-01

Pos logit contributions
ucer+0.068
unny+0.066
 Area+0.064
fish+0.064
 globe+0.063
Neg logit contributions
 finished-0.020
 finally-0.014
 longer-0.011
 finish-0.010
 gust-0.010
Token leather
Token ID11620
Feature activation+4.93e+00

Pos logit contributions
ucer+0.016
unny+0.015
 Area+0.015
fish+0.014
 globe+0.014
Neg logit contributions
 finished-0.019
 finally-0.017
 longer-0.016
 finish-0.015
 less-0.015
Token ball
Token ID2613
Feature activation+1.46e+00

Pos logit contributions
ucer+0.150
unny+0.142
 Area+0.138
fish+0.131
 globe+0.131
Neg logit contributions
 finished-0.184
 finally-0.163
 longer-0.154
 anymore-0.148
 finish-0.147
Token and
Token ID290
Feature activation+2.85e-01

Pos logit contributions
fish+0.063
ucer+0.062
unny+0.061
 globe+0.060
fly+0.059
Neg logit contributions
 finished-0.032
 finally-0.025
 gust-0.022
 rum-0.021
 finish-0.021
Token they
Token ID484
Feature activation+6.28e-01

Pos logit contributions
ucer+0.011
fish+0.011
 globe+0.011
unny+0.011
 Area+0.011
Neg logit contributions
 finished-0.007
 finally-0.006
 longer-0.006
 gust-0.005
 anymore-0.005
Token were
Token ID547
Feature activation-4.56e-01

Pos logit contributions
ucer+0.027
fish+0.027
unny+0.026
 globe+0.025
fly+0.024
Neg logit contributions
 finished-0.012
 gust-0.010
 anymore-0.010
 healthier-0.010
 less-0.010
Token very
Token ID845
Feature activation+2.78e-01

Pos logit contributions
 finished+0.010
 gust+0.009
 rum+0.008
 anymore+0.008
obb+0.007
Neg logit contributions
ucer-0.017
fish-0.016
unny-0.016
 globe-0.016
fly-0.015
Token the
Token ID262
Feature activation-2.21e-01

Pos logit contributions
 finished+0.011
 sweaty+0.008
 finally+0.007
 gust+0.007
 longer+0.007
Neg logit contributions
 globe-0.022
ucer-0.022
fish-0.022
 Area-0.022
unny-0.021
Token man
Token ID582
Feature activation+3.64e-01

Pos logit contributions
 finished+0.007
 finally+0.006
 longer+0.006
 anymore+0.006
 gust+0.006
Neg logit contributions
ucer-0.008
unny-0.007
 Area-0.007
 globe-0.007
fish-0.007
Token,
Token ID11
Feature activation+3.71e-01

Pos logit contributions
ucer+0.016
unny+0.015
 globe+0.015
fish+0.015
 Area+0.014
Neg logit contributions
 finished-0.008
 finally-0.007
 gust-0.006
 longer-0.006
 sweaty-0.006
Token grabbed
Token ID13176
Feature activation+4.41e-01

Pos logit contributions
ucer+0.013
unny+0.013
 Area+0.013
 globe+0.013
fish+0.012
Neg logit contributions
 finished-0.009
 anymore-0.008
 gust-0.007
 finally-0.007
 longer-0.007
Token the
Token ID262
Feature activation+8.02e-01

Pos logit contributions
ucer+0.020
unny+0.019
 Area+0.019
 globe+0.019
fish+0.018
Neg logit contributions
 finished-0.009
 finally-0.006
 gust-0.006
 anymore-0.006
 longer-0.006
Token leather
Token ID11620
Feature activation+4.90e+00

Pos logit contributions
ucer+0.028
unny+0.027
 Area+0.026
fish+0.026
 globe+0.025
Neg logit contributions
 finished-0.027
 finally-0.023
 longer-0.022
 finish-0.021
 less-0.021
Token shape
Token ID5485
Feature activation+1.22e+00

Pos logit contributions
ucer+0.221
unny+0.214
 Area+0.210
fish+0.205
 globe+0.204
Neg logit contributions
 finished-0.109
 finally-0.088
 longer-0.079
 less-0.073
 finish-0.073
Token,
Token ID11
Feature activation+5.41e-01

Pos logit contributions
ucer+0.050
fish+0.049
 globe+0.048
unny+0.047
 Area+0.045
Neg logit contributions
 finished-0.030
 finally-0.024
 gust-0.022
 sweaty-0.020
 longer-0.020
Token and
Token ID290
Feature activation+3.34e-02

Pos logit contributions
ucer+0.020
 globe+0.020
 telescope+0.019
fish+0.019
 compass+0.019
Neg logit contributions
 finished-0.013
 anymore-0.012
 gust-0.011
 rum-0.010
 finally-0.010
Token ran
Token ID4966
Feature activation-5.84e-01

Pos logit contributions
ucer+0.001
fish+0.001
 globe+0.001
unny+0.001
 compass+0.001
Neg logit contributions
 anymore-0.001
 finished-0.001
 gust-0.001
 miserable-0.001
 longer-0.001
Token off
Token ID572
Feature activation+1.05e+00

Pos logit contributions
 finished+0.014
 gust+0.012
 scr+0.011
 sweaty+0.011
 especially+0.011
Neg logit contributions
ucer-0.023
 Area-0.022
unny-0.022
 globe-0.021
eway-0.020
Tokenand
Token ID392
Feature activation+6.39e-01

Pos logit contributions
ucer+0.001
unny+0.001
 Area+0.001
fish+0.001
 globe+0.001
Neg logit contributions
 finished-0.001
 finally-0.001
 longer-0.001
 less-0.001
 finish-0.001
Token-
Token ID12
Feature activation+4.44e-01

Pos logit contributions
ucer+0.024
unny+0.023
 Area+0.023
fish+0.022
 globe+0.022
Neg logit contributions
 finished-0.019
 finally-0.016
 longer-0.015
 finish-0.014
 less-0.014
Tokenseek
Token ID36163
Feature activation+1.12e+00

Pos logit contributions
ucer+0.014
unny+0.013
 Area+0.013
fish+0.013
 globe+0.012
Neg logit contributions
 finished-0.016
 finally-0.014
 gust-0.013
 longer-0.013
 less-0.013
Token behind
Token ID2157
Feature activation+7.45e-01

Pos logit contributions
fish+0.043
ucer+0.042
 Area+0.042
 globe+0.041
unny+0.041
Neg logit contributions
 finished-0.028
 finally-0.023
 gust-0.022
 finish-0.020
 bra-0.020
Token the
Token ID262
Feature activation+7.58e-01

Pos logit contributions
ucer+0.033
 Area+0.032
 globe+0.032
unny+0.032
fish+0.031
Neg logit contributions
 finished-0.015
 finally-0.011
 longer-0.010
 gust-0.010
 bra-0.010
Token old
Token ID1468
Feature activation+4.89e+00

Pos logit contributions
ucer+0.025
unny+0.023
 Area+0.023
 globe+0.022
fish+0.022
Neg logit contributions
 finished-0.026
 finally-0.023
 longer-0.022
 less-0.021
 anymore-0.020
Token barn
Token ID25203
Feature activation+2.32e+00

Pos logit contributions
ucer+0.177
unny+0.170
 Area+0.163
fish+0.160
 globe+0.159
Neg logit contributions
 finished-0.155
 finally-0.133
 longer-0.123
 finish-0.117
 less-0.117
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
ucer+0.099
 Area+0.094
 globe+0.094
unny+0.093
fish+0.093
Neg logit contributions
 finished-0.053
 finally-0.041
 gust-0.040
 longer-0.039
 healthier-0.037
Token While
Token ID2893
Feature activation+1.77e+00

Pos logit contributions
 finished+0.012
 finally+0.010
 longer+0.010
 less+0.009
 healthier+0.009
Neg logit contributions
ucer-0.016
unny-0.016
 Area-0.016
 globe-0.015
fish-0.014
Token they
Token ID484
Feature activation-1.46e+00

Pos logit contributions
ucer+0.069
unny+0.066
 Area+0.065
fish+0.064
 globe+0.063
Neg logit contributions
 finished-0.050
 finally-0.042
 longer-0.039
 less-0.037
 finish-0.037
Token were
Token ID547
Feature activation-6.27e-01

Pos logit contributions
 finished+0.030
 less+0.026
 gust+0.026
 healthier+0.026
 longer+0.025
Neg logit contributions
unny-0.060
ucer-0.060
fish-0.058
 Area-0.058
 globe-0.056
Token had
Token ID550
Feature activation+8.40e-01

Pos logit contributions
ucer+0.027
unny+0.026
fish+0.026
 globe+0.025
 Area+0.025
Neg logit contributions
 finished-0.014
 finally-0.011
 longer-0.011
 less-0.010
 gust-0.010
Token been
Token ID587
Feature activation+5.43e-01

Pos logit contributions
ucer+0.035
unny+0.034
 Area+0.034
fish+0.032
 globe+0.032
Neg logit contributions
 finished-0.017
 gust-0.015
 finally-0.014
 longer-0.014
 anymore-0.013
Token hidden
Token ID7104
Feature activation-2.86e-02

Pos logit contributions
ucer+0.019
 Area+0.019
unny+0.018
fish+0.018
eds+0.017
Neg logit contributions
 finished-0.014
 gust-0.013
 finally-0.012
 anymore-0.012
 rum-0.012
Token inside
Token ID2641
Feature activation+1.54e+00

Pos logit contributions
 finished+0.001
 finally+0.001
 gust+0.001
 finish+0.001
 rum+0.000
Neg logit contributions
ucer-0.001
unny-0.001
fish-0.001
 Area-0.001
 globe-0.001
Token the
Token ID262
Feature activation+4.75e-01

Pos logit contributions
ucer+0.065
 Area+0.063
 globe+0.062
fish+0.062
unny+0.062
Neg logit contributions
 finished-0.035
 finally-0.027
 gust-0.027
 bra-0.024
 rum-0.023
Token plastic
Token ID7309
Feature activation+4.84e+00

Pos logit contributions
ucer+0.014
 globe+0.014
 Area+0.013
unny+0.013
fish+0.013
Neg logit contributions
 finished-0.017
 finally-0.015
 longer-0.014
 gust-0.014
 bra-0.013
Token eggs
Token ID9653
Feature activation-8.24e-01

Pos logit contributions
ucer+0.161
unny+0.153
 Area+0.148
fish+0.144
 globe+0.144
Neg logit contributions
 finished-0.166
 finally-0.145
 longer-0.136
 less-0.130
 finish-0.129
Token.
Token ID13
Feature activation-4.78e-01

Pos logit contributions
 finished+0.017
 finally+0.014
 gust+0.012
 longer+0.012
 bra+0.011
Neg logit contributions
ucer-0.038
fish-0.036
unny-0.036
 globe-0.035
 Area-0.035
Token
Token ID198
Feature activation-3.58e-02

Pos logit contributions
 finished+0.011
 finally+0.009
 longer+0.007
 less+0.007
 finish+0.007
Neg logit contributions
ucer-0.022
unny-0.021
fish-0.021
 Area-0.020
 globe-0.020
Token
Token ID198
Feature activation+2.37e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 even+0.000
 about+0.000
 much+0.000
Neg logit contributions
ucer-0.002
unny-0.002
fish-0.002
 Area-0.002
 globe-0.002
TokenThe
Token ID464
Feature activation-1.16e+00

Pos logit contributions
ucer+0.009
unny+0.008
 globe+0.008
fish+0.008
 Area+0.008
Neg logit contributions
 finished-0.008
 finally-0.007
 longer-0.006
 even-0.006
 finish-0.006
Token saw
Token ID2497
Feature activation-5.15e-01

Pos logit contributions
ucer+0.002
unny+0.002
fish+0.002
 Area+0.002
ox+0.002
Neg logit contributions
 finished-0.002
 longer-0.001
 gust-0.001
 less-0.001
 healthier-0.001
Token a
Token ID257
Feature activation+1.40e-01

Pos logit contributions
 finished+0.011
 finally+0.008
 longer+0.007
 finish+0.007
 anymore+0.007
Neg logit contributions
ucer-0.024
unny-0.023
 Area-0.022
fish-0.022
 globe-0.022
Token man
Token ID582
Feature activation-1.15e+00

Pos logit contributions
ucer+0.006
unny+0.006
 Area+0.006
fish+0.005
 globe+0.005
Neg logit contributions
 finished-0.004
 finally-0.003
 longer-0.003
 gust-0.002
 finish-0.002
Token with
Token ID351
Feature activation+1.38e+00

Pos logit contributions
 finished+0.031
 finally+0.026
 gust+0.024
 longer+0.023
 less+0.023
Neg logit contributions
ucer-0.044
fish-0.042
 Area-0.042
unny-0.042
 globe-0.041
Token a
Token ID257
Feature activation+1.11e+00

Pos logit contributions
ucer+0.045
 appearances+0.043
 compass+0.043
 telescope+0.042
 globe+0.042
Neg logit contributions
 finished-0.039
 anymore-0.034
 longer-0.032
 finally-0.032
 finish-0.031
Token leather
Token ID11620
Feature activation+4.81e+00

Pos logit contributions
ucer+0.041
unny+0.039
 globe+0.038
 Area+0.038
fish+0.038
Neg logit contributions
 finished-0.033
 finally-0.029
 longer-0.027
 anymore-0.025
 less-0.025
Token jacket
Token ID15224
Feature activation+7.11e-01

Pos logit contributions
ucer+0.150
unny+0.145
 Area+0.144
eway+0.134
 globe+0.132
Neg logit contributions
 finished-0.168
 finally-0.146
 longer-0.142
 at-0.137
 even-0.134
Token and
Token ID290
Feature activation+1.85e-01

Pos logit contributions
ucer+0.030
 globe+0.028
fish+0.028
 Area+0.027
unny+0.027
Neg logit contributions
 finished-0.018
 finally-0.014
 healthier-0.014
 longer-0.014
 less-0.013
Token a
Token ID257
Feature activation+3.21e-01

Pos logit contributions
ucer+0.008
unny+0.008
fish+0.008
 Area+0.008
 globe+0.007
Neg logit contributions
 finished-0.004
 finally-0.003
 longer-0.003
 anymore-0.003
 finish-0.003
Token shiny
Token ID22441
Feature activation+1.86e+00

Pos logit contributions
ucer+0.011
unny+0.011
 Area+0.010
fish+0.010
 globe+0.010
Neg logit contributions
 finished-0.011
 finally-0.009
 longer-0.008
 anymore-0.008
 finish-0.008
Token bike
Token ID7161
Feature activation-1.06e+00

Pos logit contributions
ucer+0.058
unny+0.055
 Area+0.053
fish+0.053
 globe+0.052
Neg logit contributions
 finished-0.067
 finally-0.059
 longer-0.055
 less-0.052
 finish-0.052
Token he
Token ID339
Feature activation-1.54e-01

Pos logit contributions
 finished+0.023
 finally+0.018
 longer+0.017
 finish+0.017
 anymore+0.017
Neg logit contributions
ucer-0.032
unny-0.032
fish-0.031
 Area-0.030
 globe-0.030
Token was
Token ID373
Feature activation+1.14e-01

Pos logit contributions
 finished+0.004
 longer+0.004
 anymore+0.004
 healthier+0.004
 gust+0.004
Neg logit contributions
fish-0.005
unny-0.005
fly-0.005
ucer-0.005
 Area-0.005
Token wearing
Token ID5762
Feature activation+1.62e+00

Pos logit contributions
fly+0.004
 Area+0.004
fish+0.004
ucer+0.004
unny+0.004
Neg logit contributions
 finished-0.003
 gust-0.003
obb-0.002
 finish-0.002
 healthier-0.002
Token a
Token ID257
Feature activation+9.15e-01

Pos logit contributions
ucer+0.066
 globe+0.064
 Area+0.062
fish+0.062
unny+0.061
Neg logit contributions
 finished-0.039
 finally-0.031
 finish-0.028
 longer-0.028
 gust-0.027
Token blue
Token ID4171
Feature activation+2.43e+00

Pos logit contributions
ucer+0.034
unny+0.032
fish+0.031
 Area+0.031
 globe+0.031
Neg logit contributions
 finished-0.027
 finally-0.023
 longer-0.021
 anymore-0.021
 finish-0.020
Token leather
Token ID11620
Feature activation+4.80e+00

Pos logit contributions
ucer+0.076
unny+0.072
 Area+0.070
fish+0.068
 globe+0.068
Neg logit contributions
 finished-0.088
 finally-0.078
 longer-0.073
 less-0.070
 finish-0.069
Token jacket
Token ID15224
Feature activation+7.37e-01

Pos logit contributions
ucer+0.150
unny+0.144
 Area+0.141
 globe+0.131
fish+0.130
Neg logit contributions
 finished-0.171
 finally-0.150
 longer-0.145
 even-0.136
 finish-0.136
Token.
Token ID13
Feature activation-6.26e-01

Pos logit contributions
ucer+0.031
fish+0.030
 globe+0.030
unny+0.029
 Area+0.028
Neg logit contributions
 finished-0.018
 finally-0.014
 gust-0.014
 healthier-0.013
 longer-0.012
Token "
Token ID366
Feature activation-7.57e-01

Pos logit contributions
 finished+0.017
 finally+0.014
 longer+0.013
 finish+0.012
 less+0.012
Neg logit contributions
ucer-0.025
unny-0.025
 Area-0.024
 globe-0.023
fish-0.023
TokenGo
Token ID5247
Feature activation-8.35e-01

Pos logit contributions
 finished+0.025
 finally+0.022
 longer+0.021
 less+0.020
 finish+0.020
Neg logit contributions
ucer-0.026
unny-0.025
 Area-0.024
fish-0.023
 globe-0.023
Token away
Token ID1497
Feature activation+1.76e+00

Pos logit contributions
 finished+0.021
 finally+0.017
 longer+0.015
 finish+0.014
 even+0.014
Neg logit contributions
ucer-0.036
unny-0.035
 Area-0.034
fish-0.034
 globe-0.033
Token she
Token ID673
Feature activation-1.37e+00

Pos logit contributions
 finished+0.001
 anymore+0.001
 gust+0.001
 itch+0.001
 healthier+0.001
Neg logit contributions
ucer-0.001
 telescope-0.001
unny-0.001
 globe-0.001
 Area-0.001
Token reached
Token ID4251
Feature activation-3.11e-01

Pos logit contributions
 anymore+0.037
 healthier+0.032
 less+0.032
 finished+0.031
 gust+0.030
Neg logit contributions
fish-0.048
ucer-0.046
unny-0.046
fly-0.045
 Area-0.044
Token into
Token ID656
Feature activation-5.19e-01

Pos logit contributions
 finished+0.008
 gust+0.007
 anymore+0.007
 finally+0.007
 longer+0.007
Neg logit contributions
ucer-0.012
unny-0.011
 telescope-0.011
 Area-0.011
fish-0.011
Token the
Token ID262
Feature activation+2.24e-01

Pos logit contributions
 finished+0.010
 finally+0.007
 anymore+0.007
 gust+0.006
 longer+0.006
Neg logit contributions
ucer-0.024
 Area-0.023
 globe-0.023
unny-0.023
 telescope-0.022
Token old
Token ID1468
Feature activation+3.19e+00

Pos logit contributions
ucer+0.007
 Area+0.006
unny+0.006
 globe+0.006
fish+0.006
Neg logit contributions
 finished-0.008
 finally-0.007
 longer-0.007
 anymore-0.006
 even-0.006
Token leather
Token ID11620
Feature activation+4.79e+00

Pos logit contributions
ucer+0.101
unny+0.094
 globe+0.093
 Area+0.093
fish+0.092
Neg logit contributions
 finished-0.113
 finally-0.100
 longer-0.093
 less-0.089
 anymore-0.089
Token bag
Token ID6131
Feature activation+8.32e-03

Pos logit contributions
ucer+0.152
unny+0.146
 Area+0.141
fish+0.136
 globe+0.135
Neg logit contributions
 finished-0.171
 finally-0.149
 longer-0.142
 finish-0.135
 less-0.135
Token and
Token ID290
Feature activation-4.43e-01

