TOP ACTIVATIONS
MAX = 5.852

and wondered how the all igator could talk . She stopped
Thank you , quiet all igator ! Let me give you
lake to see the all igators . One day , Tim
No way ! That all igator is too deep in the
we take the cute all igator home with us ?"
Everyday he would take the av oc ados and scatter them
I am the quiet all igator . Why are you sad
the ground so the all igator can 't see us ."
wanted to help the all igator , so he asked his
girl thought maybe the all igator was too stubborn to talk
wanted to see the all igators so badly . They looked
and saw a huge all igator . It had big teeth
find it ?" The all igator said , " Yes ,
and try to grab the av oc ados . But the
Please help me shake this rad ish , it 's too
I saw a big all igator there !" Tim
mom said , " All igators are not nice . They
help her mom put or nam ents on the tree .
got to hold an all igator toy . But M omm
and saw a cute all igator . L

MIN ACTIVATIONS
MIN = -5.049

start with the roller co aster ? â his dad
puts bread in the to aster and waits for it to
down on the roller co aster , Lily shouted , "
. She grabbed the to aster and threw it in the
toast out of the to aster and put it on a
some bread in the to aster . He goes to his
the bread in the to aster and pushed the button .
just stuck with the to aster in their modern home .
more bread in the to aster and turned it on .
saw a different roller co aster - like ride .
looking at a burnt to aster . They smelled something bad
white bread into the to aster . She saw the glowing
of bread in the to aster and pushed the lever down
She turned off the to aster and opened the window to
put it in the to aster . Then , she went
flames coming from the to aster . Their mom is trying
put it in the to aster and waited . When it
saw a big roller co aster and asked her mom if
on a scary roller co aster ride . Tim my was
the bread in the to aster and pushed the button down

INTERVAL 3.127 - 5.852
CONTAINS 0.042%

never played with the or nam ents again . They still
They played with their other magnets . They played with them
The all igator ended his journey at the
and ate their sandwiches and carrots . They were very hungry
try the broccoli c asser ole . He said , "

INTERVAL 0.401 - 3.127
CONTAINS 26.631%

." Tom and Lily were shocked and scared .
drum ming with his friends . And they all lived happily
playing with a ball . Tim laughed and said , "
in front of him . She smiled and said " Welcome
ball very high and far with her foot . Her friends

INTERVAL -2.324 - 0.401
CONTAINS 73.031%

eating it together . <|endoftext|> Once upon a time , there
time , there was a pengu in who lived in a
gray . They want to see what is in the pond
One day , Tim 's mom made some pasta for dinner
out . She said they were impressive twins . She cl

INTERVAL -5.049 - -2.324
CONTAINS 0.295%

the ugly things she had glimps ed . With that ,
things look different for a while ." Ben and
Sometimes , Sam goes with Jen to the lab , and
, a little vehicle named V icky was driving down a
dream was not just a dream . It was a goal
Token and
Token ID290
Feature activation-8.30e-01

Pos logit contributions
zed+0.012
ar+0.011
z+0.011
rd+0.011
da+0.011
Neg logit contributions
iring-0.008
efully-0.007
nam-0.007
 rad-0.006
ble-0.006
Token wondered
Token ID14028
Feature activation-3.32e-01

Pos logit contributions
ar+0.026
zed+0.026
t+0.025
 dreaming+0.025
 minutes+0.024
Neg logit contributions
nam-0.021
iring-0.020
ble-0.019
efully-0.019
ishes-0.019
Token how
Token ID703
Feature activation+1.11e+00

Pos logit contributions
ar+0.009
zed+0.009
t+0.009
rd+0.009
 dreaming+0.009
Neg logit contributions
nam-0.009
iring-0.009
efully-0.009
ble-0.009
ishes-0.008
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
nam+0.030
iring+0.027
efully+0.026
 rad+0.026
 av+0.025
Neg logit contributions
ar-0.034
ake-0.033
rd-0.032
stand-0.032
zed-0.032
Token all
Token ID477
Feature activation+1.69e+00

Pos logit contributions
nam+0.040
ishes+0.037
ble+0.035
bles+0.035
ins+0.034
Neg logit contributions
t-0.044
 moment-0.044
 ever-0.043
 minute-0.042
rd-0.041
Tokenigator
Token ID23823
Feature activation+5.23e+00

Pos logit contributions
ble+0.026
nam+0.026
bles+0.024
iring+0.023
uted+0.022
Neg logit contributions
t-0.069
 ever-0.069
zed-0.067
 moment-0.066
ar-0.065
Token could
Token ID714
Feature activation+9.60e-01

Pos logit contributions
nam+0.162
iring+0.150
ble+0.147
efully+0.145
uted+0.143
Neg logit contributions
ar-0.139
zed-0.133
t-0.132
 ever-0.129
rd-0.126
Token talk
Token ID1561
Feature activation+3.24e-01

Pos logit contributions
nam+0.032
iring+0.030
ble+0.029
efully+0.029
uted+0.029
Neg logit contributions
ar-0.023
zed-0.022
t-0.022
ake-0.021
rd-0.021
Token.
Token ID13
Feature activation-5.24e-02

Pos logit contributions
nam+0.009
iring+0.008
uted+0.008
efully+0.008
ble+0.008
Neg logit contributions
ar-0.009
zed-0.009
ake-0.009
rd-0.009
 minutes-0.009
Token She
Token ID1375
Feature activation+4.36e-01

Pos logit contributions
ar+0.002
zed+0.002
t+0.002
rd+0.002
ake+0.002
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
uted-0.001
Token stopped
Token ID5025
Feature activation-5.45e-01

Pos logit contributions
nam+0.011
iring+0.011
ble+0.010
efully+0.010
uted+0.010
Neg logit contributions
ar-0.013
zed-0.013
t-0.013
 minutes-0.012
rd-0.012
TokenThank
Token ID10449
Feature activation+3.49e-01

Pos logit contributions
zed+0.004
ar+0.004
rd+0.004
t+0.004
 minutes+0.004
Neg logit contributions
nam-0.003
efully-0.003
iring-0.003
uted-0.003
ble-0.003
Token you
Token ID345
Feature activation+1.05e+00

Pos logit contributions
nam+0.008
efully+0.008
iring+0.008
ble+0.008
 av+0.007
Neg logit contributions
zed-0.011
 dreaming-0.011
t-0.011
 minutes-0.011
ar-0.011
Token,
Token ID11
Feature activation+1.20e+00

Pos logit contributions
nam+0.029
iring+0.028
efully+0.028
ble+0.027
bles+0.026
Neg logit contributions
zed-0.030
ar-0.028
seek-0.028
t-0.027
rd-0.027
Token quiet
Token ID5897
Feature activation-1.71e-01

Pos logit contributions
nam+0.034
ishes+0.033
efully+0.033
ins+0.033
ble+0.033
Neg logit contributions
 ever-0.033
t-0.030
ar-0.030
 minute-0.029
 dreaming-0.028
Token all
Token ID477
Feature activation+1.83e+00

Pos logit contributions
ar+0.006
zed+0.005
t+0.005
rd+0.005
ake+0.005
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.004
uted-0.004
Tokenigator
Token ID23823
Feature activation+5.21e+00

Pos logit contributions
nam+0.042
iring+0.039
ble+0.038
efully+0.038
uted+0.036
Neg logit contributions
ar-0.062
t-0.060
zed-0.060
rd-0.060
 ever-0.060
Token!
Token ID0
Feature activation-2.82e-01

Pos logit contributions
iring+0.142
nam+0.141
ble+0.141
efully+0.139
 ot+0.137
Neg logit contributions
zed-0.140
t-0.132
ar-0.131
 minutes-0.131
rd-0.130
Token Let
Token ID3914
Feature activation-2.44e-01

Pos logit contributions
ar+0.007
zed+0.007
t+0.007
 minutes+0.007
rd+0.007
Neg logit contributions
nam-0.009
iring-0.008
efully-0.008
ble-0.008
uted-0.008
Token me
Token ID502
Feature activation+3.09e+00

Pos logit contributions
ar+0.006
zed+0.005
t+0.005
ake+0.005
rd+0.005
Neg logit contributions
nam-0.009
iring-0.008
ble-0.008
efully-0.008
uted-0.008
Token give
Token ID1577
Feature activation+1.30e+00

Pos logit contributions
nam+0.106
iring+0.101
ble+0.100
efully+0.099
uted+0.096
Neg logit contributions
ar-0.068
zed-0.066
t-0.065
rd-0.063
ake-0.063
Token you
Token ID345
Feature activation+9.96e-01

Pos logit contributions
nam+0.041
iring+0.038
ble+0.038
efully+0.037
uted+0.036
Neg logit contributions
ar-0.033
zed-0.032
t-0.032
rd-0.031
ake-0.031
Token lake
Token ID13546
Feature activation+1.32e+00

Pos logit contributions
nam+0.029
iring+0.027
ble+0.026
efully+0.026
ishes+0.025
Neg logit contributions
ar-0.032
zed-0.031
t-0.030
ake-0.030
rd-0.030
Token to
Token ID284
Feature activation+5.27e-02

Pos logit contributions
iring+0.034
nam+0.034
ble+0.033
 rad+0.030
 ot+0.030
Neg logit contributions
ar-0.040
zed-0.040
 minutes-0.039
da-0.039
 payoff-0.038
Token see
Token ID766
Feature activation+1.19e-01

Pos logit contributions
nam+0.002
iring+0.002
efully+0.002
ble+0.002
uted+0.002
Neg logit contributions
ar-0.001
zed-0.001
t-0.001
ake-0.001
rd-0.001
Token the
Token ID262
Feature activation+1.21e+00

Pos logit contributions
ailed+0.005
nam+0.005
efully+0.005
asure+0.005
outed+0.005
Neg logit contributions
 dreaming-0.001
 one-0.001
 this-0.001
 Halloween-0.001
 ever-0.001
Token all
Token ID477
Feature activation+1.93e+00

Pos logit contributions
nam+0.040
efully+0.035
ishes+0.034
 gladly+0.034
asure+0.033
Neg logit contributions
 moment-0.028
 ever-0.028
t-0.028
 dreaming-0.027
ake-0.027
Tokenigators
Token ID25975
Feature activation+5.17e+00

Pos logit contributions
nam+0.061
ble+0.059
efully+0.059
uted+0.058
iring+0.057
Neg logit contributions
 ever-0.045
t-0.045
 moment-0.043
 dreaming-0.043
zed-0.042
Token.
Token ID13
Feature activation+5.19e-01

Pos logit contributions
nam+0.189
efully+0.178
iring+0.174
uted+0.174
ishes+0.170
Neg logit contributions
 ever-0.102
ar-0.099
t-0.097
 dreaming-0.096
ake-0.093
Token One
Token ID1881
Feature activation-2.53e-01

Pos logit contributions
nam+0.019
ble+0.018
efully+0.018
iring+0.018
uted+0.018
Neg logit contributions
t-0.011
ar-0.010
 dreaming-0.010
zed-0.010
 moment-0.010
Token day
Token ID1110
Feature activation-4.54e-01

Pos logit contributions
ar+0.006
zed+0.005
t+0.005
rd+0.005
 dreaming+0.005
Neg logit contributions
nam-0.008
iring-0.008
ble-0.008
efully-0.008
 ot-0.008
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
ar+0.011
zed+0.010
t+0.010
rd+0.010
ake+0.010
Neg logit contributions
nam-0.015
iring-0.014
ble-0.014
efully-0.014
uted-0.014
Token Tim
Token ID5045
Feature activation+5.24e-01