Pos logit contributions
ucer+0.000
fish+0.000
unny+0.000
 globe+0.000
 Area+0.000
Neg logit contributions
 finished-0.000
 gust-0.000
 finally-0.000
 sweaty-0.000
 miserable-0.000
Token pulled
Token ID5954
Feature activation-1.09e-01

Pos logit contributions
 anymore+0.012
 finished+0.011
 longer+0.010
 gust+0.010
 less+0.009
Neg logit contributions
ucer-0.016
unny-0.015
fish-0.015
 Area-0.015
 globe-0.014
Token out
Token ID503
Feature activation-2.36e-01

Pos logit contributions
 finished+0.003
 finally+0.002
 gust+0.002
 sweaty+0.002
 longer+0.002
Neg logit contributions
ucer-0.004
unny-0.004
 Area-0.004
 globe-0.004
oris-0.004
Token a
Token ID257
Feature activation+5.15e-01

Pos logit contributions
 finished+0.005
 finally+0.004
 gust+0.003
 longer+0.003
 finish+0.003
Neg logit contributions
ucer-0.011
unny-0.010
 Area-0.010
 globe-0.010
fish-0.010
Token to
Token ID284
Feature activation+8.76e-02

Pos logit contributions
 finished+0.001
 finally+0.001
 gust+0.001
 longer+0.001
 finish+0.001
Neg logit contributions
ucer-0.001
unny-0.001
 Area-0.001
fish-0.001
 globe-0.001
Token a
Token ID257
Feature activation+6.21e-01

Pos logit contributions
ucer+0.004
unny+0.004
 globe+0.004
 Area+0.004
fish+0.004
Neg logit contributions
 finished-0.002
 finally-0.001
 longer-0.001
 anymore-0.001
 gust-0.001
Token tear
Token ID11626
Feature activation+9.10e-01

Pos logit contributions
ucer+0.020
unny+0.019
 Area+0.018
fish+0.018
 globe+0.018
Neg logit contributions
 finished-0.022
 finally-0.019
 longer-0.018
 less-0.017
 finish-0.017
Token in
Token ID287
Feature activation-3.18e-01

Pos logit contributions
ucer+0.038
fish+0.036
unny+0.035
 globe+0.035
 Area+0.035
Neg logit contributions
 finished-0.024
 finally-0.020
 longer-0.018
 healthier-0.017
 finish-0.017
Token the
Token ID262
Feature activation+1.50e-01

Pos logit contributions
 finished+0.006
 finally+0.004
 longer+0.004
 gust+0.004
 finish+0.004
Neg logit contributions
ucer-0.015
unny-0.015
 globe-0.015
 Area-0.014
fish-0.014
Token leather
Token ID11620
Feature activation+4.78e+00

Pos logit contributions
ucer+0.004
unny+0.004
 Area+0.004
fish+0.004
 globe+0.004
Neg logit contributions
 finished-0.006
 finally-0.005
 longer-0.005
 less-0.005
 finish-0.005
Token.
Token ID13
Feature activation+3.04e-02

Pos logit contributions
ucer+0.140
unny+0.136
 Area+0.135
fish+0.124
 globe+0.123
Neg logit contributions
 finished-0.173
 finally-0.152
 longer-0.147
 anymore-0.143
 finish-0.142
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
ucer+0.001
unny+0.001
 Area+0.001
fish+0.001
 globe+0.001
Neg logit contributions
 finished-0.001
 finally-0.001
 longer-0.001
 less-0.001
 finish-0.001
Token
Token ID198
Feature activation+8.40e-01

Pos logit contributions
ucer+0.009
unny+0.009
fish+0.009
 Area+0.009
 globe+0.008
Neg logit contributions
 finished-0.003
 finally-0.003
 longer-0.002
 even-0.002
 less-0.002
Token"
Token ID1
Feature activation-3.11e-01

Pos logit contributions
ucer+0.032
 globe+0.029
fish+0.029
unny+0.028
 Area+0.028
Neg logit contributions
 finished-0.025
 finally-0.022
 finish-0.020
 longer-0.020
 less-0.019
TokenMaybe
Token ID13300
Feature activation-1.82e+00

Pos logit contributions
 finished+0.010
 finally+0.009
 less+0.008
 longer+0.008
 bra+0.007
Neg logit contributions
ucer-0.012
unny-0.011
 Area-0.010
fish-0.010
 globe-0.010
Token of
Token ID286
Feature activation-3.35e-02

Pos logit contributions
ucer+0.005
unny+0.004
fish+0.004
 globe+0.004
 Area+0.004
Neg logit contributions
 finished-0.002
 finally-0.002
 gust-0.001
 longer-0.001
 finish-0.001
Token the
Token ID262
Feature activation+1.44e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 gust+0.001
 anymore+0.001
Neg logit contributions
ucer-0.001
 globe-0.001
fish-0.001
unny-0.001
 Area-0.001
Token mel
Token ID7758
Feature activation+3.16e-01

Pos logit contributions
ucer+0.005
unny+0.005
 globe+0.005
 Area+0.004
fish+0.004
Neg logit contributions
 finished-0.005
 finally-0.004
 longer-0.004
 anymore-0.004
 gust-0.004
Tokenon
Token ID261
Feature activation+7.99e-01

Pos logit contributions
ucer+0.011
unny+0.010
 Area+0.010
fish+0.010
 globe+0.009
Neg logit contributions
 finished-0.011
 finally-0.010
 longer-0.009
 gust-0.009
 less-0.009
Token in
Token ID287
Feature activation+2.61e-01

Pos logit contributions
ucer+0.036
unny+0.034
fish+0.034
 globe+0.033
 Area+0.033
Neg logit contributions
 finished-0.018
 finally-0.015
 gust-0.013
 longer-0.013
 finish-0.012
Token plastic
Token ID7309
Feature activation+4.74e+00

Pos logit contributions
ucer+0.012
 globe+0.011
unny+0.011
 Area+0.011
fish+0.011
Neg logit contributions
 finished-0.005
 finally-0.004
 anymore-0.004
 gust-0.004
 bra-0.003
Token and
Token ID290
Feature activation+6.45e-02

Pos logit contributions
ucer+0.187
unny+0.179
 Area+0.174
fish+0.172
 globe+0.172
Neg logit contributions
 finished-0.134
 finally-0.113
 longer-0.103
 gust-0.097
 less-0.096
Token put
Token ID1234
Feature activation-9.22e-02

Pos logit contributions
ucer+0.002
fish+0.002
 globe+0.002
fly+0.002
 magn+0.002
Neg logit contributions
 anymore-0.002
 gust-0.001
 longer-0.001
 finished-0.001
vious-0.001
Token it
Token ID340
Feature activation-4.10e-01

Pos logit contributions
 finished+0.003
 gust+0.002
 especially+0.002
 finally+0.002
 finish+0.002
Neg logit contributions
ucer-0.003
 globe-0.003
fish-0.003
 Area-0.003
unny-0.003
Token in
Token ID287
Feature activation-1.73e-01

Pos logit contributions
 finished+0.011
 gust+0.010
 finally+0.009
 Dr+0.009
 rum+0.009
Neg logit contributions
ucer-0.015
fish-0.014
 globe-0.014
unny-0.014
 Area-0.013
Token the
Token ID262
Feature activation+2.92e-01

Pos logit contributions
 finished+0.004
 gust+0.003
 finally+0.003
 bra+0.002
 anymore+0.002
Neg logit contributions
ucer-0.008
 globe-0.007
 Area-0.007
unny-0.007
 telescope-0.007
Token The
Token ID383
Feature activation-3.60e-01

Pos logit contributions
 finished+0.010
 finally+0.008
 longer+0.007
 less+0.007
 finish+0.007
Neg logit contributions
ucer-0.019
unny-0.018
 Area-0.018
fish-0.018
 globe-0.018
Token man
Token ID582
Feature activation-4.25e-01

Pos logit contributions
 finished+0.012
 finally+0.011
 longer+0.010
 anymore+0.010
 less+0.009
Neg logit contributions
ucer-0.012
unny-0.011
 Area-0.011
fish-0.011
 globe-0.011
Token was
Token ID373
Feature activation+6.81e-02

Pos logit contributions
 finished+0.011
 longer+0.010
 anymore+0.010
 finish+0.009
 healthier+0.009
Neg logit contributions
fish-0.015
fly-0.015
unny-0.014
ucer-0.014
 globe-0.014
Token wearing
Token ID5762
Feature activation+1.81e+00

Pos logit contributions
 Area+0.002
fly+0.002
unny+0.002
ucer+0.002
 recorder+0.002
Neg logit contributions
 finished-0.002
 anymore-0.002
 longer-0.002
 finally-0.002
 gust-0.002
Token a
Token ID257
Feature activation+8.99e-01

Pos logit contributions
 globe+0.068
ucer+0.067
 Area+0.063
 fossil+0.062
 telescope+0.062
Neg logit contributions
 finished-0.047
 finally-0.038
 longer-0.037
 finish-0.036
 anymore-0.035
Token leather
Token ID11620
Feature activation+4.74e+00

Pos logit contributions
ucer+0.034
unny+0.033
 Area+0.032
fish+0.032
 globe+0.031
Neg logit contributions
 finished-0.026
 finally-0.022
 longer-0.021
 less-0.019
 finish-0.019
Token jacket
Token ID15224
Feature activation+7.81e-01

Pos logit contributions
ucer+0.152
unny+0.147
 Area+0.144
eway+0.133
 globe+0.130
Neg logit contributions
 finished-0.164
 finally-0.142
 longer-0.138
 at-0.130
 anymore-0.129
Token.
Token ID13
Feature activation-5.66e-01

Pos logit contributions
ucer+0.031
 globe+0.030
fish+0.030
fly+0.028
 Area+0.028
Neg logit contributions
 finished-0.020
 gust-0.016
 finally-0.016
 healthier-0.016
 longer-0.015
Token Alex
Token ID4422
Feature activation+1.43e+00

Pos logit contributions
 finished+0.015
 finally+0.012
 longer+0.011
 less+0.010
 finish+0.010
Neg logit contributions
ucer-0.024
unny-0.023
 Area-0.022
fish-0.022
 globe-0.022
Token thought
Token ID1807
Feature activation+1.09e+00

Pos logit contributions
unny+0.052
fish+0.052
ucer+0.051
 Area+0.050
fly+0.049
Neg logit contributions
 finished-0.038
 longer-0.032
 anymore-0.032
 finally-0.031
 healthier-0.031
Token it
Token ID340
Feature activation-1.69e+00

Pos logit contributions
fish+0.038
 globe+0.035
 Area+0.034
unny+0.034
ucer+0.034
Neg logit contributions
 finished-0.030
 finally-0.025
 longer-0.025
 finish-0.024
thank-0.024
Token excited
Token ID6568
Feature activation-2.09e-01

Pos logit contributions
unny+0.020
ucer+0.019
fish+0.019
 Area+0.019
 appearances+0.017
Neg logit contributions
 finished-0.013
 finally-0.011
 anymore-0.010
 longer-0.010
 gust-0.010
Token to
Token ID284
Feature activation-4.46e-01

Pos logit contributions
 finished+0.005
 finally+0.004
 longer+0.004
 finish+0.004
 gust+0.004
Neg logit contributions
ucer-0.008
fish-0.008
 Area-0.008
unny-0.008
 globe-0.008
Token play
Token ID711
Feature activation+7.29e-02

Pos logit contributions
 finished+0.012
 gust+0.010
 longer+0.010
 anymore+0.010
 finally+0.009
Neg logit contributions
ucer-0.016
unny-0.016
fish-0.016
 Area-0.015
 globe-0.015
Token on
Token ID319
Feature activation-2.11e-01

Pos logit contributions
ucer+0.003
 Area+0.003
unny+0.003
fish+0.003
 globe+0.003
Neg logit contributions
 finished-0.002
 finally-0.002
 gust-0.001
 longer-0.001
 finish-0.001
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
 finished+0.005
 finally+0.003
 gust+0.003
 longer+0.003
 finish+0.003
Neg logit contributions
ucer-0.009
fish-0.009
 globe-0.009
 Area-0.009
unny-0.009
Token velvet
Token ID47750
Feature activation+4.72e+00

Pos logit contributions
ucer+0.033
unny+0.031
 Area+0.030
fish+0.030
 globe+0.030
Neg logit contributions
 finished-0.044
 finally-0.039
 longer-0.037
 less-0.035
 anymore-0.035
Token bed
Token ID3996
Feature activation-2.24e-01

Pos logit contributions
ucer+0.146
unny+0.138
 Area+0.133
fish+0.128
 globe+0.128
Neg logit contributions
 finished-0.174
 finally-0.153
 longer-0.145
 anymore-0.139
 finish-0.138
Token,
Token ID11
Feature activation+2.22e-01

Pos logit contributions
 finished+0.005
 gust+0.004
 sweaty+0.004
 finally+0.004
 frustrated+0.004
Neg logit contributions
fish-0.009
ucer-0.009
 globe-0.008
 Area-0.008
unny-0.008
Token that
Token ID326
Feature activation+1.46e+00

Pos logit contributions
ucer+0.009
 Area+0.009
unny+0.009
fish+0.008
 globe+0.008
Neg logit contributions
 finished-0.005
 finally-0.004
 anymore-0.004
 gust-0.004
 longer-0.004
Token she
Token ID673
Feature activation-7.02e-01

Pos logit contributions
ucer+0.056
fish+0.054
 globe+0.053
unny+0.053
 Area+0.052
Neg logit contributions
 finished-0.038
 longer-0.031
 finally-0.030
 finish-0.028
 gust-0.028
Token hadn
Token ID8020
Feature activation+3.19e-01

Pos logit contributions
 finished+0.018
 finally+0.015
 longer+0.015
 gust+0.014
 anymore+0.014
Neg logit contributions
ucer-0.027
unny-0.027
fish-0.027
 Area-0.026
 globe-0.025
Token girl
Token ID2576
Feature activation-6.66e-01

Pos logit contributions
ucer+0.031
unny+0.029
 Area+0.029
eway+0.027
 globe+0.027
Neg logit contributions
 finished-0.030
 finally-0.025
 longer-0.025
 gust-0.024
 less-0.023
Token who
Token ID508
Feature activation+4.20e-01

Pos logit contributions
 finished+0.018
 finally+0.015
 longer+0.014
 even+0.013
 less+0.013
Neg logit contributions
ucer-0.027
unny-0.026
 Area-0.026
 globe-0.025
fish-0.025
Token didn
Token ID1422
Feature activation-1.71e-01

Pos logit contributions
ucer+0.017
unny+0.016
 Area+0.016
 globe+0.016
fish+0.016
Neg logit contributions
 finished-0.011
 finally-0.009
 longer-0.009
 gust-0.008
 anymore-0.008
Token't
Token ID470
Feature activation+3.64e-01

Pos logit contributions
 finished+0.006
 finally+0.005
 longer+0.005
 less+0.005
 healthier+0.005
Neg logit contributions
ucer-0.006
unny-0.005
 Area-0.005
fish-0.005
 globe-0.005
Token like
Token ID588
Feature activation-1.37e+00

Pos logit contributions
ucer+0.017
unny+0.016
 Area+0.015
fish+0.015
 globe+0.015
Neg logit contributions
 finished-0.008
 finally-0.006
 longer-0.005
 gust-0.005
 anymore-0.005
Token av
Token ID1196
Feature activation-5.40e+00

Pos logit contributions
 finished+0.034
 finally+0.028
 longer+0.026
 finish+0.023
 less+0.023
Neg logit contributions
fish-0.052
 Area-0.052
ucer-0.052
 globe-0.051
unny-0.051
Tokenoc
Token ID420
Feature activation+1.63e+00

Pos logit contributions
 finished+0.247
 finally+0.228
 longer+0.215
 finish+0.209
 gust+0.207
Neg logit contributions
ucer-0.108
unny-0.100
 globe-0.090
fish-0.089
 Area-0.087
Tokenados
Token ID22484
Feature activation-1.73e+00

Pos logit contributions
unny+0.027
ucer+0.027
 appearances+0.026
 Area+0.025
 globe+0.025
Neg logit contributions
 finished-0.075
 finally-0.070
 longer-0.068
 especially-0.067
 even-0.066
Token.
Token ID13
Feature activation-7.13e-01

Pos logit contributions
 finished+0.043
 finally+0.037
 gust+0.036
 longer+0.033
 healthier+0.032
Neg logit contributions
fish-0.068
ucer-0.064
 globe-0.062
 Area-0.061
unny-0.060
Token She
Token ID1375
Feature activation+1.95e-01

Pos logit contributions
 finished+0.019
 finally+0.015
 longer+0.015
 gust+0.013
 bra+0.013
Neg logit contributions
unny-0.029
ucer-0.028
 Area-0.028
 globe-0.027
rooms-0.025
Token always
Token ID1464
Feature activation+6.31e-01

Pos logit contributions
fish+0.006
unny+0.006
ucer+0.006
 globe+0.006
 Area+0.006
Neg logit contributions
 finished-0.006
 healthier-0.005
 less-0.005
 gust-0.005
 longer-0.005
Token something
Token ID1223
Feature activation-2.85e-01

Pos logit contributions
ucer+0.003
 Area+0.003
unny+0.003
fish+0.003
 globe+0.003
Neg logit contributions
 finished-0.002
 finally-0.002
 gust-0.001
 longer-0.001
 finish-0.001
Token new
Token ID649
Feature activation-2.90e-01

Pos logit contributions
 finished+0.007
 finally+0.006
 gust+0.005
 longer+0.005
 finish+0.005
Neg logit contributions
ucer-0.012
fish-0.011
 Area-0.011
unny-0.011
 globe-0.011
Token!
Token ID0
Feature activation-5.54e-01

Pos logit contributions
 finished+0.005
 finally+0.004
 longer+0.004
 less+0.003
 finish+0.003
Neg logit contributions
ucer-0.014
unny-0.014
 Area-0.014
fish-0.013
 globe-0.013
Token She
Token ID1375
Feature activation+1.01e+00

Pos logit contributions
 finished+0.009
 finally+0.008
 less+0.006
 even+0.006
 longer+0.006
Neg logit contributions
ucer-0.028
fish-0.027
 Area-0.026
unny-0.026
 globe-0.026
Token thought
Token ID1807
Feature activation+9.85e-01

Pos logit contributions
fish+0.036
ucer+0.034
unny+0.032
 globe+0.032
fly+0.031
Neg logit contributions
 anymore-0.026
 gust-0.025
 longer-0.023
 finished-0.023
 less-0.022
Token av
Token ID1196
Feature activation-5.15e+00

Pos logit contributions
fish+0.035
ucer+0.034
unny+0.033
 globe+0.032
 Area+0.032
Neg logit contributions
 finished-0.027
 finally-0.022
 longer-0.021
 finish-0.021
 sweaty-0.021
Tokenoc
Token ID420
Feature activation+1.99e+00

Pos logit contributions
 finished+0.223
 finally+0.199
 longer+0.188
 less+0.183
 even+0.182
Neg logit contributions
ucer-0.126
unny-0.119
 Area-0.115
fish-0.111
 globe-0.109
Tokenados
Token ID22484
Feature activation-1.76e+00

Pos logit contributions
ucer+0.059
unny+0.057
 Area+0.054
 globe+0.053
fish+0.053
Neg logit contributions
 finished-0.075
 finally-0.066
 longer-0.063
 finish-0.060
 less-0.060
Token were
Token ID547
Feature activation-7.38e-01

Pos logit contributions
 finished+0.040
 longer+0.033
 finally+0.032
 gust+0.032
 finish+0.029
Neg logit contributions
ucer-0.075
fish-0.072
 globe-0.071
unny-0.071
 Area-0.069
Token the
Token ID262
Feature activation-5.50e-01

Pos logit contributions
 finished+0.016
 gust+0.013
 finally+0.012
 longer+0.012
 anymore+0.011
Neg logit contributions
 globe-0.029
ucer-0.029
fish-0.029
 Area-0.029
 fossil-0.028
Token most
Token ID749
Feature activation-1.15e+00

Pos logit contributions
 finished+0.014
 finally+0.011
 gust+0.011
 longer+0.009
 anymore+0.009
Neg logit contributions
 globe-0.021
ucer-0.021
unny-0.020
fish-0.020
 Area-0.020
Token on
Token ID319
Feature activation-2.02e+00