Pos logit contributions
efully+0.006
nam+0.006
iring+0.006
uted+0.006
ishes+0.006
Neg logit contributions
t-0.005
ar-0.005
zed-0.005
 dreaming-0.005
 ever-0.004
TokenNo
Token ID2949
Feature activation-1.19e-01

Pos logit contributions
ar+0.005
zed+0.005
t+0.005
rd+0.005
ake+0.005
Neg logit contributions
nam-0.005
iring-0.005
ble-0.005
efully-0.005
uted-0.005
Token way
Token ID835
Feature activation+1.72e+00

Pos logit contributions
zed+0.004
ar+0.004
t+0.003
seek+0.003
z+0.003
Neg logit contributions
 ot-0.003
nam-0.003
 rad-0.003
iring-0.003
ble-0.003
Token!
Token ID0
Feature activation-6.58e-01

Pos logit contributions
nam+0.051
iring+0.050
ble+0.049
efully+0.047
 ot+0.047
Neg logit contributions
zed-0.045
ar-0.045
rd-0.042
 minutes-0.042
ake-0.041
Token That
Token ID1320
Feature activation+8.26e-01

Pos logit contributions
ar+0.015
zed+0.015
t+0.015
rd+0.014
ake+0.014
Neg logit contributions
nam-0.022
iring-0.021
ble-0.020
efully-0.020
uted-0.020
Token all
Token ID477
Feature activation+1.93e+00

Pos logit contributions
nam+0.026
iring+0.025
ble+0.024
bles+0.024
efully+0.024
Neg logit contributions
t-0.021
 ever-0.020
ar-0.019
zed-0.019
rd-0.019
Tokenigator
Token ID23823
Feature activation+5.16e+00

Pos logit contributions
nam+0.042
iring+0.038
ble+0.038
efully+0.038
uted+0.036
Neg logit contributions
t-0.066
ar-0.066
zed-0.065
 ever-0.065
rd-0.064
Token is
Token ID318
Feature activation+5.63e-01

Pos logit contributions
nam+0.149
iring+0.144
ble+0.142
efully+0.140
ishes+0.138
Neg logit contributions
ar-0.134
zed-0.134
t-0.131
rd-0.130
ake-0.129
Token too
Token ID1165
Feature activation-1.44e-01

Pos logit contributions
nam+0.015
iring+0.014
ble+0.014
efully+0.014
uted+0.014
Neg logit contributions
ar-0.017
zed-0.016
rd-0.016
t-0.016
ake-0.016
Token deep
Token ID2769
Feature activation+1.35e+00

Pos logit contributions
ar+0.004
zed+0.004
t+0.004
ake+0.004
rd+0.004
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.004
uted-0.004
Token in
Token ID287
Feature activation+6.49e-01

Pos logit contributions
iring+0.030
ble+0.028
uted+0.028
ishes+0.027
efully+0.027
Neg logit contributions
zed-0.046
ar-0.046
rd-0.044
t-0.043
gh-0.042
Token the
Token ID262
Feature activation+2.54e-01

Pos logit contributions
nam+0.014
 rad+0.013
ble+0.013
 ot+0.013
iring+0.013
Neg logit contributions
ar-0.024
zed-0.024
t-0.023
seek-0.023
rd-0.023
Token we
Token ID356
Feature activation-3.20e-01

Pos logit contributions
nam+0.012
ble+0.010
 rad+0.010
iring+0.010
 ot+0.010
Neg logit contributions
 minutes-0.009
ake-0.009
ar-0.009
rd-0.009
zed-0.009
Token take
Token ID1011
Feature activation-4.56e-01

Pos logit contributions
ar+0.008
t+0.007
 ever+0.007
ake+0.007
zed+0.007
Neg logit contributions
nam-0.011
iring-0.010
ble-0.010
efully-0.010
uted-0.010
Token the
Token ID262
Feature activation+2.22e-01

Pos logit contributions
zed+0.013
t+0.013
ar+0.013
rd+0.013
 dreaming+0.012
Neg logit contributions
nam-0.012
efully-0.012
 rad-0.011
ishes-0.011
 ot-0.011
Token cute
Token ID13779
Feature activation+1.41e+00

Pos logit contributions
nam+0.006
ble+0.005
efully+0.005
iring+0.005
ins+0.005
Neg logit contributions
t-0.007
 ever-0.007
 moment-0.006
 minute-0.006
ar-0.006
Token all
Token ID477
Feature activation+1.40e+00

Pos logit contributions
nam+0.039
ble+0.033
iring+0.033
efully+0.033
uted+0.031
Neg logit contributions
ar-0.043
t-0.041
 ever-0.041
ake-0.040
rd-0.039
Tokenigator
Token ID23823
Feature activation+5.07e+00

Pos logit contributions
nam+0.041
iring+0.039
ble+0.038
efully+0.037
uted+0.036
Neg logit contributions
ar-0.039
zed-0.038
t-0.037
rd-0.036
ake-0.036
Token home
Token ID1363
Feature activation+2.16e-01

Pos logit contributions
nam+0.125
iring+0.116
ble+0.113
efully+0.112
uted+0.108
Neg logit contributions
ar-0.163
zed-0.158
t-0.157
ake-0.154
rd-0.154
Token with
Token ID351
Feature activation+6.02e-01

Pos logit contributions
iring+0.003
nam+0.003
ble+0.003
efully+0.003
ishes+0.002
Neg logit contributions
zed-0.009
ar-0.009
 minutes-0.009
t-0.009
rd-0.009
Token us
Token ID514
Feature activation-2.83e-01

Pos logit contributions
nam+0.015
iring+0.014
ble+0.014
efully+0.014
ishes+0.013
Neg logit contributions
ar-0.019
zed-0.019
t-0.019
rd-0.018
 minutes-0.018
Token?"
Token ID1701
Feature activation-6.16e-02

Pos logit contributions
ar+0.011
t+0.010
ake+0.010
zed+0.010
 ever+0.010
Neg logit contributions
nam-0.006
iring-0.005
efully-0.005
ble-0.005
uted-0.005
Token
Token ID198
Feature activation-2.71e-01

Pos logit contributions
ar+0.002
zed+0.002
t+0.002
ake+0.002
rd+0.002
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
uted-0.001
Token Everyday
Token ID48154
Feature activation+6.36e-01

Pos logit contributions
 ever+0.023
ar+0.023
zed+0.023
t+0.023
 dreaming+0.022
Neg logit contributions
nam-0.024
iring-0.024
ble-0.023
efully-0.022
ishes-0.021
Token he
Token ID339
Feature activation-6.52e-01

Pos logit contributions
nam+0.018
iring+0.016
 rad+0.016
efully+0.016
 ot+0.016
Neg logit contributions
ar-0.017
zed-0.017
t-0.017
ake-0.016
rd-0.016
Token would
Token ID561
Feature activation-1.12e+00

Pos logit contributions
ar+0.018
zed+0.017
t+0.017
rd+0.017
ake+0.017
Neg logit contributions
nam-0.019
iring-0.018
ble-0.017
efully-0.017
uted-0.017
Token take
Token ID1011
Feature activation-6.76e-01

Pos logit contributions
ar+0.032
t+0.030
ake+0.030
rd+0.030
 minutes+0.030
Neg logit contributions
nam-0.031
ble-0.029
efully-0.028
iring-0.027
 rad-0.027
Token the
Token ID262
Feature activation-3.77e-02

Pos logit contributions
t+0.024
storm+0.022
rd+0.022
ar+0.022
ake+0.022
Neg logit contributions
nam-0.014
efully-0.013
 rad-0.013
 av-0.013
ishes-0.012
Token av
Token ID1196
Feature activation+5.00e+00

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
ake+0.001
rd+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Tokenoc
Token ID420
Feature activation-1.56e+00

Pos logit contributions
nam+0.200
ble+0.193
iring+0.192
uted+0.187
 ot+0.179
Neg logit contributions
ar-0.090
ake-0.088
t-0.081
z-0.079
rd-0.075
Tokenados
Token ID22484
Feature activation+3.53e+00

Pos logit contributions
ar+0.058
ake+0.057
t+0.054
rd+0.054
zed+0.054
Neg logit contributions
nam-0.031
ble-0.026
iring-0.026
efully-0.025
uted-0.024
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
nam+0.133
iring+0.128
efully+0.126
ble+0.125
uted+0.124
Neg logit contributions
ar-0.065
t-0.065
 ever-0.060
zed-0.059
ake-0.059
Token scatter
Token ID41058
Feature activation+8.40e-01

Pos logit contributions
nam+0.027
iring+0.026
ble+0.026
efully+0.025
uted+0.025
Neg logit contributions
ar-0.029
zed-0.028
t-0.028
 ever-0.027
 minutes-0.027
Token them
Token ID606
Feature activation+3.39e-01

Pos logit contributions
nam+0.025
iring+0.024
ble+0.023
efully+0.023
uted+0.022
Neg logit contributions
ar-0.023
t-0.022
zed-0.021
ake-0.021
 minutes-0.021
Token I
Token ID314
Feature activation+3.98e-02

Pos logit contributions
nam+0.023
iring+0.022
efully+0.022
ble+0.021
uted+0.021
Neg logit contributions
ar-0.018
t-0.017
 ever-0.017
zed-0.017
rd-0.017
Token am
Token ID716
Feature activation-7.69e-02

Pos logit contributions
ble+0.001
 ot+0.001
efully+0.001
nam+0.001
bles+0.001
Neg logit contributions
zed-0.001
ar-0.001
 minutes-0.001
side-0.001
seek-0.001
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
ar+0.002
zed+0.002
t+0.002
ake+0.002
rd+0.002
Neg logit contributions
nam-0.003
iring-0.002
ble-0.002
efully-0.002
uted-0.002
Token quiet
Token ID5897
Feature activation-1.04e+00

Pos logit contributions
nam+0.003
iring+0.003
efully+0.002
ble+0.002
uted+0.002
Neg logit contributions
ar-0.003
t-0.003
zed-0.003
rd-0.003
ake-0.003
Token all
Token ID477
Feature activation+1.13e+00

Pos logit contributions
zed+0.035
ar+0.034
t+0.033
ake+0.033
seek+0.032
Neg logit contributions
nam-0.022
iring-0.022
 ot-0.022
ble-0.022
 rad-0.022
Tokenigator
Token ID23823
Feature activation+4.98e+00

Pos logit contributions
nam+0.007
iring+0.005
efully+0.004
ble+0.004
 ot+0.004
Neg logit contributions
ar-0.057
zed-0.056
ake-0.055
t-0.054
rd-0.054
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
nam+0.123
iring+0.115
ble+0.112
efully+0.111
uted+0.107
Neg logit contributions
ar-0.159
zed-0.155
t-0.154
rd-0.150
ake-0.150
Token Why
Token ID4162
Feature activation+5.44e-01

Pos logit contributions
zed+0.008
ar+0.008
ake+0.008
gh+0.008
t+0.008
Neg logit contributions
nam-0.008
iring-0.008
efully-0.007
 ot-0.007
ble-0.007
Token are
Token ID389
Feature activation+8.25e-01

Pos logit contributions
nam+0.013
iring+0.012
efully+0.011
ble+0.011
uted+0.011
Neg logit contributions
ar-0.018
zed-0.018
t-0.018
rd-0.017
 ever-0.017
Token you
Token ID345
Feature activation+7.11e-01