Pos logit contributions
ucer+0.015
unny+0.015
 Area+0.014
 globe+0.014
fish+0.014
Neg logit contributions
 finished-0.008
 finally-0.006
 longer-0.006
 less-0.005
 anymore-0.005
Token,
Token ID11
Feature activation+3.01e-01

Pos logit contributions
 finished+0.042
 finally+0.031
 longer+0.028
 finish+0.028
 bra+0.027
Neg logit contributions
ucer-0.091
unny-0.090
fish-0.089
 globe-0.088
 Area-0.087
Token whenever
Token ID8797
Feature activation-7.58e-01

Pos logit contributions
ucer+0.010
unny+0.010
fish+0.009
 globe+0.009
 Area+0.009
Neg logit contributions
 finished-0.009
 gust-0.007
 rum-0.007
 sweaty-0.007
 finish-0.007
Token they
Token ID484
Feature activation-1.63e+00

Pos logit contributions
 finished+0.019
 finally+0.014
 finish+0.013
 gust+0.013
 scr+0.013
Neg logit contributions
ucer-0.030
fish-0.028
 Area-0.028
 globe-0.028
unny-0.028
Token wanted
Token ID2227
Feature activation+7.38e-02

Pos logit contributions
 longer+0.038
 less+0.038
 healthier+0.036
 okay+0.036
 finished+0.036
Neg logit contributions
fish-0.058
ucer-0.056
 Area-0.054
fly-0.053
 globe-0.053
Token av
Token ID1196
Feature activation-5.12e+00

Pos logit contributions
fish+0.002
 fossil+0.002
 Area+0.002
 globe+0.002
ucer+0.002
Neg logit contributions
 finished-0.002
whe-0.002
 gust-0.002
 finally-0.002
 finish-0.002
Tokenoc
Token ID420
Feature activation+2.05e+00

Pos logit contributions
 finished+0.244
 finally+0.222
 longer+0.210
 finish+0.207
 gust+0.206
Neg logit contributions
ucer-0.100
unny-0.095
 Area-0.083
 globe-0.083
fish-0.082
Tokenados
Token ID22484
Feature activation-2.07e+00

Pos logit contributions
ucer+0.048
unny+0.047
 Area+0.044
 globe+0.044
fish+0.042
Neg logit contributions
 finished-0.088
 finally-0.079
 longer-0.076
 finish-0.074
 gust-0.073
Token,
Token ID11
Feature activation+1.92e-01

Pos logit contributions
 finished+0.048
 gust+0.039
 finally+0.038
 longer+0.036
 sweaty+0.036
Neg logit contributions
fish-0.083
ucer-0.081
unny-0.080
 globe-0.077
fly-0.077
Token they
Token ID484
Feature activation-1.20e-01

Pos logit contributions
ucer+0.006
unny+0.006
fish+0.006
 Area+0.006
 globe+0.006
Neg logit contributions
 finished-0.006
 finally-0.005
 finish-0.005
 rum-0.005
 gust-0.005
Token would
Token ID561
Feature activation+2.67e-01

Pos logit contributions
 finished+0.003
 gust+0.003
 longer+0.003
 less+0.003
 anymore+0.003
Neg logit contributions
fish-0.004
ucer-0.004
unny-0.004
 globe-0.004
fly-0.004
Tokenongo
Token ID25162
Feature activation+2.83e+00

Pos logit contributions
ucer+0.049
unny+0.047
 Area+0.045
fish+0.044
 globe+0.044
Neg logit contributions
 finished-0.050
 finally-0.043
 longer-0.041
 less-0.039
 finish-0.038
Token didn
Token ID1422
Feature activation-8.96e-02

Pos logit contributions
ucer+0.113
unny+0.111
fish+0.108
 Area+0.106
 globe+0.104
Neg logit contributions
 finished-0.073
 finally-0.060
 longer-0.058
 less-0.055
 gust-0.055
Token't
Token ID470
Feature activation+6.19e-01

Pos logit contributions
 finished+0.003
 finally+0.003
 longer+0.003
 less+0.002
 gust+0.002
Neg logit contributions
ucer-0.003
unny-0.003
 Area-0.003
fish-0.003
 globe-0.003
Token like
Token ID588
Feature activation-1.08e+00

Pos logit contributions
ucer+0.028
unny+0.027
 Area+0.027
 globe+0.027
fish+0.026
Neg logit contributions
 finished-0.014
 finally-0.012
 longer-0.011
 even-0.010
 finish-0.010
Token wet
Token ID9583
Feature activation+3.62e-02

Pos logit contributions
 finished+0.030
 finally+0.024
 longer+0.023
 finish+0.022
 bra+0.021
Neg logit contributions
fish-0.037
 globe-0.037
 appearances-0.036
ucer-0.036
 Area-0.036
Token av
Token ID1196
Feature activation-5.06e+00

Pos logit contributions
ucer+0.001
 globe+0.001
rooms+0.001
fish+0.001
 Area+0.001
Neg logit contributions
 finished-0.001
 finally-0.001
 finish-0.001
 longer-0.001
 bra-0.001
Tokenoc
Token ID420
Feature activation+1.32e+00

Pos logit contributions
 finished+0.235
 finally+0.214
 longer+0.203
 finish+0.196
 gust+0.195
Neg logit contributions
ucer-0.105
unny-0.097
 Area-0.087
 globe-0.087
fish-0.085
Tokenados
Token ID22484
Feature activation-1.74e+00

Pos logit contributions
ucer+0.025
unny+0.024
 globe+0.023
 Area+0.022
 appearances+0.022
Neg logit contributions
 finished-0.060
 finally-0.055
 longer-0.053
 especially-0.052
 sweaty-0.051
Token,
Token ID11
Feature activation+7.83e-01

Pos logit contributions
 finished+0.039
 finally+0.034
 gust+0.032
 longer+0.030
 healthier+0.029
Neg logit contributions
fish-0.069
ucer-0.068
 globe-0.064
unny-0.063
 Area-0.061
Token so
Token ID523
Feature activation-9.42e-02

Pos logit contributions
ucer+0.035
fish+0.034
unny+0.034
 Area+0.033
 globe+0.033
Neg logit contributions
 finished-0.016
 finally-0.011
 finish-0.010
 longer-0.009
 anymore-0.008
Token he
Token ID339
Feature activation-6.34e-01

Pos logit contributions
 finished+0.002
 finish+0.002
 finally+0.002
 anymore+0.002
 healthier+0.002
Neg logit contributions
ucer-0.004
unny-0.004
fish-0.004
 globe-0.003
 Area-0.003
Token to
Token ID284
Feature activation-2.05e-01

Pos logit contributions
fish+0.009
ucer+0.009
 Area+0.008
unny+0.008
 globe+0.008
Neg logit contributions
 finished-0.007
 gust-0.006
 finally-0.005
 sweaty-0.005
 bra-0.005
Token see
Token ID766
Feature activation-6.14e-01

Pos logit contributions
 finished+0.005
 anymore+0.005
 gust+0.005
 healthier+0.005
 longer+0.005
Neg logit contributions
ucer-0.007
 Area-0.007
 telescope-0.007
 globe-0.006
unny-0.006
Token where
Token ID810
Feature activation+1.03e+00

Pos logit contributions
 finished+0.015
 finally+0.011
 gust+0.011
 longer+0.010
 finish+0.010
Neg logit contributions
ucer-0.026
 globe-0.025
 Area-0.024
unny-0.024
fish-0.024
Token their
Token ID511
Feature activation-1.66e+00

Pos logit contributions
ucer+0.039
unny+0.036
fish+0.036
 globe+0.036
 Area+0.035
Neg logit contributions
 finished-0.027
 longer-0.022
 finish-0.021
 finally-0.021
 bra-0.020
Token cup
Token ID6508
Feature activation-1.81e+00

Pos logit contributions
 finished+0.049
 finally+0.043
 longer+0.042
 less+0.040
 gust+0.040
Neg logit contributions
 globe-0.056
ucer-0.056
 Area-0.055
unny-0.054
 telescope-0.052
Tokencakes
Token ID37263
Feature activation-5.01e+00

Pos logit contributions
 finished+0.052
 longer+0.052
 bra+0.049
 gust+0.048
 healthier+0.048
Neg logit contributions
ucer-0.062
 globe-0.060
fish-0.056
unny-0.055
 Area-0.055
Token would
Token ID561
Feature activation+3.91e-01

Pos logit contributions
 gust+0.129
 bra+0.127
 frustrated+0.125
 younger+0.125
 cav+0.125
Neg logit contributions
 globe-0.157
ucer-0.146
fish-0.142
 Area-0.130
rooms-0.117
Token go
Token ID467
Feature activation-1.62e+00

Pos logit contributions
 globe+0.013
ucer+0.013
fish+0.013
 Area+0.013
unny+0.012
Neg logit contributions
 finished-0.010
 gust-0.009
 bored-0.009
 bra-0.009
 sweaty-0.008
Token on
Token ID319
Feature activation-4.80e-01

Pos logit contributions
 finished+0.041
 gust+0.035
 tum+0.033
 sweaty+0.032
 bra+0.031
Neg logit contributions
ucer-0.064
 Area-0.060
 globe-0.058
unny-0.057
fish-0.056
Token the
Token ID262
Feature activation+3.34e-01

Pos logit contributions
 finished+0.011
 gust+0.009
 bra+0.009
 sweaty+0.009
vious+0.008
Neg logit contributions
 globe-0.019
ucer-0.018
 Area-0.018
fish-0.018
aby-0.017
Token tour
Token ID4205
Feature activation-1.09e+00

Pos logit contributions
 globe+0.010
ucer+0.010
 Area+0.009
fish+0.009
unny+0.009
Neg logit contributions
 finished-0.012
 finally-0.010
 longer-0.010
 gust-0.010
 anymore-0.009
Token Maybe
Token ID6674
Feature activation-1.49e+00

Pos logit contributions
ucer+0.001
unny+0.001
fish+0.001
 Area+0.001
 globe+0.001
Neg logit contributions
 finished-0.001
 finally-0.001
 longer-0.001
 less-0.001
 finish-0.001
Token they
Token ID484
Feature activation-1.02e+00

Pos logit contributions
 finished+0.045
 finally+0.037
 gust+0.034
 finish+0.034
 anymore+0.033
Neg logit contributions
ucer-0.054
fish-0.051
unny-0.051
 Area-0.050
 globe-0.050
Token could
Token ID714
Feature activation-2.76e-01

Pos logit contributions
 finished+0.030
 gust+0.026
 finally+0.026
 longer+0.026
 less+0.025
Neg logit contributions
ucer-0.036
fish-0.034
unny-0.034
 globe-0.033
 Area-0.032
Token grow
Token ID1663
Feature activation+8.81e-01

Pos logit contributions
 finished+0.008
 gust+0.007
 finally+0.006
 sweaty+0.006
 bra+0.006
Neg logit contributions
fish-0.010
ucer-0.009
unny-0.009
 globe-0.009
fly-0.009
Token more
Token ID517
Feature activation-4.16e-01

Pos logit contributions
fish+0.038
ucer+0.037
 globe+0.035
unny+0.035
 Area+0.034
Neg logit contributions
 finished-0.020
 finally-0.015
 gust-0.015
whe-0.014
 rum-0.013
Token av
Token ID1196
Feature activation-4.92e+00

Pos logit contributions
 finished+0.015
 finally+0.013
 gust+0.012
 finish+0.012
 longer+0.012
Neg logit contributions
fish-0.012
ucer-0.012
 globe-0.011
unny-0.011
 Area-0.011
Tokenoc
Token ID420
Feature activation+1.26e+00

Pos logit contributions
 finished+0.223
 finally+0.202
 longer+0.191
 less+0.185
 finish+0.185
Neg logit contributions
ucer-0.110
unny-0.102
 Area-0.096
fish-0.094
 globe-0.093
Tokenados
Token ID22484
Feature activation-1.83e+00

Pos logit contributions
ucer+0.033
unny+0.032
 Area+0.030
 globe+0.030
fish+0.029
Neg logit contributions
 finished-0.052
 finally-0.047
 longer-0.044
 gust-0.042
 finish-0.042
Token and
Token ID290
Feature activation-3.46e-01

Pos logit contributions
 finished+0.044
 gust+0.039
 finally+0.037
 rum+0.033
 frustrated+0.033
Neg logit contributions
fish-0.076
ucer-0.073
 globe-0.070
unny-0.069
 Area-0.068
Token share
Token ID2648
Feature activation+4.93e-01

Pos logit contributions
 finished+0.009
 finally+0.007
 gust+0.007
 anymore+0.007
whe+0.007
Neg logit contributions
fish-0.013
ucer-0.012
 globe-0.012
fly-0.012
unny-0.011
Token them
Token ID606
Feature activation+1.70e-01

Pos logit contributions
ucer+0.020
unny+0.019
fish+0.018
 Area+0.018
 globe+0.018
Neg logit contributions
 finished-0.014
 finally-0.011
 longer-0.010
 gust-0.010
 finish-0.010
Token tree
Token ID5509
Feature activation-7.30e-01

Pos logit contributions
 finished+0.013
 gust+0.011
 longer+0.011
 finally+0.011
 Dr+0.011
Neg logit contributions
fish-0.018
ucer-0.018
 globe-0.017
unny-0.016
fly-0.016
Token could
Token ID714
Feature activation-1.22e-01

Pos logit contributions
 finished+0.018
 gust+0.016
 longer+0.015
 Dr+0.015
 sweaty+0.015
Neg logit contributions
fish-0.028
fly-0.027
ucer-0.026
 globe-0.026
unny-0.025
Token see
Token ID766
Feature activation-1.18e+00

Pos logit contributions
 finished+0.003
 gust+0.003
 sweaty+0.003
 Tommy+0.003
 anymore+0.003
Neg logit contributions
fish-0.004
fly-0.004
unny-0.004
ucer-0.004
 globe-0.004
Token lots
Token ID6041
Feature activation-5.29e-01

Pos logit contributions
 finished+0.031
 finally+0.024
 gust+0.023
 finish+0.023
 longer+0.022
Neg logit contributions
ucer-0.047
fish-0.046
 globe-0.046
unny-0.045
 Area-0.045
Token of
Token ID286
Feature activation-8.96e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 sweaty+0.012
 gust+0.011
 bored+0.011
Neg logit contributions
fish-0.020
ucer-0.017
 globe-0.017
unny-0.017
fly-0.016
Token av
Token ID1196
Feature activation-4.91e+00

Pos logit contributions
 finished+0.026
 finally+0.022
 finish+0.020
whe+0.019
 gust+0.019
Neg logit contributions
fish-0.030
 globe-0.028
 fossil-0.028
ucer-0.027
 telescope-0.026
Tokenoc
Token ID420
Feature activation+1.73e+00

Pos logit contributions
 finished+0.232
 finally+0.212
 longer+0.199
 finish+0.196
 gust+0.195
Neg logit contributions
ucer-0.095
unny-0.087
 Area-0.078
 globe-0.078
fish-0.078
Tokenados
Token ID22484
Feature activation-1.39e+00

Pos logit contributions
ucer+0.037
unny+0.036
 globe+0.033
 Area+0.033
fish+0.032
Neg logit contributions
 finished-0.076
 finally-0.070
 longer-0.065
 especially-0.065
 finish-0.064
Token that
Token ID326
Feature activation+1.67e+00

Pos logit contributions
 finished+0.032
 gust+0.026
 finally+0.025
 sweaty+0.023
 longer+0.022
Neg logit contributions
fish-0.059
ucer-0.058
 globe-0.055
fly-0.054
 Area-0.053
Token the
Token ID262
Feature activation-7.92e-01

Pos logit contributions
ucer+0.062
fish+0.062
 globe+0.061
fly+0.057
unny+0.057
Neg logit contributions
 finished-0.045
 longer-0.038
 gust-0.036
 finish-0.034
 anymore-0.034
Token supplier
Token ID22693
Feature activation+9.02e-02

Pos logit contributions
 finished+0.026
 finally+0.022
 longer+0.021
 about+0.020
 anymore+0.020
Neg logit contributions
 globe-0.025
ucer-0.024
unny-0.023
fish-0.023
 fossil-0.022
Token happy
Token ID3772
Feature activation+1.05e-01

Pos logit contributions
ucer+0.025
fish+0.024
unny+0.024
 Area+0.023
 globe+0.023
Neg logit contributions
 anymore-0.015
 finished-0.014
 longer-0.012
 gust-0.012
 finally-0.012
Token that
Token ID326
Feature activation+1.22e+00

Pos logit contributions
ucer+0.005
unny+0.004
fish+0.004
 Area+0.004
 globe+0.004
Neg logit contributions
 finished-0.002
 finally-0.002
 longer-0.002
 gust-0.002
 finish-0.002
Token it
Token ID340
Feature activation-2.10e-01

Pos logit contributions
ucer+0.042
 globe+0.042
fish+0.042
 Area+0.040
fly+0.039
Neg logit contributions
 finished-0.035
 longer-0.026
 gust-0.026
 finish-0.025
 finally-0.025
Token produced
Token ID4635
Feature activation+4.84e-02

Pos logit contributions
 finished+0.005
 longer+0.004
 gust+0.004
 anymore+0.004
 finally+0.004
Neg logit contributions
ucer-0.008
fish-0.008
unny-0.008
 globe-0.008
 Area-0.008
Token more
Token ID517
Feature activation-5.44e-01

Pos logit contributions
ucer+0.002
fish+0.002
 globe+0.002
fly+0.002
unny+0.002
Neg logit contributions
 finished-0.001
 gust-0.001
whe-0.001
 sweaty-0.001
 finally-0.001
Token av
Token ID1196
Feature activation-4.82e+00

Pos logit contributions
 finished+0.016
 finally+0.013
 gust+0.012
whe+0.012
 finish+0.012
Neg logit contributions
fish-0.019
ucer-0.018
 globe-0.017
 fossil-0.017
unny-0.017
Tokenoc
Token ID420
Feature activation+1.07e+00

Pos logit contributions
 finished+0.227
 finally+0.206
 longer+0.195
 gust+0.191
 anymore+0.190
Neg logit contributions
ucer-0.098
unny-0.091
 Area-0.082
fish-0.082
 globe-0.081
Tokenados
Token ID22484
Feature activation-1.22e+00

Pos logit contributions
ucer+0.024
unny+0.024
 globe+0.022
fish+0.021
 Area+0.021
Neg logit contributions
 finished-0.047
 finally-0.042
 longer-0.040
 finish-0.040
 gust-0.039
Token than
Token ID621
Feature activation+6.28e-01

Pos logit contributions
 finished+0.028
 gust+0.023
 finally+0.023
 longer+0.021
 sweaty+0.020
Neg logit contributions
ucer-0.051
fish-0.051
 globe-0.049
unny-0.047
 Area-0.047
Token ever
Token ID1683
Feature activation-1.39e-01

Pos logit contributions
fish+0.024
ucer+0.024
fly+0.023
 globe+0.023
 fossil+0.023
Neg logit contributions
 finished-0.014
whe-0.011
 gust-0.011
 finally-0.011
 finish-0.011
Token before
Token ID878
Feature activation-8.73e-03

Pos logit contributions
 finished+0.003
 gust+0.003
whe+0.003
 finally+0.003
 finish+0.002
Neg logit contributions
ucer-0.005
fish-0.005
fly-0.005
 Area-0.005
 globe-0.005
Token something
Token ID1223
Feature activation-2.15e-01

Pos logit contributions
ucer+0.007
unny+0.007
 Area+0.007
fish+0.007
 globe+0.007
Neg logit contributions
 finished-0.005
 finally-0.004
 gust-0.003
 longer-0.003
 finish-0.003
Token new
Token ID649
Feature activation-1.27e-01

Pos logit contributions
 finished+0.006
 finally+0.005
 gust+0.004
 longer+0.004
 finish+0.004
Neg logit contributions
ucer-0.009
fish-0.008
 Area-0.008
unny-0.008
 globe-0.008
Token!
Token ID0
Feature activation-6.52e-01

Pos logit contributions
 finished+0.002
 finally+0.002
 longer+0.001
 less+0.001
 anymore+0.001
Neg logit contributions
ucer-0.006
unny-0.006
 Area-0.006
fish-0.006
 globe-0.006
Token She
Token ID1375
Feature activation+1.15e+00