Pos logit contributions
nam+0.027
iring+0.027
ble+0.027
efully+0.026
uted+0.026
Neg logit contributions
ar-0.018
t-0.018
zed-0.017
 ever-0.017
rd-0.017
Token sad
Token ID6507
Feature activation+1.27e+00

Pos logit contributions
nam+0.020
iring+0.019
ble+0.019
efully+0.018
uted+0.018
Neg logit contributions
ar-0.020
zed-0.020
t-0.019
rd-0.019
 minutes-0.019
Token the
Token ID262
Feature activation+3.93e-01

Pos logit contributions
ar+0.011
t+0.011
zed+0.011
rd+0.011
ake+0.010
Neg logit contributions
nam-0.010
iring-0.009
ble-0.009
efully-0.009
uted-0.009
Token ground
Token ID2323
Feature activation+8.29e-01

Pos logit contributions
nam+0.010
iring+0.010
ins+0.010
ishes+0.009
efully+0.009
Neg logit contributions
 ever-0.011
zed-0.011
t-0.011
 minutes-0.011
ar-0.011
Token so
Token ID523
Feature activation+1.66e+00

Pos logit contributions
iring+0.019
nam+0.019
ble+0.019
bles+0.018
uted+0.018
Neg logit contributions
zed-0.028
ar-0.026
rd-0.025
ake-0.025
gh-0.024
Token the
Token ID262
Feature activation+9.05e-01

Pos logit contributions
nam+0.056
iring+0.053
ble+0.052
efully+0.048
uted+0.047
Neg logit contributions
rd-0.039
ar-0.039
zed-0.039
ake-0.039
 dreaming-0.037
Token all
Token ID477
Feature activation+1.63e+00

Pos logit contributions
nam+0.022
ishes+0.021
iring+0.021
efully+0.021
ble+0.020
Neg logit contributions
t-0.028
 ever-0.027
 moment-0.026
 minutes-0.026
 minute-0.026
Tokenigator
Token ID23823
Feature activation+4.97e+00

Pos logit contributions
nam+0.025
iring+0.023
ble+0.022
efully+0.022
uted+0.020
Neg logit contributions
 ever-0.066
t-0.066
ar-0.065
zed-0.065
 minutes-0.064
Token can
Token ID460
Feature activation+1.22e-01

Pos logit contributions
nam+0.159
iring+0.148
efully+0.143
ble+0.143
uted+0.140
Neg logit contributions
ar-0.128
t-0.124
zed-0.122
 ever-0.119
ake-0.117
Token't
Token ID470
Feature activation+8.04e-01

Pos logit contributions
nam+0.004
iring+0.004
ble+0.003
efully+0.003
uted+0.003
Neg logit contributions
ar-0.003
zed-0.003
t-0.003
rd-0.003
ake-0.003
Token see
Token ID766
Feature activation-4.77e-01

Pos logit contributions
nam+0.028
ishes+0.026
efully+0.026
iring+0.026
uted+0.025
Neg logit contributions
 ever-0.020
t-0.020
ar-0.018
zed-0.018
ake-0.017
Token us
Token ID514
Feature activation+2.69e-01

Pos logit contributions
ar+0.012
zed+0.012
t+0.012
rd+0.012
ake+0.012
Neg logit contributions
nam-0.015
iring-0.014
ble-0.014
efully-0.014
uted-0.013
Token."
Token ID526
Feature activation+3.00e-01

Pos logit contributions
nam+0.008
iring+0.007
efully+0.007
ble+0.007
uted+0.007
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
ake-0.007
rd-0.007
Token wanted
Token ID2227
Feature activation+9.90e-01

Pos logit contributions
nam+0.024
iring+0.024
ying+0.023
ble+0.023
ishes+0.022
Neg logit contributions
zed-0.014
ar-0.013
t-0.013
 ever-0.013
 minutes-0.011
Token to
Token ID284
Feature activation+3.97e-01

Pos logit contributions
 rad+0.032
nam+0.031
 ot+0.030
 av+0.029
iring+0.029
Neg logit contributions
rd-0.025
ar-0.024
zed-0.024
z-0.023
ake-0.023
Token help
Token ID1037
Feature activation+8.76e-01

Pos logit contributions
nam+0.016
iring+0.015
ins+0.015
ishes+0.015
efully+0.015
Neg logit contributions
 ever-0.007
ar-0.007
t-0.007
zed-0.007
 arrest-0.006
Token the
Token ID262
Feature activation+2.00e+00

Pos logit contributions
nam+0.030
efully+0.029
iring+0.028
ishes+0.027
uted+0.027
Neg logit contributions
ar-0.020
t-0.020
 ever-0.020
zed-0.019
ake-0.019
Token all
Token ID477
Feature activation+2.06e+00

Pos logit contributions
nam+0.061
ishes+0.052
asure+0.051
 ey+0.050
ble+0.048
Neg logit contributions
t-0.056
 ever-0.055
 moment-0.053
 minute-0.051
storm-0.049
Tokenigator
Token ID23823
Feature activation+4.90e+00

Pos logit contributions
nam+0.045
uted+0.038
ble+0.038
iring+0.038
efully+0.037
Neg logit contributions
t-0.076
 ever-0.075
 minute-0.073
 moment-0.072
ar-0.072
Token,
Token ID11
Feature activation+5.18e-01

Pos logit contributions
nam+0.184
efully+0.172
uted+0.168
iring+0.168
ins+0.166
Neg logit contributions
t-0.096
 ever-0.096
ar-0.093
 dreaming-0.091
ake-0.089
Token so
Token ID523
Feature activation+2.08e+00

Pos logit contributions
nam+0.017
iring+0.017
efully+0.017
ble+0.017
uted+0.016
Neg logit contributions
t-0.012
ar-0.011
 minutes-0.011
 dreaming-0.011
zed-0.011
Token he
Token ID339
Feature activation+1.65e+00

Pos logit contributions
nam+0.070
iring+0.067
efully+0.066
ble+0.066
uted+0.064
Neg logit contributions
ar-0.047
zed-0.046
t-0.045
rd-0.044
ake-0.044
Token asked
Token ID1965
Feature activation+1.74e-01

Pos logit contributions
nam+0.057
iring+0.055
uted+0.052
ble+0.050
ying+0.049
Neg logit contributions
ar-0.042
t-0.039
 ever-0.038
zed-0.038
 minutes-0.037
Token his
Token ID465
Feature activation+5.84e-01

Pos logit contributions
nam+0.005
iring+0.005
efully+0.005
ble+0.005
uted+0.004
Neg logit contributions
ar-0.005
zed-0.005
t-0.005
 ever-0.005
ake-0.005
Token girl
Token ID2576
Feature activation+5.13e-01

Pos logit contributions
ble+0.049
nam+0.048
iring+0.047
uted+0.047
bles+0.044
Neg logit contributions
 moment-0.051
ar-0.049
 minute-0.049
 ever-0.048
 minutes-0.048
Token thought
Token ID1807
Feature activation+5.74e-01

Pos logit contributions
nam+0.013
iring+0.012
efully+0.012
ble+0.012
uted+0.012
Neg logit contributions
ar-0.015
zed-0.015
t-0.015
ake-0.015
rd-0.015
Token maybe
Token ID3863
Feature activation-1.27e+00

Pos logit contributions
nam+0.014
 rad+0.014
 av+0.014
iring+0.014
ble+0.014
Neg logit contributions
ar-0.017
rd-0.017
ake-0.017
seek-0.017
z-0.017
Token the
Token ID262
Feature activation+3.68e-01

Pos logit contributions
ake+0.041
ar+0.040
rd+0.039
t+0.039
z+0.039
Neg logit contributions
nam-0.035
 av-0.031
 rad-0.031
 ot-0.029
iring-0.028
Token all
Token ID477
Feature activation+1.59e+00

Pos logit contributions
nam+0.011
ishes+0.010
ins+0.009
iring+0.009
asure+0.009
Neg logit contributions
 moment-0.011
 minute-0.010
t-0.010
 ever-0.010
 payoff-0.009
Tokenigator
Token ID23823
Feature activation+4.81e+00

Pos logit contributions
nam+0.024
ble+0.023
iring+0.022
bles+0.021
efully+0.019
Neg logit contributions
 ever-0.067
zed-0.066
t-0.066
ar-0.065
rd-0.064
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
nam+0.138
iring+0.129
ble+0.126
efully+0.124
uted+0.121
Neg logit contributions
ar-0.136
zed-0.132
t-0.131
rd-0.126
ake-0.126
Token too
Token ID1165
Feature activation-6.29e-01

Pos logit contributions
nam+0.030
iring+0.029
ble+0.028
efully+0.028
uted+0.027
Neg logit contributions
ar-0.032
zed-0.031
t-0.031
ake-0.030
rd-0.030
Token stubborn
Token ID24444
Feature activation+5.16e-01

Pos logit contributions
ar+0.019
zed+0.019
t+0.019
rd+0.018
ake+0.018
Neg logit contributions
nam-0.016
iring-0.015
ble-0.015
efully-0.015
uted-0.014
Token to
Token ID284
Feature activation-2.58e-01

Pos logit contributions
iring+0.011
ying+0.011
uted+0.010
ishes+0.010
ins+0.010
Neg logit contributions
zed-0.018
ar-0.017
rd-0.017
da-0.016
z-0.016
Token talk
Token ID1561
Feature activation+7.65e-02

Pos logit contributions
ar+0.007
zed+0.007
t+0.007
rd+0.007
 minutes+0.007
Neg logit contributions
nam-0.007
ble-0.007
iring-0.007
efully-0.007
uted-0.007
Token wanted
Token ID2227
Feature activation+5.47e-01

Pos logit contributions
ar+0.010
zed+0.010
t+0.009
 ever+0.009
 minutes+0.009
Neg logit contributions
nam-0.010
iring-0.010
ble-0.010
efully-0.009
uted-0.009
Token to
Token ID284
Feature activation-2.06e-01

Pos logit contributions
 rad+0.017
nam+0.017
iring+0.016
 ducks+0.016
 ot+0.016
Neg logit contributions
ar-0.014
zed-0.014
rd-0.014
z-0.014
ake-0.013
Token see
Token ID766
Feature activation-1.89e-01

Pos logit contributions
ar+0.005
zed+0.004
 ever+0.004
t+0.004
rd+0.004
Neg logit contributions
nam-0.007
iring-0.007
ishes-0.007
efully-0.007
uted-0.007
Token the
Token ID262
Feature activation+2.32e-01

Pos logit contributions
ar+0.004
 ever+0.004
 minutes+0.004
zed+0.004
 dreaming+0.004
Neg logit contributions
nam-0.006
iring-0.006
ble-0.006
efully-0.006
uted-0.005
Token all
Token ID477
Feature activation+1.27e+00

Pos logit contributions
nam+0.006
ble+0.005
efully+0.005
asure+0.005
uted+0.005
Neg logit contributions
ar-0.007
t-0.007
 ever-0.007
 moment-0.007
 minutes-0.007
Tokenigators
Token ID25975
Feature activation+4.81e+00

Pos logit contributions
nam+0.015
ble+0.012
iring+0.012
efully+0.011
uted+0.010
Neg logit contributions
ar-0.057
t-0.056
 ever-0.056
zed-0.056
 minutes-0.055
Token so
Token ID523
Feature activation+1.93e+00