Pos logit contributions
 finished+0.012
 finally+0.009
 less+0.007
 even+0.007
 longer+0.007
Neg logit contributions
ucer-0.032
fish-0.031
 Area-0.031
unny-0.031
 globe-0.030
Token thought
Token ID1807
Feature activation+1.07e+00

Pos logit contributions
fish+0.040
ucer+0.038
 globe+0.036
unny+0.036
fly+0.035
Neg logit contributions
 anymore-0.031
 gust-0.029
 longer-0.027
 finished-0.027
 less-0.025
Token av
Token ID1196
Feature activation-4.80e+00

Pos logit contributions
fish+0.039
ucer+0.037
unny+0.036
 globe+0.035
 Area+0.035
Neg logit contributions
 finished-0.029
 finally-0.024
 longer-0.023
 finish-0.023
 sweaty-0.022
Tokenoc
Token ID420
Feature activation+2.15e+00

Pos logit contributions
 finished+0.203
 finally+0.181
 longer+0.171
 less+0.167
 even+0.167
Neg logit contributions
ucer-0.123
unny-0.115
 Area-0.113
fish-0.109
 globe-0.106
Tokenados
Token ID22484
Feature activation-1.61e+00

Pos logit contributions
ucer+0.066
unny+0.063
 Area+0.061
fish+0.059
 globe+0.059
Neg logit contributions
 finished-0.079
 finally-0.070
 longer-0.066
 less-0.063
 finish-0.063
Token were
Token ID547
Feature activation-6.37e-01

Pos logit contributions
 finished+0.037
 longer+0.030
 gust+0.030
 finally+0.030
 finish+0.027
Neg logit contributions
ucer-0.068
fish-0.066
 globe-0.065
unny-0.065
 Area-0.063
Token the
Token ID262
Feature activation-4.66e-01

Pos logit contributions
 finished+0.014
 gust+0.011
 finally+0.010
 longer+0.010
 anymore+0.009
Neg logit contributions
ucer-0.026
 globe-0.025
fish-0.025
 Area-0.025
 fossil-0.024
Token most
Token ID749
Feature activation-1.07e+00

Pos logit contributions
 finished+0.012
 gust+0.010
 finally+0.010
 longer+0.008
 anymore+0.008
Neg logit contributions
 globe-0.017
ucer-0.017
unny-0.017
fish-0.016
 Area-0.016
Token the
Token ID262
Feature activation-4.23e-01

Pos logit contributions
unny+0.014
ucer+0.014
 Area+0.013
 globe+0.013
aby+0.013
Neg logit contributions
 finished-0.008
 sweaty-0.006
 finish-0.006
 finally-0.006
 longer-0.005
Token tree
Token ID5509
Feature activation+1.11e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.012
 anymore+0.012
 less+0.011
Neg logit contributions
unny-0.013
ucer-0.013
 globe-0.013
 Area-0.012
fish-0.012
Token if
Token ID611
Feature activation+6.29e-01

Pos logit contributions
ucer+0.005
unny+0.005
 Area+0.005
fish+0.005
 globe+0.005
Neg logit contributions
 finished-0.002
 finally-0.002
 longer-0.002
 gust-0.002
 finish-0.002
Token they
Token ID484
Feature activation-1.32e+00

Pos logit contributions
ucer+0.025
unny+0.024
fish+0.024
 Area+0.023
 globe+0.023
Neg logit contributions
 finished-0.016
 longer-0.012
 finally-0.012
 finish-0.012
 gust-0.012
Token were
Token ID547
Feature activation-7.64e-01

Pos logit contributions
 finished+0.040
 longer+0.035
 gust+0.035
 less+0.034
 healthier+0.034
Neg logit contributions
unny-0.043
fish-0.042
ucer-0.042
 globe-0.039
fly-0.038
Token av
Token ID1196
Feature activation-4.80e+00

Pos logit contributions
 finished+0.020
 gust+0.019
whe+0.018
 finally+0.016
 rum+0.016
Neg logit contributions
fish-0.024
ucer-0.023
unny-0.022
 Area-0.022
 torch-0.021
Tokenoc
Token ID420
Feature activation+2.21e+00

Pos logit contributions
 finished+0.221
 finally+0.200
 longer+0.190
 finish+0.184
 less+0.184
Neg logit contributions
ucer-0.104
unny-0.097
 Area-0.090
fish-0.087
 globe-0.087
Tokenados
Token ID22484
Feature activation-2.04e+00

Pos logit contributions
ucer+0.053
unny+0.051
 Area+0.047
 globe+0.046
fish+0.046
Neg logit contributions
 finished-0.096
 finally-0.086
 longer-0.081
 finish-0.080
 especially-0.078
Token,
Token ID11
Feature activation+4.55e-01

Pos logit contributions
 finished+0.046
 gust+0.038
 finally+0.037
 sweaty+0.031
 longer+0.031
Neg logit contributions
fish-0.086
ucer-0.085
unny-0.083
 globe-0.080
 Area-0.079
Token and
Token ID290
Feature activation-2.85e-01

Pos logit contributions
ucer+0.016
unny+0.016
 Area+0.016
fish+0.016
 globe+0.015
Neg logit contributions
 finished-0.014
 finally-0.011
 finish-0.010
 longer-0.010
 gust-0.010
Token they
Token ID484
Feature activation-8.26e-02

Pos logit contributions
 finished+0.007
 anymore+0.006
 gust+0.006
 finally+0.005
 finish+0.005
Neg logit contributions
ucer-0.011
fish-0.010
unny-0.010
 Area-0.010
fly-0.010
Token want
Token ID765
Feature activation-1.04e-01

Pos logit contributions
ucer+0.015
unny+0.015
 Area+0.014
fish+0.014
 globe+0.013
Neg logit contributions
 finished-0.010
 finally-0.009
 longer-0.008
 gust-0.008
 less-0.007
Token to
Token ID284
Feature activation-6.43e-01

Pos logit contributions
 finished+0.003
 finally+0.002
 gust+0.002
 longer+0.002
 rum+0.002
Neg logit contributions
ucer-0.004
 Area-0.004
unny-0.004
fish-0.003
 globe-0.003
Token leave
Token ID2666
Feature activation-5.18e-01

Pos logit contributions
 finished+0.015
 gust+0.014
 finally+0.013
 bra+0.012
 healthier+0.012
Neg logit contributions
ucer-0.023
unny-0.023
fish-0.023
 Area-0.022
 globe-0.021
Token her
Token ID607
Feature activation-4.85e-01

Pos logit contributions
 finished+0.013
 gust+0.010
whe+0.010
vious+0.009
 rum+0.009
Neg logit contributions
ucer-0.018
 globe-0.018
aby-0.018
 Area-0.017
 magn-0.017
Token mud
Token ID17492
Feature activation-7.60e-01

Pos logit contributions
 finished+0.017
 finally+0.015
 gust+0.014
 bra+0.014
 healthier+0.014
Neg logit contributions
ucer-0.014
fish-0.014
 globe-0.014
unny-0.014
 Area-0.013
Token pies
Token ID47199
Feature activation-4.78e+00

Pos logit contributions
 finished+0.021
 gust+0.018
 finally+0.017
 rum+0.015
 healthier+0.015
Neg logit contributions
ucer-0.029
fish-0.028
unny-0.027
 globe-0.027
 Area-0.026
Token.
Token ID13
Feature activation-6.48e-01

Pos logit contributions
 finished+0.122
 gust+0.116
 bra+0.106
 rum+0.105
 finally+0.103
Neg logit contributions
ucer-0.166
fish-0.148
unny-0.147
 globe-0.147
row-0.145
Token
Token ID198
Feature activation-8.88e-01

Pos logit contributions
 finished+0.018
 finally+0.014
 longer+0.014
 less+0.013
 even+0.013
Neg logit contributions
ucer-0.026
unny-0.025
 Area-0.024
 globe-0.023
fish-0.023
Token
Token ID198
Feature activation-3.87e-01

Pos logit contributions
 finished+0.018
 finally+0.015
 longer+0.012
 anymore+0.011
 even+0.011
Neg logit contributions
ucer-0.042
unny-0.040
fish-0.040
 Area-0.040
 globe-0.040
Token"
Token ID1
Feature activation-1.58e-01

Pos logit contributions
 finished+0.013
 finally+0.011
 longer+0.010
 finish+0.010
 even+0.010
Neg logit contributions
ucer-0.014
unny-0.013
fish-0.013
 globe-0.013
 Area-0.013
TokenL
Token ID43
Feature activation+7.12e-01

Pos logit contributions
 finished+0.005
 finally+0.004
 longer+0.004
 less+0.004
 finish+0.004
Neg logit contributions
ucer-0.006
unny-0.006
 Area-0.005
fish-0.005
 globe-0.005
Token the
Token ID262
Feature activation-5.30e-02

Pos logit contributions
ucer+0.032
 globe+0.031
 Area+0.031
unny+0.031
 telescope+0.030
Neg logit contributions
 finished-0.018
 finally-0.015
 longer-0.014
 gust-0.014
 bra-0.013
Token store
Token ID3650
Feature activation+6.57e-01

Pos logit contributions
 finished+0.002
 finally+0.002
 gust+0.002
 longer+0.002
 anymore+0.001
Neg logit contributions
ucer-0.002
 globe-0.002
 Area-0.002
fish-0.001
unny-0.001
Token to
Token ID284
Feature activation+4.54e-01

Pos logit contributions
ucer+0.025
 globe+0.024
 Area+0.023
unny+0.023
fish+0.021
Neg logit contributions
 finished-0.017
 gust-0.015
 rum-0.014
 bra-0.014
 finally-0.013
Token get
Token ID651
Feature activation+8.03e-01

Pos logit contributions
ucer+0.015
 Area+0.015
 globe+0.015
unny+0.014
 telescope+0.014
Neg logit contributions
 finished-0.013
 gust-0.011
 anymore-0.011
 longer-0.011
 bra-0.010
Token more
Token ID517
Feature activation-3.02e-01

Pos logit contributions
ucer+0.028
fish+0.025
 Area+0.024
 coral+0.023
 globe+0.023
Neg logit contributions
 finished-0.019
 gust-0.018
 itch-0.016
whe-0.016
 anymore-0.016
Token av
Token ID1196
Feature activation-4.76e+00

Pos logit contributions
 finished+0.009
 finally+0.008
 gust+0.008
 Dr+0.008
whe+0.008
Neg logit contributions
fish-0.010
ucer-0.009
 fossil-0.008
 telescope-0.008
 globe-0.008
Tokenoc
Token ID420
Feature activation+1.40e+00

Pos logit contributions
 finished+0.223
 finally+0.203
 longer+0.191
 anymore+0.186
 gust+0.186
Neg logit contributions
ucer-0.100
unny-0.093
 Area-0.084
fish-0.083
 globe-0.083
Tokenados
Token ID22484
Feature activation-1.90e+00

Pos logit contributions
ucer+0.034
unny+0.033
 Area+0.030
 globe+0.030
fish+0.030
Neg logit contributions
 finished-0.060
 finally-0.054
 longer-0.051
 gust-0.050
 especially-0.050
Token.
Token ID13
Feature activation-5.75e-01

Pos logit contributions
 finished+0.046
 gust+0.041
 finally+0.039
 sweaty+0.036
 rum+0.036
Neg logit contributions
ucer-0.075
fish-0.072
 globe-0.069
unny-0.067
 Area-0.065
Token Gary
Token ID10936
Feature activation+1.43e+00

Pos logit contributions
 finished+0.016
 finally+0.014
 longer+0.012
 less+0.012
 finish+0.012
Neg logit contributions
ucer-0.024
unny-0.022
fish-0.022
 Area-0.022
 globe-0.021
Token looked
Token ID3114
Feature activation+7.02e-02

Pos logit contributions
fish+0.047
unny+0.045
ucer+0.045
 globe+0.044
 Area+0.043
Neg logit contributions
 gust-0.039
 anymore-0.036
 longer-0.036
 finished-0.035
 less-0.033
Token away
Token ID1497
Feature activation+1.37e+00

Pos logit contributions
 finished+0.034
 gust+0.028
 finally+0.028
 fifteen+0.026
 happiest+0.026
Neg logit contributions
ucer-0.039
 Area-0.037
fish-0.034
eds-0.034
 globe-0.034
Token.
Token ID13
Feature activation-8.61e-01

Pos logit contributions
ucer+0.047
fish+0.046
 globe+0.044
 Area+0.043
unny+0.043
Neg logit contributions
 finished-0.035
 gust-0.031
 finally-0.030
 sweaty-0.027
Whe-0.026
Token She
Token ID1375
Feature activation+6.08e-01

Pos logit contributions
 finished+0.022
 longer+0.018
 finally+0.017
 anymore+0.016
 gust+0.016
Neg logit contributions
ucer-0.036
unny-0.035
 Area-0.034
 globe-0.033
fish-0.031
Token learned
Token ID4499
Feature activation+1.81e-01

Pos logit contributions
fish+0.022
ucer+0.019
 globe+0.018
unny+0.018
ox+0.017
Neg logit contributions
 gust-0.015
 anymore-0.015
 finished-0.014
 longer-0.013
whe-0.013
Token that
Token ID326
Feature activation+1.90e+00

Pos logit contributions
ucer+0.007
unny+0.007
 Area+0.007
fish+0.007
 globe+0.007
Neg logit contributions
 finished-0.005
 finally-0.004
 gust-0.004
 longer-0.004
 finish-0.003
Token av
Token ID1196
Feature activation-4.74e+00

Pos logit contributions
ucer+0.077
unny+0.074
fish+0.073
 Area+0.073
 globe+0.072
Neg logit contributions
 finished-0.049
 finally-0.039
 longer-0.035
 finish-0.034
 gust-0.033
Tokenoc
Token ID420
Feature activation+2.17e+00

Pos logit contributions
 finished+0.203
 finally+0.181
 longer+0.172
 less+0.168
 even+0.166
Neg logit contributions
ucer-0.118
unny-0.111
 Area-0.109
fish-0.105
 globe-0.103
Tokenados
Token ID22484
Feature activation-1.66e+00

Pos logit contributions
ucer+0.061
unny+0.058
 Area+0.055
 globe+0.055
fish+0.054
Neg logit contributions
 finished-0.086
 finally-0.076
 longer-0.073
 finish-0.069
 gust-0.069
Token are
Token ID389
Feature activation-1.07e+00

Pos logit contributions
 finished+0.048
 finally+0.041
 longer+0.039
 gust+0.037
 less+0.036
Neg logit contributions
ucer-0.062
unny-0.059
fish-0.059
 globe-0.058
 Area-0.058
Token good
Token ID922
Feature activation+2.08e-01

Pos logit contributions
 finished+0.023
 finally+0.019
 gust+0.018
 rum+0.016
 anymore+0.016
Neg logit contributions
ucer-0.044
unny-0.042
fish-0.042
 Area-0.042
 globe-0.041
Token for
Token ID329
Feature activation-9.74e-01

Pos logit contributions
ucer+0.009
unny+0.009
 Area+0.009
fish+0.009
 globe+0.009
Neg logit contributions
 finished-0.004
 finally-0.004
 gust-0.003
 longer-0.003
 finish-0.003
Token the
Token ID262
Feature activation-1.78e+00

Pos logit contributions
 finished+0.006
 anymore+0.005
 gust+0.005
 sweaty+0.005
whe+0.004
Neg logit contributions
ucer-0.012
unny-0.012
fish-0.012
 globe-0.011
 Area-0.011
Token tree
Token ID5509
Feature activation-8.44e-01

Pos logit contributions
 finished+0.060
 anymore+0.051
 finally+0.051
 longer+0.051
 less+0.048
Neg logit contributions
 globe-0.054
ucer-0.054
fish-0.052
unny-0.052
 Area-0.051
Token knew
Token ID2993
Feature activation-6.56e-01

Pos logit contributions
 finished+0.021
 gust+0.017
 anymore+0.017
 longer+0.016
 finally+0.016
Neg logit contributions
fish-0.033
unny-0.032
ucer-0.032
fly-0.031
 globe-0.031
Token that
Token ID326
Feature activation+9.91e-01

Pos logit contributions
 finished+0.017
 finally+0.014
 gust+0.013
 finish+0.013
 longer+0.013
Neg logit contributions
ucer-0.026
fish-0.025
unny-0.025
 Area-0.024
 globe-0.024
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
fish+0.037
ucer+0.036
 globe+0.036
 Area+0.035
 appearances+0.035
Neg logit contributions
 finished-0.026
 finally-0.020
 finish-0.019
 gust-0.019
 longer-0.018
Token av
Token ID1196
Feature activation-4.72e+00

Pos logit contributions
 finished+0.036
 finally+0.030
 longer+0.029
 anymore+0.027
 about+0.027
Neg logit contributions
 globe-0.036
ucer-0.035
unny-0.034
fish-0.034
 fossil-0.033
Tokenoc
Token ID420
Feature activation+1.89e+00

Pos logit contributions
 finished+0.223
 finally+0.202
 longer+0.192
 gust+0.187
 anymore+0.187
Neg logit contributions
ucer-0.096
unny-0.088
fish-0.080
 Area-0.080
 globe-0.080
Tokenados
Token ID22484
Feature activation-1.85e+00

Pos logit contributions
ucer+0.048
unny+0.045
 globe+0.045
 Area+0.042
fish+0.042
Neg logit contributions
 finished-0.080
 finally-0.071
 longer-0.068
 finish-0.066
 gust-0.065
Token would
Token ID561
Feature activation+3.50e-01

Pos logit contributions
 finished+0.046
 longer+0.037
 finally+0.037
 gust+0.036
 less+0.034
Neg logit contributions
ucer-0.075
fish-0.073
unny-0.071
 globe-0.071
 Area-0.069
Token be
Token ID307
Feature activation+3.22e-01

Pos logit contributions
ucer+0.013
fish+0.013
unny+0.013
 globe+0.013
 Area+0.012
Neg logit contributions
 finished-0.009
 gust-0.007
 finally-0.007
 longer-0.007
 sweaty-0.007
Token back
Token ID736
Feature activation-4.29e-01

Pos logit contributions
ucer+0.011
fish+0.011
fly+0.011
unny+0.011
 Area+0.011
Neg logit contributions
whe-0.007
 finished-0.007
 gust-0.006
Whe-0.005
 finish-0.005
Token outside
Token ID2354
Feature activation+5.80e-01

Pos logit contributions
 finished+0.019
 gust+0.017
 finally+0.017
 bra+0.015
 finish+0.015
Neg logit contributions
 globe-0.032
ucer-0.031
 Area-0.030
fish-0.029
unny-0.028
Token.
Token ID13
Feature activation-8.84e-01

Pos logit contributions
ucer+0.022
 globe+0.021
fish+0.020
 Area+0.020
unny+0.019
Neg logit contributions
 finished-0.015
 gust-0.013
 bra-0.012
 finally-0.012
 frustrated-0.011
Token When
Token ID1649
Feature activation+8.25e-01

Pos logit contributions
 finished+0.021
 finally+0.017
 longer+0.016
 less+0.015
 finish+0.015
Neg logit contributions
ucer-0.038
unny-0.037
 Area-0.036
 globe-0.035
fish-0.035
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
ucer+0.028
 globe+0.026
 Area+0.025
fish+0.025
unny+0.025
Neg logit contributions
 finished-0.024
 bra-0.020
 finally-0.020
whe-0.020
 longer-0.020
Token cup
Token ID6508
Feature activation-1.40e+00

Pos logit contributions
 finished+0.038
 finally+0.032
 longer+0.029
 even+0.028
 bra+0.028
Neg logit contributions
ucer-0.066
 globe-0.064
 Area-0.064
unny-0.063
fish-0.063
Tokencakes
Token ID37263
Feature activation-4.71e+00

Pos logit contributions
 bra+0.037
 longer+0.036
 healthier+0.035
 finished+0.035
 less+0.034
Neg logit contributions
ucer-0.046
 globe-0.045
fish-0.045
unny-0.045
 Area-0.044
Token were
Token ID547
Feature activation-1.25e+00

Pos logit contributions
 bra+0.104
 curly+0.096
 less+0.095
 healthier+0.095
 okay+0.094
Neg logit contributions
 globe-0.167
fish-0.166
ucer-0.161
 Area-0.157
unny-0.140
Token done
Token ID1760
Feature activation-1.79e+00

Pos logit contributions
 bra+0.020
 less+0.017
hy+0.017
whe+0.017
 anymore+0.017
Neg logit contributions
ucer-0.051
 Area-0.050
unny-0.046
fish-0.046
 globe-0.046
Token,
Token ID11
Feature activation-6.41e-01

Pos logit contributions
 finished+0.041
 bra+0.039
vious+0.037
 less+0.036
 sweaty+0.034
Neg logit contributions
 globe-0.064
ucer-0.063
 Area-0.062
fish-0.062
aby-0.059
Token they
Token ID484
Feature activation-9.46e-02

Pos logit contributions
 finished+0.017
 finally+0.013
 bra+0.013
 rum+0.012
 finish+0.012
Neg logit contributions
ucer-0.025
 globe-0.023
fish-0.023
unny-0.022
 Area-0.022
Token sat
Token ID3332
Feature activation-2.54e+00

Pos logit contributions
 anymore+0.002
 finished+0.002
 less+0.002
 longer+0.002
 healthier+0.002
Neg logit contributions
ucer-0.004
fish-0.004
unny-0.003
 globe-0.003
 Area-0.003
Token his
Token ID465
Feature activation-4.12e-01

Pos logit contributions
 finished+0.008
 finally+0.006
 longer+0.005
 less+0.004
 finish+0.004
Neg logit contributions
ucer-0.027
unny-0.026
 Area-0.026
fish-0.025
 globe-0.025
Token hands
Token ID2832
Feature activation-2.91e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.013
 anymore+0.012
 less+0.012
Neg logit contributions
ucer-0.013
unny-0.012
 Area-0.012
fish-0.011
 globe-0.011
Token and
Token ID290
Feature activation-1.39e-01

Pos logit contributions
 finished+0.008
 gust+0.007
 finally+0.006
 bra+0.006
 sweaty+0.005
Neg logit contributions
ucer-0.011
fish-0.011
 globe-0.010
unny-0.010
fly-0.010
Token make
Token ID787
Feature activation-6.96e-01

Pos logit contributions
 finished+0.004
 finally+0.003
 longer+0.003
 anymore+0.003
 gust+0.003
Neg logit contributions
ucer-0.006
unny-0.005
fish-0.005
 globe-0.005
 Area-0.005
Token mud
Token ID17492
Feature activation-8.76e-01

Pos logit contributions
 finished+0.019
 finally+0.015
 gust+0.014
 longer+0.013
 anymore+0.013
Neg logit contributions
ucer-0.027
fish-0.026
unny-0.026
 globe-0.025
 Area-0.025
Token pies
Token ID47199
Feature activation-4.67e+00

Pos logit contributions
 finished+0.027
 finally+0.024
 gust+0.022
 longer+0.021
 finish+0.020
Neg logit contributions
ucer-0.031
fish-0.030
unny-0.029
 globe-0.029
 Area-0.028
Token.
Token ID13
Feature activation-3.48e-01

Pos logit contributions
 finished+0.115
 gust+0.110
 finally+0.098
 frustrated+0.094
 miserable+0.092
Neg logit contributions
ucer-0.181
 globe-0.177
fish-0.174
unny-0.160
 Area-0.155
Token One
Token ID1881
Feature activation-7.74e-01

Pos logit contributions
 finished+0.008
 finally+0.006
 longer+0.006
 less+0.005
 finish+0.005
Neg logit contributions
ucer-0.016
unny-0.015
 Area-0.015
fish-0.014
 globe-0.014
Token day
Token ID1110
Feature activation+3.01e-01

Pos logit contributions
 finished+0.019
 finally+0.016
 longer+0.014
 less+0.013
 anymore+0.013
Neg logit contributions
ucer-0.033
unny-0.032
fish-0.031
 Area-0.031
 globe-0.031
Token,
Token ID11
Feature activation-2.37e-01

Pos logit contributions
ucer+0.014
unny+0.013
fish+0.013
 Area+0.013
 globe+0.013
Neg logit contributions
 finished-0.006
 finally-0.005
 longer-0.004
 healthier-0.004
 finish-0.004
Token Tim
Token ID5045
Feature activation+1.15e-01

Pos logit contributions
 finished+0.005
 finally+0.004
 longer+0.003
 finish+0.003
 less+0.003
Neg logit contributions
ucer-0.011
unny-0.010
 Area-0.010
fish-0.010
 globe-0.010
Token.
Token ID13
Feature activation+7.92e-01

Pos logit contributions
 finished+0.007
 gust+0.007
 finally+0.006
 longer+0.006
 bra+0.006
Neg logit contributions
ucer-0.009
unny-0.008
fish-0.008
 globe-0.008
 Area-0.008
Token Can
Token ID1680
Feature activation-4.74e-01

Pos logit contributions
ucer+0.031
unny+0.029
fish+0.029
 Area+0.028
 globe+0.028
Neg logit contributions
 finished-0.023
 finally-0.019
 longer-0.018
 less-0.017
 finish-0.017
Token we
Token ID356
Feature activation-8.59e-01

Pos logit contributions
 finished+0.016
 finally+0.014
 longer+0.013
 less+0.012
 finish+0.012
Neg logit contributions
ucer-0.017
unny-0.016
 Area-0.015
fish-0.015
 globe-0.015
Token make
Token ID787
Feature activation-8.64e-01

Pos logit contributions
 finished+0.021
 gust+0.020
 bra+0.018
 anymore+0.018
 sweaty+0.018
Neg logit contributions
ucer-0.030
unny-0.030
fish-0.029
 Area-0.028
 globe-0.028
Token cup
Token ID6508
Feature activation-1.30e+00

Pos logit contributions
 finished+0.025
 finally+0.022
 gust+0.020
 longer+0.019
 finish+0.018
Neg logit contributions
ucer-0.030
fish-0.029
 Area-0.028
unny-0.028
 globe-0.028
Tokencakes
Token ID37263
Feature activation-4.66e+00

Pos logit contributions
 finished+0.037
 finally+0.034
 gust+0.032
 longer+0.029
 curly+0.028
Neg logit contributions
ucer-0.048
fish-0.046
 Area-0.043
unny-0.043
 globe-0.042
Token next
Token ID1306
Feature activation-1.70e+00

Pos logit contributions
 gust+0.140
 finished+0.134
 frustrated+0.127
 finally+0.127
 miserable+0.123
Neg logit contributions
fish-0.139
ucer-0.136
 globe-0.131
 Area-0.125
ute-0.121
Token time
Token ID640
Feature activation+1.92e+00

Pos logit contributions
 finished+0.045
 finally+0.038
 bra+0.037
 gust+0.037
 less+0.036
Neg logit contributions
ucer-0.063
 Area-0.061
unny-0.059
fish-0.059
 globe-0.058
Token?"
Token ID1701
Feature activation-1.40e+00

Pos logit contributions
ucer+0.053
 Area+0.050
fish+0.050
unny+0.048
 globe+0.045
Neg logit contributions
 finished-0.069
 finally-0.064
 bra-0.063
 gust-0.060
 less-0.058
Token
Token ID220
Feature activation+1.11e+00

Pos logit contributions
 finished+0.039
 finally+0.031
 longer+0.029
 anymore+0.028
 finish+0.028
Neg logit contributions
ucer-0.054
unny-0.054
 Area-0.051
fish-0.051
 globe-0.050
Token
Token ID198
Feature activation+5.22e-01

Pos logit contributions
ucer+0.047
unny+0.045
 Area+0.044
fish+0.043
 globe+0.043
Neg logit contributions
 finished-0.028
 finally-0.023
 longer-0.021
 less-0.019
 finish-0.019
Token says
Token ID1139
Feature activation+1.11e+00

Pos logit contributions
 finished+0.007
 finally+0.006
 longer+0.005
 less+0.005
 finish+0.005
Neg logit contributions
ucer-0.008
unny-0.007
 Area-0.007
fish-0.007
 globe-0.007
Token,
Token ID11
Feature activation-4.65e-01

Pos logit contributions
unny+0.048
ucer+0.047
fish+0.047
 globe+0.046
 Area+0.046
Neg logit contributions
 finished-0.025
 finally-0.019
 longer-0.018
 finish-0.017
 sweaty-0.016
Token "
Token ID366
Feature activation-5.49e-01

Pos logit contributions
 finished+0.014
 finally+0.011
 longer+0.011
 finish+0.010
 less+0.010
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.017
 globe-0.016
fish-0.016
TokenThey
Token ID2990
Feature activation+2.00e-01

Pos logit contributions
 finished+0.011
 finally+0.010
 even+0.010
 less+0.009
 especially+0.009
Neg logit contributions
ucer-0.024
aby-0.023
unny-0.023
fish-0.023
 torch-0.022
Token are
Token ID389
Feature activation-1.20e+00

Pos logit contributions
ucer+0.008
unny+0.008
 Area+0.008
fish+0.007
 globe+0.007
Neg logit contributions
 finished-0.005
 finally-0.005
 longer-0.004
 less-0.004
 finish-0.004
Token av
Token ID1196
Feature activation-4.65e+00

Pos logit contributions
 finished+0.028
 finally+0.022
 longer+0.020
 gust+0.019
 anymore+0.019
Neg logit contributions
ucer-0.050
 Area-0.049
unny-0.049
 globe-0.048
fish-0.047
Tokenoc
Token ID420
Feature activation+2.31e+00

Pos logit contributions
 finished+0.200
 finally+0.178
 longer+0.171
 less+0.165
 even+0.164
Neg logit contributions
ucer-0.114
unny-0.107
 Area-0.104
fish-0.101
 globe-0.099
Tokenados
Token ID22484
Feature activation-1.40e+00

Pos logit contributions
ucer+0.065
unny+0.063
 Area+0.060
 globe+0.059
fish+0.058
Neg logit contributions
 finished-0.091
 finally-0.082
 longer-0.077
 finish-0.073
 even-0.073
Token.
Token ID13
Feature activation-1.09e-01

Pos logit contributions
 finished+0.031
 finally+0.026
 longer+0.022
 gust+0.022
 less+0.020
Neg logit contributions
ucer-0.063
unny-0.060
fish-0.060
 Area-0.059
 globe-0.059
Token My
Token ID2011
Feature activation-2.03e+00

Pos logit contributions
 finished+0.003
 finally+0.003
 longer+0.002
 less+0.002
 even+0.002
Neg logit contributions
ucer-0.004
unny-0.004
fish-0.004
 Area-0.004
 globe-0.004
Token mom
Token ID1995
Feature activation-2.59e+00

Pos logit contributions
 finished+0.067
 finally+0.056
 longer+0.053
 less+0.050
 finish+0.050
Neg logit contributions
unny-0.069
ucer-0.068
 globe-0.066
 Area-0.066
fish-0.065
Token sat
Token ID3332
Feature activation-2.77e+00

Pos logit contributions
 finished+0.008
 finally+0.006
 gust+0.005
 finish+0.005
 longer+0.005
Neg logit contributions
ucer-0.009
 Area-0.009
 appearances-0.008
unny-0.008
fish-0.008
Token down
Token ID866
Feature activation-8.38e-01

Pos logit contributions
 finished+0.079
 finish+0.063
 gust+0.063
 finally+0.062
 excellent+0.060
Neg logit contributions
ucer-0.100
fish-0.098
 globe-0.092
unny-0.089
ute-0.089
Token and
Token ID290
Feature activation-2.08e-01

Pos logit contributions
 finished+0.022
 gust+0.019
 happiest+0.018
 finally+0.018
 healthier+0.018
Neg logit contributions
fish-0.028
ucer-0.027
 globe-0.027
 Area-0.027
eway-0.026
Token enjoyed
Token ID8359
Feature activation-1.67e+00

Pos logit contributions
 finished+0.005
 anymore+0.004
 longer+0.004
 gust+0.004
 finally+0.004
Neg logit contributions
ucer-0.008
fish-0.008
unny-0.007
 globe-0.007
 Area-0.007
Token their
Token ID511
Feature activation-3.76e-01

Pos logit contributions
 finished+0.042
vious+0.034
 gust+0.034
 finish+0.034
 finally+0.033
Neg logit contributions
fish-0.061
 globe-0.059
ucer-0.058
 Area-0.056
aby-0.054
Token pies
Token ID47199
Feature activation-4.63e+00

Pos logit contributions
 finished+0.010
 finally+0.009
 gust+0.008
 longer+0.008
 anymore+0.008
Neg logit contributions
fish-0.014
 globe-0.014
ucer-0.014
unny-0.013
 Area-0.013
Token together
Token ID1978
Feature activation+1.38e-01

Pos logit contributions
 gust+0.126
 finished+0.118
 frustrated+0.105
 miserable+0.105
 finally+0.103
Neg logit contributions
fish-0.169
ucer-0.169
 globe-0.162
unny-0.148
row-0.145
Token.
Token ID13
Feature activation-4.07e-02

Pos logit contributions
fish+0.005
ucer+0.005
 globe+0.005
 Area+0.005
unny+0.005
Neg logit contributions
 finished-0.004
 gust-0.003
 finally-0.003
 sweaty-0.003
 frustrated-0.003
Token From
Token ID3574
Feature activation-7.55e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 less+0.001
 finish+0.001
Neg logit contributions
ucer-0.002
unny-0.002
 Area-0.002
 globe-0.002
fish-0.002
Token that
Token ID326
Feature activation+2.38e+00

Pos logit contributions
 finished+0.016
 finally+0.013
 longer+0.012
 less+0.011
 finish+0.011
Neg logit contributions
ucer-0.033
fish-0.032
unny-0.032
 Area-0.032
 globe-0.031
Token day
Token ID1110
Feature activation+1.01e+00

Pos logit contributions
ucer+0.095
unny+0.092
 globe+0.090
 Area+0.090
fish+0.089
Neg logit contributions
 finished-0.063
 finally-0.053
 longer-0.048
 less-0.046
 anymore-0.045
Token dig
Token ID3100
Feature activation-7.61e-01

Pos logit contributions
 finished+0.006
 finally+0.005
 longer+0.005
 anymore+0.005
 less+0.005
Neg logit contributions
ucer-0.007
unny-0.007
 globe-0.006
fish-0.006
 Area-0.006
Token holes
Token ID10421
Feature activation+4.41e-01

Pos logit contributions
 finished+0.019
 finally+0.015
 longer+0.014
 even+0.013
 less+0.013
Neg logit contributions
ucer-0.033
unny-0.032
 Area-0.031
 globe-0.030
fish-0.030
Token and
Token ID290
Feature activation-2.84e-01

Pos logit contributions
ucer+0.021
unny+0.020
fish+0.020
 Area+0.019
 globe+0.019
Neg logit contributions
 finished-0.009
 finally-0.007
 longer-0.006
 gust-0.006
 finish-0.006
Token make
Token ID787
Feature activation-4.76e-01

Pos logit contributions
 finished+0.008
 finally+0.007
 longer+0.006
 finish+0.006
 even+0.006
Neg logit contributions
ucer-0.011
unny-0.011
 Area-0.010
fish-0.010
 globe-0.010
Token mud
Token ID17492
Feature activation-8.86e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.012
 gust+0.011
 less+0.011
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.016
fish-0.016
 globe-0.016
Token pies
Token ID47199
Feature activation-4.61e+00

Pos logit contributions
 finished+0.025
 finally+0.022
 longer+0.020
 gust+0.019
 finish+0.018
Neg logit contributions
ucer-0.034
unny-0.033
fish-0.032
 Area-0.032
 globe-0.032
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
 finished+0.108
 finally+0.091
 gust+0.090
 longer+0.081
 miserable+0.077
Neg logit contributions
ucer-0.195
 globe-0.184
fish-0.181
unny-0.177
 Area-0.174
Token They
Token ID1119
Feature activation+9.90e-01

Pos logit contributions
 finished+0.009
 finally+0.007
 longer+0.007
 less+0.006
 bra+0.006
Neg logit contributions
ucer-0.015
unny-0.015
 Area-0.015
 globe-0.014
fish-0.014
Token saw
Token ID2497
Feature activation-2.06e-01

Pos logit contributions
ucer+0.040
unny+0.039
fish+0.038
 globe+0.037
 Area+0.037
Neg logit contributions
 finished-0.025
 finally-0.021
 longer-0.020
 anymore-0.020
 less-0.019
Token a
Token ID257
Feature activation-5.02e-02

Pos logit contributions
 finished+0.005
 finally+0.004
 longer+0.003
 finish+0.003
 anymore+0.003
Neg logit contributions
ucer-0.009
unny-0.009
fish-0.009
 globe-0.009
 Area-0.009
Token big
Token ID1263
Feature activation-5.02e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 gust+0.001
 longer+0.001
 even+0.001
Neg logit contributions
ucer-0.002
unny-0.002
 Area-0.002
eway-0.002
ark-0.002
Token He
Token ID679
Feature activation+1.07e+00

Pos logit contributions
 finished+0.005
 longer+0.005
 finally+0.004
 anymore+0.004
 less+0.004
Neg logit contributions
unny-0.006
ucer-0.006
 Area-0.006
oris-0.006
 globe-0.006
Token saw
Token ID2497
Feature activation-1.19e-01

Pos logit contributions
ucer+0.043
unny+0.042
fish+0.041
 Area+0.041
 globe+0.039
Neg logit contributions
 finished-0.027
 finally-0.022
 anymore-0.022
 longer-0.022
 less-0.021
Token lots
Token ID6041
Feature activation+9.80e-02

Pos logit contributions
 finished+0.003
 finally+0.002
 longer+0.002
 finish+0.002
 anymore+0.002
Neg logit contributions
ucer-0.005
unny-0.005
fish-0.005
 Area-0.005
 globe-0.005
Token of
Token ID286
Feature activation-9.04e-01

Pos logit contributions
fish+0.004
ucer+0.004
unny+0.004
 Area+0.004
 globe+0.004
Neg logit contributions
 finished-0.002
 finally-0.002
 longer-0.002
 finish-0.002
 anymore-0.002
Token shiny
Token ID22441
Feature activation+1.84e+00

Pos logit contributions
 finished+0.030
 finally+0.026
 longer+0.023
 finish+0.023
 anymore+0.022
Neg logit contributions
ucer-0.030
unny-0.029
 Area-0.028
fish-0.028
 globe-0.028
Token red
Token ID2266
Feature activation+3.04e+00

Pos logit contributions
ucer+0.060
unny+0.057
 Area+0.055
 globe+0.053
fish+0.053
Neg logit contributions
 finished-0.065
 finally-0.056
 longer-0.054
 less-0.051
 even-0.051
Token apples
Token ID22514
Feature activation-1.14e+00

Pos logit contributions
ucer+0.109
unny+0.104
 Area+0.101
fish+0.099
 globe+0.098
Neg logit contributions
 finished-0.097
 finally-0.083
 longer-0.078
 less-0.074
 anymore-0.073
Token hanging
Token ID10938
Feature activation-5.18e-01

Pos logit contributions
 finished+0.025
 finally+0.020
 longer+0.018
 gust+0.018
 less+0.017
Neg logit contributions
ucer-0.050
fish-0.049
 globe-0.048
 Area-0.047
unny-0.047
Token from
Token ID422
Feature activation-8.53e-01

Pos logit contributions
 finished+0.015
 finally+0.012
 gust+0.011
 longer+0.011
 finish+0.010
Neg logit contributions
ucer-0.020
unny-0.020
 globe-0.019
fish-0.019
 Area-0.019
Token its
Token ID663
Feature activation-1.27e-01

Pos logit contributions
 finished+0.018
 finally+0.013
 gust+0.012
 finish+0.011
 longer+0.011
Neg logit contributions
ucer-0.038
 globe-0.037
 Area-0.036
unny-0.036
fish-0.036
Token branches
Token ID13737
Feature activation-1.88e+00

Pos logit contributions
 finished+0.005
 finally+0.004
 gust+0.004
 longer+0.004
 anymore+0.004
Neg logit contributions
unny-0.004
ucer-0.004
 globe-0.003
 Area-0.003
fish-0.003
Token metal
Token ID6147
Feature activation+2.21e+00