Pos logit contributions
nam+0.147
iring+0.141
ble+0.139
efully+0.136
uted+0.132
Neg logit contributions
ar-0.123
zed-0.122
t-0.119
rd-0.116
ake-0.116
Token badly
Token ID11234
Feature activation+1.92e+00

Pos logit contributions
nam+0.059
iring+0.058
ble+0.054
uted+0.052
efully+0.052
Neg logit contributions
ar-0.051
ake-0.050
 basis-0.049
rd-0.049
zed-0.049
Token.
Token ID13
Feature activation+1.09e-01

Pos logit contributions
iring+0.046
ble+0.045
uted+0.041
nam+0.041
 ot+0.041
Neg logit contributions
rd-0.063
zed-0.062
ake-0.060
z-0.058
 basis-0.058
Token They
Token ID1119
Feature activation-1.25e-01

Pos logit contributions
nam+0.003
iring+0.003
efully+0.002
ble+0.002
uted+0.002
Neg logit contributions
ar-0.003
zed-0.003
t-0.003
ake-0.003
rd-0.003
Token looked
Token ID3114
Feature activation+1.11e+00

Pos logit contributions
ar+0.003
zed+0.003
t+0.003
 ever+0.003
 minutes+0.003
Neg logit contributions
iring-0.004
nam-0.004
ble-0.004
uted-0.003
efully-0.003
Token and
Token ID290
Feature activation+1.16e-01

Pos logit contributions
seek+0.042
zed+0.041
rd+0.041
t+0.041
gh+0.040
Neg logit contributions
iring-0.016
 ot-0.016
 rad-0.016
efully-0.015
ble-0.014
Token saw
Token ID2497
Feature activation-2.97e-01

Pos logit contributions
nam+0.004
efully+0.003
iring+0.003
ble+0.003
uted+0.003
Neg logit contributions
ake-0.003
ar-0.003
rd-0.003
zed-0.003
t-0.003
Token a
Token ID257
Feature activation+6.95e-01

Pos logit contributions
ar+0.008
zed+0.008
t+0.008
ake+0.007
rd+0.007
Neg logit contributions
nam-0.009
iring-0.009
ble-0.008
efully-0.008
uted-0.008
Token huge
Token ID3236
Feature activation+9.93e-01

Pos logit contributions
nam+0.021
iring+0.020
efully+0.020
uted+0.019
ishes+0.019
Neg logit contributions
ar-0.019
t-0.018
zed-0.017
 minutes-0.017
ake-0.017
Token all
Token ID477
Feature activation+1.68e+00

Pos logit contributions
nam+0.026
iring+0.025
ble+0.024
efully+0.024
uted+0.023
Neg logit contributions
ar-0.029
zed-0.029
t-0.029
rd-0.028
ake-0.028
Tokenigator
Token ID23823
Feature activation+4.81e+00

Pos logit contributions
nam+0.024
efully+0.020
ishes+0.019
ble+0.019
iring+0.019
Neg logit contributions
t-0.071
 ever-0.071
 minutes-0.070
ar-0.070
rd-0.069
Token.
Token ID13
Feature activation-2.98e-02

Pos logit contributions
nam+0.145
iring+0.139
ble+0.137
efully+0.134
uted+0.131
Neg logit contributions
ar-0.125
zed-0.122
t-0.120
rd-0.118
ake-0.117
Token It
Token ID632
Feature activation-1.24e-01

Pos logit contributions
ar+0.001
t+0.001
zed+0.001
 minutes+0.001
rd+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Token had
Token ID550
Feature activation+7.29e-02

Pos logit contributions
ar+0.003
zed+0.003
ake+0.003
rd+0.003
t+0.003
Neg logit contributions
nam-0.004
iring-0.003
ble-0.003
efully-0.003
uted-0.003
Token big
Token ID1263
Feature activation-3.61e-01

Pos logit contributions
nam+0.002
efully+0.002
iring+0.002
 rad+0.002
ble+0.002
Neg logit contributions
ar-0.002
rd-0.002
ake-0.002
t-0.002
zed-0.002
Token teeth
Token ID9941
Feature activation-1.06e-01

Pos logit contributions
ar+0.012
t+0.012
zed+0.012
ake+0.012
rd+0.012
Neg logit contributions
nam-0.008
iring-0.008
ble-0.007
efully-0.007
uted-0.007
Token find
Token ID1064
Feature activation+1.20e+00

Pos logit contributions
nam+0.082
efully+0.076
iring+0.076
uted+0.073
ble+0.071
Neg logit contributions
ar-0.086
t-0.083
zed-0.082
ake-0.082
 dreaming-0.081
Token it
Token ID340
Feature activation-2.57e-01

Pos logit contributions
nam+0.035
iring+0.033
ble+0.032
efully+0.032
ishes+0.031
Neg logit contributions
ar-0.033
zed-0.032
t-0.032
rd-0.031
ake-0.031
Token?"
Token ID1701
Feature activation+1.17e-01

Pos logit contributions
ar+0.010
t+0.010
zed+0.010
ake+0.009
rd+0.009
Neg logit contributions
nam-0.005
iring-0.004
efully-0.004
ble-0.004
uted-0.004
Token The
Token ID383
Feature activation+6.46e-01

Pos logit contributions
nam+0.004
iring+0.004
ble+0.004
ishes+0.004
bles+0.004
Neg logit contributions
ar-0.003
t-0.003
 ever-0.002
zed-0.002
 dreaming-0.002
Token all
Token ID477
Feature activation+2.40e+00

Pos logit contributions
ishes+0.019
nam+0.019
ins+0.019
asure+0.018
ants+0.018
Neg logit contributions
 moment-0.015
 minute-0.015
 single-0.014
 next-0.013
 ever-0.013
Tokenigator
Token ID23823
Feature activation+4.79e+00