Pos logit contributions
 finished+0.013
 finally+0.011
 longer+0.010
 less+0.010
 anymore+0.010
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.016
fish-0.016
 globe-0.016
Token sign
Token ID1051
Feature activation-3.23e-01

Pos logit contributions
ucer+0.067
unny+0.064
 Area+0.061
fish+0.058
 globe+0.057
Neg logit contributions
 finished-0.083
 finally-0.073
 longer-0.070
 anymore-0.067
 less-0.067
Token that
Token ID326
Feature activation+1.21e+00

Pos logit contributions
 finished+0.009
 finally+0.008
 sweaty+0.007
 gust+0.007
 longer+0.007
Neg logit contributions
fish-0.011
 globe-0.011
ucer-0.011
 Area-0.010
fly-0.010
Token said
Token ID531
Feature activation+1.90e+00

Pos logit contributions
ucer+0.047
fish+0.046
 globe+0.045
 Area+0.044
unny+0.044
Neg logit contributions
 finished-0.032
 longer-0.027
 finally-0.026
 anymore-0.025
 less-0.025
Token "
Token ID366
Feature activation-1.58e+00

Pos logit contributions
ucer+0.070
 globe+0.067
fish+0.067
 Area+0.067
unny+0.066
Neg logit contributions
 finished-0.055
 finally-0.045
 longer-0.045
 sweaty-0.042
 gust-0.042
TokenD
Token ID35
Feature activation+3.49e+00

Pos logit contributions
 finished+0.059
 finally+0.052
 longer+0.049
 less+0.047
 finish+0.047
Neg logit contributions
ucer-0.048
unny-0.046
 Area-0.044
fish-0.043
 globe-0.042
Tokenanger
Token ID2564
Feature activation+5.46e-01

Pos logit contributions
ucer+0.086
 globe+0.079
fish+0.077
unny+0.076
 Area+0.076
Neg logit contributions
 finished-0.144
 finally-0.126
 finish-0.122
 at-0.122
 anymore-0.121
Token:
Token ID25
Feature activation+3.45e-01

Pos logit contributions
ucer+0.021
unny+0.020
 Area+0.019
fish+0.019
 globe+0.019
Neg logit contributions
 finished-0.016
 finally-0.014
 longer-0.013
 less-0.012
 gust-0.012
Token Do
Token ID2141
Feature activation-2.83e-01

Pos logit contributions
ucer+0.013
unny+0.012
 Area+0.012
fish+0.012
 globe+0.012
Neg logit contributions
 finished-0.010
 finally-0.009
 longer-0.008
 less-0.008
 finish-0.008
Token not
Token ID407
Feature activation-1.23e+00

Pos logit contributions
 finished+0.006
 finally+0.005
 longer+0.004
 anymore+0.004
 finish+0.004
Neg logit contributions
ucer-0.014
unny-0.013
 Area-0.013
 globe-0.012
fish-0.012
Token cross
Token ID3272
Feature activation-2.01e+00

Pos logit contributions
 finished+0.035
 finally+0.030
 longer+0.027
 less+0.026
 healthier+0.026
Neg logit contributions
ucer-0.046
unny-0.044
 Area-0.044
fish-0.043
 globe-0.042
TokenTom
Token ID13787
Feature activation+6.30e-01

Pos logit contributions
ucer+0.075
unny+0.072
 Area+0.070
fish+0.069
 globe+0.068
Neg logit contributions
 finished-0.058
 finally-0.049
 longer-0.046
 less-0.043
 finish-0.043
Token walked
Token ID6807
Feature activation-4.71e-01

Pos logit contributions
unny+0.024
fish+0.024
ucer+0.024
 globe+0.023
 Area+0.022
Neg logit contributions
 finished-0.015
 anymore-0.014
 longer-0.013
 gust-0.013
 healthier-0.012
Token slowly
Token ID6364
Feature activation-9.47e-02

Pos logit contributions
 finished+0.012
 gust+0.010
 finally+0.010
 anymore+0.009
 longer+0.009
Neg logit contributions
ucer-0.019
unny-0.019
 Area-0.019
fish-0.017
 globe-0.017
Token to
Token ID284
Feature activation+3.37e-01

Pos logit contributions
 finished+0.003
 finally+0.002
 gust+0.002
 especially+0.002
 okay+0.002
Neg logit contributions
 Area-0.003
ucer-0.003
fish-0.003
unny-0.003
 globe-0.003
Token the
Token ID262
Feature activation+5.48e-01

Pos logit contributions
ucer+0.017
unny+0.017
 Area+0.016
 globe+0.016
fish+0.016
Neg logit contributions
 finished-0.006
 finally-0.004
 longer-0.003
 anymore-0.003
 gust-0.003
Token old
Token ID1468
Feature activation+4.12e+00

Pos logit contributions
ucer+0.021
unny+0.020
 Area+0.019
eway+0.019
 globe+0.018
Neg logit contributions
 finished-0.016
 finally-0.014
 more-0.014
 finish-0.014
 less-0.013
Token sw
Token ID1509
Feature activation+2.30e+00

Pos logit contributions
ucer+0.162
unny+0.160
 Area+0.147
oris+0.147
eway+0.144
Neg logit contributions
 finished-0.105
 more-0.099
 longer-0.096
 finally-0.096
 even-0.096
Tokenan
Token ID272
Feature activation+1.75e+00

Pos logit contributions
ucer+0.046
unny+0.040
 globe+0.039
 Area+0.038
fish+0.035
Neg logit contributions
 finished-0.107
 finally-0.098
 longer-0.097
 finish-0.094
 at-0.093
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
ucer+0.091
unny+0.088
 Area+0.086
 globe+0.085
fish+0.085
Neg logit contributions
 finished-0.027
 finally-0.020
 longer-0.017
 less-0.015
 anymore-0.015
Token He
Token ID679
Feature activation+8.13e-01

Pos logit contributions
unny+0.006
ucer+0.006
 Area+0.005
 globe+0.005
eway+0.005
Neg logit contributions
 finished-0.004
 longer-0.003
 finally-0.003
 even-0.003
 especially-0.003
Token held
Token ID2714
Feature activation+3.41e-01

Pos logit contributions
ucer+0.030
unny+0.030
fish+0.030
 Area+0.029
 globe+0.028
Neg logit contributions
 finished-0.022
 anymore-0.019
 longer-0.018
 gust-0.018
 finally-0.018
Token to
Token ID284
Feature activation-4.27e-01

Pos logit contributions
ucer+0.043
unny+0.042
fish+0.040
 Area+0.040
 globe+0.039
Neg logit contributions
 finished-0.025
 gust-0.019
 finally-0.018
 rum-0.017
 longer-0.017
Token only
Token ID691
Feature activation-3.19e-02

Pos logit contributions
 finished+0.010
 gust+0.008
 finally+0.007
 anymore+0.007
 longer+0.007
Neg logit contributions
ucer-0.018
unny-0.017
fish-0.017
 globe-0.017
 Area-0.016
Token play
Token ID711
Feature activation-3.22e-01

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 gust+0.001
 anymore+0.001
Neg logit contributions
ucer-0.001
unny-0.001
 Area-0.001
fish-0.001
 globe-0.001
Token with
Token ID351
Feature activation+7.98e-01

Pos logit contributions
 finished+0.009
 gust+0.008
 finally+0.008
 rum+0.008
 sweaty+0.007
Neg logit contributions
ucer-0.011
 globe-0.011
 Area-0.011
fish-0.010
unny-0.010
Token one
Token ID530
Feature activation-9.45e-01

Pos logit contributions
ucer+0.031
fish+0.030
unny+0.030
 globe+0.030
 Area+0.029
Neg logit contributions
 finished-0.021
 finally-0.017
 gust-0.016
 finish-0.015
 longer-0.015
Token toy
Token ID13373
Feature activation+3.04e+00

Pos logit contributions
 finished+0.021
 finally+0.017
 gust+0.014
 rum+0.014
 bra+0.013
Neg logit contributions
ucer-0.041
fish-0.040
unny-0.040
 globe-0.040
 Area-0.038
Token at
Token ID379
Feature activation-4.94e-01

Pos logit contributions
ucer+0.123
fish+0.117
 globe+0.115
unny+0.114
 Area+0.111
Neg logit contributions
 finished-0.078
 finally-0.064
 gust-0.061
 rum-0.057
 bra-0.055
Token a
Token ID257
Feature activation+1.36e+00

Pos logit contributions
 finished+0.012
 bra+0.010
 gust+0.010
 finally+0.009
 longer+0.009
Neg logit contributions
ucer-0.020
 globe-0.019
 Area-0.019
unny-0.019
fish-0.018
Token time
Token ID640
Feature activation+1.32e+00

Pos logit contributions
ucer+0.055
unny+0.054
 Area+0.054
 globe+0.053
fish+0.052
Neg logit contributions
 finished-0.032
 finally-0.024
 gust-0.021
 at-0.021
 less-0.021
Token and
Token ID290
Feature activation-1.08e-01

Pos logit contributions
fish+0.046
ucer+0.046
unny+0.044
 globe+0.044
 Area+0.043
Neg logit contributions
 finished-0.032
 gust-0.028
 rum-0.026
 healthier-0.025
 itch-0.025
Token put
Token ID1234
Feature activation-3.48e-01

Pos logit contributions
 finished+0.003
 gust+0.002
 anymore+0.002
 longer+0.002
 finally+0.002
Neg logit contributions
ucer-0.004
fish-0.004
unny-0.004
 globe-0.004
 Area-0.004
Token The
Token ID383
Feature activation-4.96e-01

Pos logit contributions
 finished+0.009
 longer+0.008
 finally+0.007
 anymore+0.007
 even+0.007
Neg logit contributions
unny-0.015
 Area-0.014
ucer-0.014
 globe-0.013
fish-0.013
Token man
Token ID582
Feature activation-4.23e-01

Pos logit contributions
 finished+0.018
 finally+0.016
 longer+0.016
 anymore+0.015
 even+0.014
Neg logit contributions
ucer-0.014
 globe-0.014
fish-0.014
 Area-0.013
unny-0.013
Token was
Token ID373
Feature activation+2.02e-01

Pos logit contributions
 finished+0.011
 anymore+0.010
 healthier+0.010
 longer+0.010
 less+0.010
Neg logit contributions
fish-0.015
fly-0.014
ucer-0.014
unny-0.014
 Area-0.013
Token wearing
Token ID5762
Feature activation+1.83e+00

Pos logit contributions
 Area+0.007
fly+0.006
unny+0.006
ucer+0.006
 recorder+0.006
Neg logit contributions
 finished-0.005
 anymore-0.005
 longer-0.004
 gust-0.004
 healthier-0.004
Token an
Token ID281
Feature activation+4.57e-01

Pos logit contributions
 globe+0.063
ucer+0.060
 telescope+0.058
 magn+0.058
 compass+0.057
Neg logit contributions
 finished-0.049
 finish-0.041
 longer-0.041
 finally-0.040
 anymore-0.038
Token expensive
Token ID5789
Feature activation+3.21e+00

Pos logit contributions
ucer+0.016
 telescope+0.016
 Area+0.015
unny+0.015
fish+0.015
Neg logit contributions
 finished-0.012
 finally-0.010
 anymore-0.010
 longer-0.009
 less-0.009
Token suit
Token ID6050
Feature activation-3.23e-01

Pos logit contributions
ucer+0.095
 globe+0.089
unny+0.087
fish+0.087
 Area+0.087
Neg logit contributions
 finished-0.119
 finally-0.106
 longer-0.098
 finish-0.095
 less-0.095
Token and
Token ID290
Feature activation-2.67e-01

Pos logit contributions
 finished+0.008
 gust+0.007
 healthier+0.007
 finally+0.007
 less+0.006
Neg logit contributions
ucer-0.012
 globe-0.012
fish-0.011
 recorder-0.011
 Area-0.010
Token hat
Token ID6877
Feature activation-9.99e-01

Pos logit contributions
 finished+0.007
 anymore+0.005
 longer+0.005
 finish+0.005
 finally+0.005
Neg logit contributions
ucer-0.010
fish-0.010
unny-0.009
 Area-0.009
 globe-0.009
Token.
Token ID13
Feature activation-4.61e-01

Pos logit contributions
 finished+0.024
 gust+0.021
 healthier+0.021
 longer+0.020
 finish+0.020
Neg logit contributions
ucer-0.038
fish-0.037
 globe-0.037
fly-0.036
unny-0.034
Token He
Token ID679
Feature activation+1.08e+00

Pos logit contributions
 finished+0.013
 longer+0.011
 finally+0.011
 anymore+0.010
 gust+0.010
Neg logit contributions
unny-0.017
ucer-0.016
 Area-0.016
fish-0.015
 globe-0.015
Token I
Token ID314
Feature activation-9.42e-02

Pos logit contributions
ucer+0.044
fish+0.042
unny+0.041
 Area+0.040
 globe+0.040
Neg logit contributions
 finished-0.028
 finally-0.024
 less-0.022
 finish-0.021
 longer-0.021
Token will
Token ID481
Feature activation+4.15e-01

Pos logit contributions
 finished+0.003
 finally+0.003
 gust+0.003
 longer+0.003
 less+0.002
Neg logit contributions
ucer-0.003
unny-0.003
fish-0.003
 Area-0.003
 globe-0.003
Token wait
Token ID4043
Feature activation-5.48e-01

Pos logit contributions
ucer+0.016
unny+0.015
fish+0.015
 Area+0.015
 globe+0.015
Neg logit contributions
 finished-0.011
 gust-0.009
 finally-0.009
 longer-0.008
 anymore-0.008
Token for
Token ID329
Feature activation-9.05e-01

Pos logit contributions
 finished+0.013
 finally+0.010
 gust+0.010
whe+0.010
 bra+0.009
Neg logit contributions
ucer-0.021
fish-0.021
 Area-0.021
unny-0.020
 globe-0.020
Token your
Token ID534
Feature activation-5.60e-01

Pos logit contributions
 finished+0.026
 finally+0.021
 gust+0.019
 longer+0.019
 anymore+0.019
Neg logit contributions
ucer-0.034
unny-0.033
 Area-0.032
fish-0.032
 globe-0.031
Token signal
Token ID6737
Feature activation+1.66e-01

Pos logit contributions
 finished+0.018
 finally+0.015
 longer+0.014
 less+0.014
 gust+0.013
Neg logit contributions
ucer-0.020
unny-0.019
 Area-0.018
 globe-0.018
fish-0.018
Token.
Token ID13
Feature activation+7.81e-01

Pos logit contributions
ucer+0.006
unny+0.006
fish+0.006
 Area+0.006
 globe+0.006
Neg logit contributions
 finished-0.004
 finally-0.004
 gust-0.004
 longer-0.003
 healthier-0.003
Token Over
Token ID3827
Feature activation-1.62e+00

Pos logit contributions
ucer+0.030
fish+0.028
unny+0.028
 Area+0.027
 globe+0.027
Neg logit contributions
 finished-0.023
 finally-0.020
 longer-0.018
 less-0.018
 finish-0.018
Token,"
Token ID553
Feature activation-8.04e-01

Pos logit contributions
 finished+0.034
 finally+0.026
 gust+0.023
 healthier+0.022
 bra+0.021
Neg logit contributions
ucer-0.071
 Area-0.071
unny-0.070
fish-0.068
 globe-0.068
Token the
Token ID262
Feature activation-8.35e-01

Pos logit contributions
 finished+0.020
 finally+0.015
 anymore+0.015
 longer+0.015
 finish+0.014
Neg logit contributions
ucer-0.033
unny-0.032
fish-0.031
 Area-0.031
 globe-0.031
Token man
Token ID582
Feature activation-7.89e-01

Pos logit contributions
 finished+0.027
 finally+0.023
 longer+0.021
 less+0.020
 finish+0.020
Neg logit contributions
ucer-0.030
unny-0.029
 Area-0.028
fish-0.027
 globe-0.027
Token they
Token ID484
Feature activation-1.07e+00

Pos logit contributions
ucer+0.040
 globe+0.039
fish+0.039
 Area+0.039
unny+0.037
Neg logit contributions
 finished-0.037
 finally-0.030
 finish-0.028
 bra-0.028
 longer-0.028
Token saw
Token ID2497
Feature activation-4.81e-01

Pos logit contributions
 finished+0.027
 less+0.023
 longer+0.023
 anymore+0.022
 healthier+0.022
Neg logit contributions
ucer-0.041
fish-0.039
 Area-0.039
unny-0.038
 globe-0.037
Token the
Token ID262
Feature activation-2.16e-01

Pos logit contributions
 finished+0.012
 finally+0.009
 longer+0.009
 finish+0.008
 gust+0.008
Neg logit contributions
ucer-0.020
 globe-0.019
fish-0.019
 Area-0.019
unny-0.018
Token flower
Token ID15061
Feature activation+4.35e-01

Pos logit contributions
 finished+0.007
 finally+0.006
 longer+0.005
 less+0.005
 anymore+0.005
Neg logit contributions
ucer-0.008
unny-0.008
 Area-0.007
fish-0.007
 globe-0.007
Token and
Token ID290
Feature activation+9.49e-03

Pos logit contributions
fish+0.018
ucer+0.018
 globe+0.017
fly+0.017
unny+0.017
Neg logit contributions
 finished-0.010
 finally-0.008
 gust-0.007
 longer-0.007
 bra-0.007
Token they
Token ID484
Feature activation+6.52e-01

Pos logit contributions
ucer+0.000
fish+0.000
 Area+0.000
 globe+0.000
unny+0.000
Neg logit contributions
 finished-0.000
 finally-0.000
 longer-0.000
 anymore-0.000
 gust-0.000
Token agreed
Token ID4987
Feature activation+7.89e-01

Pos logit contributions
ucer+0.027
fish+0.026
 globe+0.025
unny+0.025
 Area+0.025
Neg logit contributions
 finished-0.015
 longer-0.012
 finally-0.012
 anymore-0.012
 less-0.011
Token with
Token ID351
Feature activation+1.05e+00

Pos logit contributions
ucer+0.034
 Area+0.032
fish+0.032
unny+0.032
 globe+0.031
Neg logit contributions
 finished-0.018
 finally-0.014
 gust-0.013
 longer-0.012
 sweaty-0.012
Token the
Token ID262
Feature activation+2.75e-01

Pos logit contributions
ucer+0.041
 globe+0.039
 Area+0.038
fish+0.038
unny+0.038
Neg logit contributions
 finished-0.028
 finally-0.023
 longer-0.021
 finish-0.020
 gust-0.020
Token message
Token ID3275
Feature activation+1.66e+00

Pos logit contributions
ucer+0.010
unny+0.009
 Area+0.009
fish+0.009
 globe+0.009
Neg logit contributions
 finished-0.009
 finally-0.008
 longer-0.007
 less-0.007
 finish-0.007
Token.
Token ID13
Feature activation-3.54e-01

Pos logit contributions
ucer+0.072
fish+0.070
 globe+0.068
unny+0.067
 Area+0.067
Neg logit contributions
 finished-0.036
 finally-0.028
 gust-0.028
 rum-0.026
 sweaty-0.025
Token very
Token ID845
Feature activation+1.32e-01

Pos logit contributions
 finished+0.000
 anymore+0.000
 gust+0.000
 longer+0.000
 finish+0.000
Neg logit contributions
ucer-0.000
fly-0.000
 fossil-0.000
fish-0.000
 Area-0.000
Token proud
Token ID6613
Feature activation+7.96e-01

Pos logit contributions
ucer+0.005
fish+0.005
unny+0.005
 Area+0.005
 globe+0.005
Neg logit contributions
 finished-0.003
 anymore-0.003
 finally-0.003
 gust-0.003
 longer-0.002
Token of
Token ID286
Feature activation-6.37e-01

Pos logit contributions
ucer+0.035
fish+0.035
unny+0.034
 Area+0.034
 globe+0.033
Neg logit contributions
 finished-0.017
 finally-0.014
 finish-0.011
 longer-0.011
 gust-0.011
Token his
Token ID465
Feature activation-4.95e-02

Pos logit contributions
 finished+0.013
 finally+0.010
 longer+0.009
 gust+0.008
 finish+0.008
Neg logit contributions
ucer-0.030
unny-0.029
 Area-0.029
 globe-0.028
fish-0.028
Token shield
Token ID7614
Feature activation-8.74e-02

Pos logit contributions
 finished+0.002
 finally+0.002
 longer+0.002
 less+0.002
 anymore+0.002
Neg logit contributions
ucer-0.001
unny-0.001
fish-0.001
 globe-0.001
 Area-0.001
Token,
Token ID11
Feature activation+7.75e-01

Pos logit contributions
 finished+0.002
 finally+0.002
 gust+0.001
 longer+0.001
 healthier+0.001
Neg logit contributions
ucer-0.004
 globe-0.004
fish-0.004
unny-0.004
 Area-0.004
Token and
Token ID290
Feature activation-6.40e-01

Pos logit contributions
 globe+0.032
ucer+0.032
fish+0.032
 Area+0.031
unny+0.031
Neg logit contributions
 finished-0.018
 finally-0.013
 finish-0.012
 longer-0.012
 gust-0.012
Token all
Token ID477
Feature activation+3.33e-01

Pos logit contributions
 finished+0.017
 anymore+0.013
 gust+0.013
 longer+0.013
 finally+0.012
Neg logit contributions
ucer-0.025
fish-0.024
 globe-0.024
unny-0.023
 Area-0.023
Token other
Token ID584
Feature activation+1.82e-01

Pos logit contributions
ucer+0.015
fish+0.015
 globe+0.014
unny+0.014
 Area+0.014
Neg logit contributions
 finished-0.007
 finally-0.005
 longer-0.005
 gust-0.005
 healthier-0.004
Token knights
Token ID27536
Feature activation-7.05e-01

Pos logit contributions
ucer+0.005
fish+0.005
unny+0.005
 globe+0.005
 Area+0.005
Neg logit contributions
 finished-0.007
 finally-0.006
 finish-0.006
 longer-0.005
 gust-0.005
Token were
Token ID547
Feature activation-1.36e-01

Pos logit contributions
 finished+0.015
 finally+0.012
 longer+0.010
 less+0.009
 finish+0.009
Neg logit contributions
ucer-0.033
unny-0.032
 Area-0.031
fish-0.031
 globe-0.030
Token meet
Token ID1826
Feature activation-4.92e-01

Pos logit contributions
ucer+0.004
unny+0.003
 Area+0.003
 globe+0.003
fish+0.003
Neg logit contributions
 finished-0.003
 finally-0.002
 longer-0.002
 gust-0.002
 less-0.002
Token you
Token ID345
Feature activation+7.39e-01

Pos logit contributions
 finished+0.016
 finally+0.013
 gust+0.012
 longer+0.012
 finish+0.012
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.017
fish-0.016
 globe-0.016
Token."
Token ID526
Feature activation-5.18e-01

Pos logit contributions
ucer+0.030
unny+0.029
 Area+0.029
fish+0.028
 globe+0.028
Neg logit contributions
 finished-0.019
 finally-0.016
 gust-0.014
 longer-0.014
 finish-0.013
Token Lily
Token ID20037
Feature activation+1.52e-02

Pos logit contributions
 finished+0.010
 finally+0.008
 longer+0.006
 less+0.006
 finish+0.006
Neg logit contributions
ucer-0.026
fish-0.025
unny-0.025
 Area-0.025
 globe-0.024
Token was
Token ID373
Feature activation-5.31e-02

Pos logit contributions
ucer+0.001
unny+0.001
 Area+0.001
fish+0.001
 globe+0.001
Neg logit contributions
 finished-0.000
 finally-0.000
 longer-0.000
 less-0.000
 anymore-0.000
Token happy
Token ID3772
Feature activation+2.82e-01

Pos logit contributions
 finished+0.001
 gust+0.001
 longer+0.001
 anymore+0.001
 finish+0.001
Neg logit contributions
 globe-0.002
 Area-0.002
ucer-0.002
fly-0.002
unny-0.002
Token that
Token ID326
Feature activation+1.55e+00

Pos logit contributions
ucer+0.013
unny+0.012
fish+0.012
 Area+0.012
 globe+0.012
Neg logit contributions
 finished-0.006
 finally-0.005
 longer-0.004
 gust-0.004
 finish-0.004
Token her
Token ID607
Feature activation-1.68e+00

Pos logit contributions
ucer+0.049
unny+0.043
 Area+0.042
 globe+0.042
 telescope+0.041
Neg logit contributions
 finished-0.053
 finally-0.043
 longer-0.042
 finish-0.041
 rum-0.041
Token mom
Token ID1995
Feature activation-1.92e+00

Pos logit contributions
 finished+0.051
 finally+0.044
 longer+0.041
 less+0.039
 gust+0.038
Neg logit contributions
ucer-0.061
unny-0.059
 globe-0.057
 Area-0.057
fish-0.056
Tokenmy
Token ID1820
Feature activation+1.01e-01

Pos logit contributions
 finished+0.050
 finally+0.042
 longer+0.039
 gust+0.037
 less+0.036
Neg logit contributions
ucer-0.079
unny-0.076
 Area-0.073
 globe-0.073
fish-0.073
Token liked
Token ID8288
Feature activation+1.83e-01

Pos logit contributions
ucer+0.004
unny+0.004
 Area+0.004
fish+0.004
 globe+0.004
Neg logit contributions
 finished-0.002
 longer-0.002
 finally-0.002
 gust-0.002
 anymore-0.002
Tokenila
Token ID10102
Feature activation-5.17e-01

Pos logit contributions
ucer+0.047
 Area+0.044
unny+0.044
 globe+0.044
 appearances+0.042
Neg logit contributions
 finished-0.045
 finally-0.041
 at-0.040
 longer-0.038
 anymore-0.037
Token and
Token ID290
Feature activation-9.77e-01

Pos logit contributions
 finished+0.012
 finally+0.009
 longer+0.008
 finish+0.008
 less+0.008
Neg logit contributions
ucer-0.023
unny-0.022
fish-0.022
 globe-0.022
 Area-0.022
Token Ben
Token ID3932
Feature activation-4.81e-01

Pos logit contributions
 finished+0.022
 finally+0.018
 longer+0.016
 less+0.015
 finish+0.015
Neg logit contributions
ucer-0.044
unny-0.043
 Area-0.042
 globe-0.041
fish-0.041
Token,"
Token ID553
Feature activation-1.23e+00

Pos logit contributions
 finished+0.013
 finally+0.011
 longer+0.010
 gust+0.009
 less+0.009
Neg logit contributions
ucer-0.020
unny-0.019
 Area-0.018
fish-0.018
 globe-0.018
Token Sam
Token ID3409
Feature activation-8.30e-01

Pos logit contributions
 finished+0.028
 finally+0.022
 longer+0.020
 anymore+0.019
 finish+0.018
Neg logit contributions
ucer-0.055
unny-0.053
fish-0.052
 Area-0.051
 globe-0.051
Token said
Token ID531
Feature activation+5.85e-01

Pos logit contributions
 finished+0.024
 longer+0.020
 finally+0.020
 healthier+0.020
 anymore+0.019
Neg logit contributions
ucer-0.029
fish-0.028
unny-0.028
 Area-0.028
 globe-0.027
Token.
Token ID13
Feature activation+9.32e-01

Pos logit contributions
ucer+0.023
unny+0.023
fish+0.022
 globe+0.021
 Area+0.021
Neg logit contributions
 finished-0.016
 finally-0.012
 especially-0.011
 gust-0.011
 finish-0.011
Token "
Token ID366
Feature activation-4.02e-01

Pos logit contributions
ucer+0.043
unny+0.040
 Area+0.039
fish+0.039
 globe+0.039
Neg logit contributions
 finished-0.021
 finally-0.017
 longer-0.015
 less-0.015
 even-0.014
TokenI
Token ID40
Feature activation-3.12e-01

Pos logit contributions
 finished+0.010
 finally+0.010
 even+0.009
 less+0.008
 longer+0.008
Neg logit contributions
ucer-0.016
unny-0.015
fish-0.015
 Area-0.014
oris-0.014
Token saw
Token ID2497
Feature activation+2.34e-01

Pos logit contributions
 finished+0.009
 finally+0.008
 longer+0.008
 gust+0.007
 less+0.007
Neg logit contributions
ucer-0.011
unny-0.011
 Area-0.010
fish-0.010
 globe-0.010
Token your
Token ID534
Feature activation-7.32e-01

Pos logit contributions
ucer+0.010
unny+0.009
 Area+0.009
fish+0.009
 globe+0.009
Neg logit contributions
 finished-0.006
 finally-0.005
 longer-0.005
 less-0.004
 anymore-0.004
Token sm
Token ID895
Feature activation-9.52e-01

Pos logit contributions
 finished+0.033
 finally+0.030
whe+0.025
 gust+0.024
 longer+0.023
Neg logit contributions
fish-0.069
ucer-0.068
 Area-0.066
 globe-0.065
unny-0.062
Tokenelly
Token ID6148
Feature activation-3.00e-01

Pos logit contributions
 finished+0.039
 finally+0.035
 longer+0.033
 less+0.032
 finish+0.032
Neg logit contributions
ucer-0.026
unny-0.024
 Area-0.023
fish-0.022
 globe-0.022
Token,
Token ID11
Feature activation+5.06e-01

Pos logit contributions
 finished+0.008
 finally+0.007
 gust+0.007
 longer+0.006
 finish+0.006
Neg logit contributions
ucer-0.011
fish-0.011
 Area-0.011
unny-0.011
 globe-0.011
Token but
Token ID475
Feature activation-3.46e-02

Pos logit contributions
ucer+0.019
fish+0.019
 globe+0.018
 Area+0.018
unny+0.018
Neg logit contributions
 finished-0.013
 finally-0.010
 anymore-0.009
 longer-0.009
 gust-0.009
Token it
Token ID340
Feature activation-1.48e+00

Pos logit contributions
 finished+0.001
 finally+0.001
 longer+0.001
 gust+0.001
 bra+0.001
Neg logit contributions
ucer-0.001
unny-0.001
fish-0.001
 Area-0.001
 globe-0.001
Tokenâ
Token ID22940
Feature activation-9.88e-01

Pos logit contributions
 finished+0.048
 finally+0.042
 longer+0.041
 gust+0.040
 anymore+0.039
Neg logit contributions
ucer-0.048
unny-0.047
fish-0.046
 Area-0.044
 globe-0.044
Token€
Token ID26391
Feature activation+1.39e+00

Pos logit contributions
 finished+0.029
 finally+0.025
 longer+0.025
 even+0.024
 less+0.023
Neg logit contributions
ucer-0.036
unny-0.034
 Area-0.034
 globe-0.033
fish-0.032
Tokenâ„¢
Token ID8151
Feature activation-5.06e-01

Pos logit contributions
ucer+0.044
unny+0.042
 Area+0.040
 globe+0.039
fish+0.038
Neg logit contributions
 finished-0.050
 finally-0.044
 longer-0.042
 less-0.040
 finish-0.039
Tokens
Token ID82
Feature activation-1.13e+00

Pos logit contributions
 finished+0.020
 finally+0.018
 longer+0.018
 bra+0.017
 gust+0.017
Neg logit contributions
ucer-0.014
unny-0.013
 Area-0.012
fish-0.012
 globe-0.012
Token good
Token ID922
Feature activation-1.25e-01

Pos logit contributions
 finished+0.026
 finally+0.022
 longer+0.020
 gust+0.020
 bra+0.020
Neg logit contributions
ucer-0.046
unny-0.045
fish-0.044
 Area-0.044
 globe-0.043
Token for
Token ID329
Feature activation-1.02e+00

Pos logit contributions
 finished+0.003
 finally+0.002
 gust+0.002
 longer+0.002
 less+0.002
Neg logit contributions
ucer-0.005
fish-0.005
unny-0.005
 Area-0.005
 globe-0.005
Token a
Token ID257
Feature activation-5.41e-01

Pos logit contributions
ucer+0.031
unny+0.030
fish+0.029
 Area+0.029
fly+0.029
Neg logit contributions
 finished-0.018
 finally-0.015
 longer-0.013
 gust-0.013
 finish-0.012
Token pet
Token ID4273
Feature activation+2.64e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.012
 less+0.011
 finish+0.011
Neg logit contributions
ucer-0.021
unny-0.021
 Area-0.020
fish-0.020
 globe-0.020
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
ucer+0.011
unny+0.011
 Area+0.011
fish+0.011
 globe+0.010
Neg logit contributions
 finished-0.007
 finally-0.006
 longer-0.005
 gust-0.005
 sweaty-0.004
Token It
Token ID632
Feature activation+4.98e-01

Pos logit contributions
ucer+0.018
unny+0.017
 Area+0.016
fish+0.016
 globe+0.016
Neg logit contributions
 finished-0.011
 finally-0.009
 longer-0.008
 less-0.008
 finish-0.008
Token is
Token ID318
Feature activation-5.82e-01

Pos logit contributions
ucer+0.020
unny+0.019
 Area+0.018
 globe+0.018
fish+0.018
Neg logit contributions
 finished-0.015
 finally-0.012
 longer-0.011
 less-0.011
 even-0.011
Token a
Token ID257
Feature activation-5.69e-01

Pos logit contributions
 finished+0.013
 finally+0.011
 gust+0.010
 longer+0.009
 finish+0.009
Neg logit contributions
ucer-0.024
 Area-0.023
unny-0.023
fish-0.023
fly-0.023
Token wild
Token ID4295
Feature activation+8.43e-01

Pos logit contributions
 finished+0.015
 finally+0.013
 longer+0.012
 less+0.011
 finish+0.011
Neg logit contributions
ucer-0.023
unny-0.022
 Area-0.022
fish-0.021
 globe-0.021
Token animal
Token ID5044
Feature activation+8.56e-01

Pos logit contributions
ucer+0.028
unny+0.027
 Area+0.026
fish+0.025
 globe+0.024
Neg logit contributions
 finished-0.029
 finally-0.025
 longer-0.024
 anymore-0.023
 less-0.023
Token.
Token ID13
Feature activation+3.67e-01

Pos logit contributions
ucer+0.040
unny+0.038
 Area+0.038
fish+0.037
 globe+0.037
Neg logit contributions
 finished-0.018
 finally-0.014
 longer-0.012
 gust-0.011
 finish-0.011
Token It
Token ID632
Feature activation+8.61e-01

Pos logit contributions
ucer+0.015
unny+0.014
 Area+0.014
fish+0.014
 globe+0.014
Neg logit contributions
 finished-0.010
 finally-0.008
 longer-0.007
 less-0.007
 finish-0.007
Token does
Token ID857
Feature activation+6.01e-01

Pos logit contributions
ucer+0.032
unny+0.030
 Area+0.029
 globe+0.028
fish+0.028
Neg logit contributions
 finished-0.028
 finally-0.024
 longer-0.022
 less-0.021
 even-0.021
Token wanted
Token ID2227
Feature activation+1.46e-01

Pos logit contributions
 finished+0.009
 anymore+0.009
 longer+0.008
 less+0.008
 finish+0.008
Neg logit contributions
fish-0.010
unny-0.010
ucer-0.010
fly-0.010
 Area-0.009
Token to
Token ID284
Feature activation-3.94e-01

Pos logit contributions
unny+0.005
ucer+0.005
 Area+0.005
 globe+0.005
fish+0.005
Neg logit contributions
 finished-0.004
 gust-0.003
 finally-0.003
 longer-0.003
 rum-0.003
Token play
Token ID711
Feature activation-5.74e-01

Pos logit contributions
 finished+0.011
 gust+0.009
 finally+0.009
 longer+0.009
 anymore+0.008
Neg logit contributions
unny-0.014
ucer-0.014
fish-0.014
 globe-0.013
 Area-0.013
Token.
Token ID13
Feature activation-5.85e-01

Pos logit contributions
 finished+0.017
 finally+0.013
 rum+0.013
 gust+0.013
 sweaty+0.012
Neg logit contributions
 Area-0.019
ucer-0.019
fish-0.019
 globe-0.019
unny-0.019
Token They
Token ID1119
Feature activation+8.06e-01

Pos logit contributions
 finished+0.017
 longer+0.014
 finally+0.014
 even+0.013
 gust+0.012
Neg logit contributions
unny-0.022
ucer-0.020
 Area-0.020
 globe-0.019
fish-0.018
Token played
Token ID2826
Feature activation-6.91e-01

Pos logit contributions
ucer+0.035
unny+0.034
 Area+0.033
fish+0.032
 globe+0.032
Neg logit contributions
 finished-0.017
 finally-0.013
 anymore-0.013
 less-0.013
 longer-0.013
Token for
Token ID329
Feature activation-3.86e-01

Pos logit contributions
 finished+0.020
 finally+0.016
 longer+0.015
 gust+0.015
 rum+0.014
Neg logit contributions
ucer-0.026
unny-0.025
 Area-0.025
 globe-0.024
fish-0.024
Token a
Token ID257
Feature activation+5.03e-01

Pos logit contributions
 finished+0.007
 finally+0.006
 longer+0.005
 finish+0.004
 gust+0.004
Neg logit contributions
ucer-0.018
unny-0.018
 Area-0.018
 globe-0.017
fish-0.017
Token little
Token ID1310
Feature activation+1.26e+00

Pos logit contributions
ucer+0.024
unny+0.023
 Area+0.023
 globe+0.022
rooms+0.021
Neg logit contributions
 finished-0.011
 finally-0.009
 longer-0.008
 even-0.007
 finish-0.007
Token while
Token ID981
Feature activation-9.44e-02

Pos logit contributions
ucer+0.055
unny+0.052
 Area+0.051
 globe+0.050
fish+0.050
Neg logit contributions
 finished-0.032
 finally-0.027
 longer-0.026
 even-0.023
 finish-0.023
Token,
Token ID11
Feature activation+2.25e-01

Pos logit contributions
 finished+0.003
 finish+0.002
 sweaty+0.002
 healthier+0.002
 bra+0.002
Neg logit contributions
unny-0.003
fish-0.003
 Area-0.003
 globe-0.003
fly-0.003
Token kept
Token ID4030
Feature activation+1.15e+00

Pos logit contributions
ucer+0.019
fish+0.019
unny+0.018
 globe+0.018
 Area+0.018
Neg logit contributions
 finished-0.010
 gust-0.008
 healthier-0.008
 less-0.008
 longer-0.008
Token playing
Token ID2712
Feature activation+7.24e-02

Pos logit contributions
 Area+0.042
ucer+0.042
 globe+0.041
fish+0.039
utes+0.039
Neg logit contributions
 finished-0.029
 anymore-0.023
 gust-0.023
 longer-0.023
 finally-0.023
Token it
Token ID340
Feature activation+3.69e-01

Pos logit contributions
 globe+0.003
ucer+0.003
 Area+0.003
fish+0.003
unny+0.002
Neg logit contributions
 finished-0.002
 finally-0.002
 gust-0.002
 rum-0.002
 sweaty-0.001
Token every
Token ID790
Feature activation-5.28e-01

Pos logit contributions
fish+0.013
 globe+0.013
ucer+0.013
unny+0.012
 Area+0.012
Neg logit contributions
 finished-0.010
 gust-0.009
 finally-0.008
 rum-0.008
 Dr-0.008
Token day
Token ID1110
Feature activation+9.00e-01

Pos logit contributions
 finished+0.014
 finally+0.011
 less+0.010
 longer+0.010
 bra+0.010
Neg logit contributions
ucer-0.021
unny-0.021
 Area-0.020
fish-0.020
 globe-0.020
Token.
Token ID13
Feature activation-5.69e-01

Pos logit contributions
fish+0.030
ucer+0.029
 globe+0.028
 Area+0.027
unny+0.027
Neg logit contributions
 finished-0.025
 gust-0.021
 rum-0.020
 finally-0.020
 healthier-0.020
Token They
Token ID1119
Feature activation+1.08e+00

Pos logit contributions
 finished+0.016
 finally+0.013
 longer+0.013
 gust+0.012
 bra+0.012
Neg logit contributions
ucer-0.022
unny-0.022
 Area-0.021
 globe-0.021
fish-0.020
Token would
Token ID561
Feature activation+8.70e-01

Pos logit contributions
fish+0.043
ucer+0.042
 globe+0.040
unny+0.040
 Area+0.038
Neg logit contributions
 finished-0.023
 anymore-0.021
 gust-0.021
 less-0.021
 longer-0.021
Token all
Token ID477
Feature activation+1.02e+00

Pos logit contributions
ucer+0.033
 globe+0.032
fish+0.032
unny+0.032
 Area+0.031
Neg logit contributions
 finished-0.022
 gust-0.018
 finally-0.018
 longer-0.017
 anymore-0.017
Token join
Token ID4654
Feature activation-4.94e-01

Pos logit contributions
ucer+0.037
fish+0.037
unny+0.035
 globe+0.035
fly+0.034
Neg logit contributions
 finished-0.027
 finally-0.023
 gust-0.022
 longer-0.022
 healthier-0.022
Token together
Token ID1978
Feature activation+5.92e-01

Pos logit contributions
 finished+0.011
 finally+0.008
 longer+0.007
 less+0.007
 gust+0.007
Neg logit contributions
ucer-0.022
unny-0.022
 Area-0.021
fish-0.021
 globe-0.021
Token round
Token ID2835
Feature activation+3.97e-01

Pos logit contributions
 finished+0.017
 finally+0.014
 longer+0.013
 anymore+0.013
 finish+0.012
Neg logit contributions
ucer-0.025
 globe-0.024
fish-0.024
unny-0.024
 Area-0.024
Token and
Token ID290
Feature activation-8.41e-01

Pos logit contributions
ucer+0.017
fish+0.017
 globe+0.016
unny+0.016
 Area+0.016
Neg logit contributions
 finished-0.009
 finally-0.008
 longer-0.006
 finish-0.006
 gust-0.006
Token shiny
Token ID22441
Feature activation+8.92e-01

Pos logit contributions
 finished+0.024
 finally+0.020
 longer+0.019
 anymore+0.018
 finish+0.017
Neg logit contributions
ucer-0.032
 globe-0.031
unny-0.030
 Area-0.030
fish-0.030
Token.
Token ID13
Feature activation+3.55e-01

Pos logit contributions
ucer+0.039
 globe+0.039
fish+0.038
 Area+0.037
unny+0.037
Neg logit contributions
 finished-0.020
 finally-0.017
 finish-0.013
 longer-0.013
 gust-0.013
Token It
Token ID632
Feature activation+7.32e-01

Pos logit contributions
ucer+0.016
unny+0.015
fish+0.014
 Area+0.014
 globe+0.014
Neg logit contributions
 finished-0.009
 finally-0.007
 longer-0.006
 less-0.006
 anymore-0.006
Token looks
Token ID3073
Feature activation-2.62e-01

Pos logit contributions
ucer+0.026
unny+0.024
 Area+0.023
 globe+0.023
fish+0.023
Neg logit contributions
 finished-0.024
 finally-0.021
 longer-0.020
 less-0.019
 finish-0.019
Token like
Token ID588
Feature activation-2.95e-01

Pos logit contributions
 finished+0.006
 finally+0.004
whe+0.004
 finish+0.004
 gust+0.004
Neg logit contributions
fish-0.010
 Area-0.010
ucer-0.009
 globe-0.009
 fossil-0.009
Token a
Token ID257
Feature activation-4.91e-01

Pos logit contributions
 finished+0.007
 finally+0.005
 longer+0.005
 finish+0.005
 anymore+0.005
Neg logit contributions
ucer-0.012
fish-0.012
 Area-0.012
 globe-0.012
unny-0.011
Token balloon
Token ID21190
Feature activation-5.09e-01

Pos logit contributions
 finished+0.016
 finally+0.014
 longer+0.013
 less+0.012
 finish+0.012
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.016
fish-0.015
 globe-0.015
Token,
Token ID11
Feature activation+5.51e-01

Pos logit contributions
 finished+0.011
 finally+0.009
 longer+0.007
 gust+0.007
 healthier+0.007
Neg logit contributions
ucer-0.023
fish-0.023
 globe-0.022
unny-0.022
 Area-0.022
Token but
Token ID475
Feature activation-3.29e-02

Pos logit contributions
ucer+0.025
unny+0.024
 Area+0.024
 globe+0.024
fish+0.023
Neg logit contributions
 finished-0.012
 finally-0.009
 longer-0.008
 finish-0.008
 gust-0.008
Token
Token ID198
Feature activation-6.66e-01

Pos logit contributions
 finished+0.011
 finally+0.009
 less+0.007
 at+0.007
 so+0.007
Neg logit contributions
ucer-0.030
fish-0.029
 globe-0.029
 Area-0.028
 telescope-0.028
Token
Token ID198
Feature activation-4.27e-01

Pos logit contributions
 finished+0.012
 finally+0.010
 about+0.007
 even+0.007
 longer+0.007
Neg logit contributions
ucer-0.034
 Area-0.032
unny-0.031
 globe-0.031
fish-0.031
TokenMax
Token ID11518
Feature activation+1.15e+00

Pos logit contributions
 finished+0.014
 finally+0.012
 finish+0.011
 longer+0.011
 even+0.011
Neg logit contributions
ucer-0.015
 globe-0.014
fish-0.014
 Area-0.014
unny-0.014
Token learned
Token ID4499
Feature activation+3.06e-01

Pos logit contributions
ucer+0.049
unny+0.048
 Area+0.047
fish+0.046
 globe+0.045
Neg logit contributions
 finished-0.026
 finally-0.021
 longer-0.020
 anymore-0.020
 gust-0.019
Token to
Token ID284
Feature activation+4.65e-01

Pos logit contributions
ucer+0.015
unny+0.014
 Area+0.014
 globe+0.014
fish+0.014
Neg logit contributions
 finished-0.006
 finally-0.005
 longer-0.004
 less-0.004
 even-0.004
Token sit
Token ID1650
Feature activation-2.69e+00

Pos logit contributions
ucer+0.021
unny+0.020
 Area+0.020
fish+0.019
 globe+0.019
Neg logit contributions
 finished-0.011
 finally-0.009
 longer-0.008
 finish-0.007
 less-0.007
Token,
Token ID11
Feature activation+7.48e-01

Pos logit contributions
 finished+0.063
 finally+0.049
 gust+0.044
 longer+0.043
 finish+0.042
Neg logit contributions
ucer-0.121
unny-0.117
 Area-0.114
 globe-0.113
fish-0.112
Token stay
Token ID2652
Feature activation-4.67e-01

Pos logit contributions
fish+0.025
ucer+0.024
 appearances+0.024
 Area+0.024
 globe+0.023
Neg logit contributions
 finished-0.019
 gust-0.015
 anymore-0.015
 finally-0.015
 longer-0.014
Token,
Token ID11
Feature activation+7.83e-02

Pos logit contributions
 finished+0.011
 finally+0.009
 gust+0.008
 longer+0.008
 anymore+0.008
Neg logit contributions
ucer-0.020
unny-0.020
 Area-0.019
 globe-0.019
fish-0.019
Token and
Token ID290
Feature activation+9.61e-02

Pos logit contributions
fish+0.003
 globe+0.003
ucer+0.003
fly+0.002
 recorder+0.002
Neg logit contributions
 finished-0.002
 gust-0.002
 anymore-0.001
 finally-0.001
whe-0.001
Token roll
Token ID4836
Feature activation-4.72e-01

Pos logit contributions
ucer+0.003
fish+0.003
unny+0.003
 globe+0.003
fly+0.003
Neg logit contributions
 finished-0.002
 gust-0.002
 anymore-0.002
 longer-0.002
 finally-0.002
Token angry
Token ID7954
Feature activation-1.32e+00

Pos logit contributions
ucer+0.010
 recorder+0.008
 Area+0.008
unny+0.008
 device+0.008
Neg logit contributions
 gust-0.006
 anymore-0.006
 finished-0.006
hy-0.005
 fifteen-0.005
Token.
Token ID13
Feature activation-4.44e-01

Pos logit contributions
 finished+0.035
 finally+0.029
 gust+0.026
 healthier+0.025
 finish+0.024
Neg logit contributions
ucer-0.049
fish-0.047
 Area-0.047
 globe-0.045
unny-0.045
Token It
Token ID632
Feature activation+1.18e+00

Pos logit contributions
 finished+0.012
 longer+0.010
 finally+0.009
 anymore+0.009
 bra+0.009
Neg logit contributions
ucer-0.017
unny-0.017
 Area-0.016
 globe-0.015
oris-0.015
Token was
Token ID373
Feature activation-2.69e-01

Pos logit contributions
ucer+0.039
fish+0.039
unny+0.037
 Area+0.036
fly+0.036
Neg logit contributions
 finished-0.032
 anymore-0.029
 longer-0.029
 healthier-0.028
 gust-0.028
Token too
Token ID1165
Feature activation+1.78e-01

Pos logit contributions
 finished+0.005
 anymore+0.005
 healthier+0.005
 finally+0.005
 bra+0.005
Neg logit contributions
 Area-0.009
 disc-0.009
 recorder-0.009
ucer-0.009
 device-0.009
Token early
Token ID1903
Feature activation-2.68e+00

Pos logit contributions
ucer+0.008
unny+0.007
 Area+0.007
fish+0.007
 globe+0.007
Neg logit contributions
 finished-0.004
 finally-0.004
 longer-0.003
 anymore-0.003
 less-0.003
Token to
Token ID284
Feature activation+1.75e-02

Pos logit contributions
 finished+0.058
 scr+0.052
 healthier+0.051
 less+0.050
 gust+0.050
Neg logit contributions
 Area-0.096
ucer-0.096
 globe-0.091
fish-0.091
 recorder-0.087
Token take
Token ID1011
Feature activation-5.30e-01

Pos logit contributions
ucer+0.001
unny+0.001
fish+0.001
aby+0.001
 globe+0.001
Neg logit contributions
 finished-0.000
 gust-0.000
 bored-0.000
 less-0.000
 healthier-0.000
Token a
Token ID257
Feature activation+7.50e-01

Pos logit contributions
 finished+0.013
 finally+0.010
 gust+0.010
 longer+0.010
 healthier+0.009
Neg logit contributions
ucer-0.021
 Area-0.019
unny-0.019
 disc-0.018
 globe-0.018
Token bath
Token ID7837
Feature activation+1.30e+00

Pos logit contributions
ucer+0.030
unny+0.029
 Area+0.028
 globe+0.028
fish+0.027
Neg logit contributions
 finished-0.021
 finally-0.018
 longer-0.016
 finish-0.016
 gust-0.015
Token!
Token ID0
Feature activation-5.12e-01

Pos logit contributions
ucer+0.056
unny+0.053
fish+0.053
 Area+0.051
 globe+0.051
Neg logit contributions
 finished-0.030
 gust-0.025
 finally-0.025
 bra-0.022
 rum-0.022
Token.
Token ID13
Feature activation-2.66e-01

Pos logit contributions
ucer+0.073
unny+0.069
fish+0.069
 globe+0.068
 Area+0.067
Neg logit contributions
 finished-0.040
 finally-0.033
 gust-0.029
 longer-0.028
 finish-0.027
Token The
Token ID383
Feature activation-1.09e+00

Pos logit contributions
 finished+0.008
 finally+0.006
 longer+0.006
 gust+0.006
 bra+0.006
Neg logit contributions
ucer-0.010
unny-0.010
 Area-0.010
 globe-0.009
oris-0.009
Token family
Token ID1641
Feature activation+1.48e+00

Pos logit contributions
 finished+0.032
 finally+0.028
 longer+0.026
 anymore+0.025
 less+0.024
Neg logit contributions
ucer-0.040
unny-0.039
 Area-0.038
 globe-0.038
fish-0.037
Token felt
Token ID2936
Feature activation+2.93e-01

Pos logit contributions
ucer+0.060
fish+0.058
 globe+0.057
unny+0.056
 Area+0.054
Neg logit contributions
 finished-0.035
 gust-0.031
 longer-0.030
 anymore-0.029
 finally-0.029
Token so
Token ID523
Feature activation+3.68e-01

Pos logit contributions
ucer+0.009
fish+0.009
 Area+0.008
 globe+0.008
unny+0.008
Neg logit contributions
 finished-0.006
 anymore-0.006
 gust-0.006
 fifteen-0.006
whe-0.005
Token much
Token ID881
Feature activation-2.88e+00

Pos logit contributions
ucer+0.015
fish+0.015
unny+0.014
 globe+0.014
 Area+0.014
Neg logit contributions
 finished-0.007
 anymore-0.006
 longer-0.006
 finally-0.006
 gust-0.006
Token love
Token ID1842
Feature activation+7.67e-01

Pos logit contributions
 finished+0.052
 fifteen+0.046
 scr+0.046
 sweaty+0.046
 curly+0.045
Neg logit contributions
fish-0.101
ucer-0.093
 compass-0.089
 globe-0.089
 Area-0.087
Token and
Token ID290
Feature activation+5.00e-02

Pos logit contributions
ucer+0.031
 globe+0.030
fish+0.030
 Area+0.030
unny+0.029
Neg logit contributions
 finished-0.018
 finally-0.015
 gust-0.014
 longer-0.014
 finish-0.013
Token joy
Token ID8716
Feature activation+6.96e-01

Pos logit contributions
ucer+0.002
fish+0.002
 globe+0.002
unny+0.002
 Area+0.002
Neg logit contributions
 finished-0.001
 longer-0.001
 gust-0.001
 anymore-0.001
 finally-0.001
Token when
Token ID618
Feature activation+1.55e-01

Pos logit contributions
ucer+0.028
fish+0.026
 globe+0.025
unny+0.025
fly+0.025
Neg logit contributions
 finished-0.018
 gust-0.015
 finally-0.015
 sweaty-0.015
 longer-0.014
Token the
Token ID262
Feature activation-2.18e+00

Pos logit contributions
ucer+0.005
 Area+0.004
 globe+0.004
fish+0.004
 telescope+0.004
Neg logit contributions
 finished-0.005
 gust-0.004
 finally-0.004
 itch-0.004
 finish-0.004
Token at
Token ID379
Feature activation-6.95e-01

Pos logit contributions
 finished+0.014
 gust+0.012
 finally+0.011
 rum+0.011
 sweaty+0.010
Neg logit contributions
ucer-0.024
fish-0.023
 Area-0.023
unny-0.023
 globe-0.023
Token first
Token ID717
Feature activation-1.57e-01

Pos logit contributions
 finished+0.017
 bra+0.014
 tum+0.014
 gust+0.014
 rum+0.013
Neg logit contributions
 Area-0.024
 globe-0.023
ucer-0.023
fish-0.023
eway-0.022
Token,
Token ID11
Feature activation-1.87e-01

Pos logit contributions
 finished+0.004
 finally+0.003
 healthier+0.003
 finish+0.003
 bra+0.003
Neg logit contributions
 Area-0.006
fish-0.006
unny-0.006
ucer-0.006
eway-0.006
Token but
Token ID475
Feature activation-4.52e-01

Pos logit contributions
 finished+0.006
 finally+0.004
 finish+0.004
 rum+0.004
 gust+0.004
Neg logit contributions
unny-0.006
fish-0.006
ucer-0.006
 globe-0.005
 Area-0.005
Token if
Token ID611
Feature activation-3.28e-01

Pos logit contributions
 finished+0.011
 finally+0.008
 longer+0.007
 gust+0.007
 finish+0.007
Neg logit contributions
ucer-0.020
unny-0.019
 Area-0.019
fish-0.018
 globe-0.018
Token she
Token ID673
Feature activation-2.87e+00

Pos logit contributions
 finished+0.009
 finally+0.008
 finish+0.007
 gust+0.007
 longer+0.007
Neg logit contributions
ucer-0.012
unny-0.012
fish-0.012
 Area-0.011
 globe-0.011
Token kept
Token ID4030
Feature activation+6.61e-01

Pos logit contributions
 finished+0.070
 gust+0.063
 longer+0.061
 healthier+0.060
 less+0.059
Neg logit contributions
unny-0.108
fish-0.107
ucer-0.106
 Area-0.100
 globe-0.099
Token looking
Token ID2045
Feature activation+3.11e-01

Pos logit contributions
ucer+0.026
 Area+0.025
fish+0.024
 globe+0.024
utes+0.024
Neg logit contributions
 finished-0.016
 gust-0.012
 finally-0.012
 anymore-0.011
 rum-0.011
Token,
Token ID11
Feature activation-4.48e-01

Pos logit contributions
ucer+0.012
fish+0.012
 telescope+0.011
 Area+0.011
unny+0.011
Neg logit contributions
 finished-0.007
 finally-0.006
whe-0.006
 gust-0.005
 rum-0.005
Token she
Token ID673
Feature activation-1.30e+00

Pos logit contributions
 finished+0.013
 finally+0.010
 finish+0.009
 rum+0.009
 gust+0.009
Neg logit contributions
ucer-0.015
fish-0.015
unny-0.014
 Area-0.014
 appearances-0.014
Token would
Token ID561
Feature activation+2.06e-01

Pos logit contributions
 finished+0.041
 gust+0.035
 finally+0.034
 longer+0.033
 anymore+0.032
Neg logit contributions
ucer-0.043
fish-0.042
unny-0.042
 Area-0.039
 globe-0.038
Token as
Token ID355
Feature activation+1.77e+00

Pos logit contributions
 finished+0.009
 anymore+0.008
 longer+0.007
 finally+0.007
 gust+0.007
Neg logit contributions
ucer-0.014
fish-0.013
unny-0.013
 Area-0.013
 globe-0.013
Token he
Token ID339
Feature activation-1.17e+00

Pos logit contributions
ucer+0.072
fish+0.069
unny+0.068
 globe+0.067
 Area+0.064
Neg logit contributions
 finished-0.046
 finally-0.035
 anymore-0.034
 longer-0.034
 gust-0.033
Token did
Token ID750
Feature activation-1.06e+00

Pos logit contributions
 finished+0.030
 anymore+0.025
 finally+0.024
 longer+0.024
 less+0.024
Neg logit contributions
ucer-0.046
unny-0.045
fish-0.044
 Area-0.043
 globe-0.041
Token he
Token ID339
Feature activation-7.41e-01

Pos logit contributions
 finished+0.023
 gust+0.017
 finally+0.017
 longer+0.016
 finish+0.015
Neg logit contributions
ucer-0.046
fish-0.045
unny-0.044
 Area-0.044
 globe-0.044
Token suddenly
Token ID6451
Feature activation+1.79e-01

Pos logit contributions
 finished+0.018
 healthier+0.018
 gust+0.018
 less+0.017
 anymore+0.017
Neg logit contributions
fish-0.027
unny-0.026
ucer-0.026
 Area-0.024
fly-0.024
Token sne
Token ID10505
Feature activation-3.40e+00

Pos logit contributions
ucer+0.007
fish+0.007
unny+0.006
 Area+0.006
 telescope+0.006
Neg logit contributions
 finished-0.004
 longer-0.004
 healthier-0.004
 finally-0.004
 less-0.003
Tokenez
Token ID8471
Feature activation+5.85e-01

Pos logit contributions
 finished+0.123
 finally+0.109
 longer+0.104
 finish+0.099
 gust+0.099
Neg logit contributions
ucer-0.106
unny-0.103
 Area-0.095
fish-0.093
 globe-0.089
Tokened
Token ID276
Feature activation-1.33e+00

Pos logit contributions
ucer+0.017
unny+0.016
fish+0.015
 Area+0.014
ark+0.014
Neg logit contributions
 finished-0.023
 finally-0.021
 longer-0.020
 healthier-0.019
 less-0.019
Token.
Token ID13
Feature activation-3.85e-01

Pos logit contributions
 finished+0.034
 finally+0.026
 gust+0.025
 sweaty+0.024
 finish+0.024
Neg logit contributions
ucer-0.048
unny-0.046
 globe-0.046
fly-0.045
fish-0.045
Token
Token ID220
Feature activation+4.97e-01

Pos logit contributions
 finished+0.010
 longer+0.008
 finally+0.008
 anymore+0.007
 less+0.007
Neg logit contributions
unny-0.015
ucer-0.015
 Area-0.015
 globe-0.014
fish-0.014
Token
Token ID198
Feature activation-4.29e-02

Pos logit contributions
ucer+0.021
unny+0.020
 Area+0.020
fish+0.020
 globe+0.020
Neg logit contributions
 finished-0.012
 finally-0.010
 longer-0.009
 less-0.009
 finish-0.009