Pos logit contributions
ble+0.039
iring+0.039
nam+0.038
bles+0.035
ishes+0.034
Neg logit contributions
t-0.097
 ever-0.095
zed-0.094
ar-0.093
 moment-0.092
Token said
Token ID531
Feature activation+1.23e-01

Pos logit contributions
nam+0.121
iring+0.113
ble+0.109
efully+0.107
uted+0.104
Neg logit contributions
ar-0.153
zed-0.147
t-0.146
rd-0.142
ake-0.142
Token,
Token ID11
Feature activation-4.24e-02

Pos logit contributions
ble+0.003
nam+0.003
iring+0.003
bles+0.003
 rad+0.003
Neg logit contributions
 basis-0.004
rd-0.004
ake-0.004
storm-0.004
ital-0.004
Token "
Token ID366
Feature activation-3.83e-01

Pos logit contributions
ar+0.002
rd+0.002
ake+0.002
t+0.002
zed+0.002
Neg logit contributions
nam-0.001
ble-0.001
uted-0.001
iring-0.001
 rad-0.001
TokenYes
Token ID5297
Feature activation+7.49e-01

Pos logit contributions
zed+0.011
ar+0.011
rd+0.010
ake+0.010
 minutes+0.010
Neg logit contributions
nam-0.011
iring-0.010
efully-0.010
ble-0.010
uted-0.010
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
ble+0.019
nam+0.018
iring+0.018
 rad+0.018
bles+0.017
Neg logit contributions
seek-0.023
zed-0.022
rd-0.022
ake-0.021
 dreaming-0.021
Token and
Token ID290
Feature activation+2.94e-01

Pos logit contributions
nam+0.015
ble+0.015
iring+0.015
efully+0.014
uted+0.014
Neg logit contributions
zed-0.020
ar-0.020
rd-0.019
 minutes-0.018
ake-0.018
Token try
Token ID1949
Feature activation+2.06e-01

Pos logit contributions
nam+0.009
ble+0.008
efully+0.008
iring+0.008
ishes+0.008
Neg logit contributions
ar-0.008
t-0.008
zed-0.008
ake-0.008
rd-0.008
Token to
Token ID284
Feature activation+9.18e-01

Pos logit contributions
nam+0.007
ble+0.007
iring+0.007
 rad+0.007
bles+0.007
Neg logit contributions
ar-0.005
rd-0.005
t-0.004
zed-0.004
ake-0.004
Token grab
Token ID5552
Feature activation+9.64e-01

Pos logit contributions
iring+0.033
nam+0.033
ins+0.032
efully+0.032
ishes+0.032
Neg logit contributions
ar-0.018
 ever-0.018
t-0.017
zed-0.017
 bite-0.016
Token the
Token ID262
Feature activation+1.25e-02

Pos logit contributions
nam+0.029
iring+0.027
ble+0.027
efully+0.027
uted+0.026
Neg logit contributions
ar-0.026
zed-0.025
t-0.025
rd-0.024
ake-0.024
Token av
Token ID1196
Feature activation+4.76e+00

Pos logit contributions
efully+0.000
uted+0.000
iring+0.000
nam+0.000
ins+0.000
Neg logit contributions
 ever-0.000
t-0.000
 moment-0.000
 bite-0.000
 payoff-0.000
Tokenoc
Token ID420
Feature activation-2.01e+00

Pos logit contributions
nam+0.172
iring+0.164
ble+0.161
efully+0.158
uted+0.157
Neg logit contributions
ar-0.101
t-0.095
ake-0.093
zed-0.092
rd-0.090
Tokenados
Token ID22484
Feature activation+2.79e+00

Pos logit contributions
ar+0.082
ake+0.078
t+0.076
zed+0.076
rd+0.075
Neg logit contributions
nam-0.037
iring-0.030
efully-0.029
ble-0.029
uted-0.028
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
nam+0.085
iring+0.080
efully+0.079
ble+0.077
uted+0.076
Neg logit contributions
ar-0.073
t-0.071
zed-0.069
 ever-0.068
ake-0.068
Token But
Token ID887
Feature activation-8.57e-01

Pos logit contributions
nam+0.004
iring+0.003
ble+0.003
efully+0.003
uted+0.003
Neg logit contributions
ar-0.005
zed-0.005
t-0.004
rd-0.004
ake-0.004
Token the
Token ID262
Feature activation+3.07e-01

Pos logit contributions
ar+0.020
zed+0.020
t+0.019
ake+0.019
rd+0.019
Neg logit contributions
nam-0.028
iring-0.027
ble-0.026
efully-0.026
uted-0.026
TokenPlease
Token ID5492
Feature activation+1.22e+00

Pos logit contributions
nam+0.022
iring+0.021
ble+0.020
efully+0.020
uted+0.020
Neg logit contributions
ar-0.020
zed-0.019
t-0.019
ake-0.019
rd-0.019
Token help
Token ID1037
Feature activation+1.44e+00

Pos logit contributions
nam+0.036
ble+0.034
iring+0.033
efully+0.032
uted+0.032
Neg logit contributions
ar-0.032
zed-0.032
rd-0.031
ake-0.031
 minutes-0.031
Token me
Token ID502
Feature activation+2.88e+00

Pos logit contributions
nam+0.042
iring+0.040
ble+0.039
efully+0.039
uted+0.038
Neg logit contributions
ar-0.039
zed-0.038
t-0.037
rd-0.037
ake-0.036
Token shake
Token ID13279
Feature activation+3.23e-01

Pos logit contributions
nam+0.084
ble+0.080
iring+0.080
efully+0.078
uted+0.076
Neg logit contributions
ar-0.077
zed-0.075
t-0.074
rd-0.073
ake-0.072
Token this
Token ID428
Feature activation+2.14e-01

Pos logit contributions
nam+0.009
iring+0.008
ble+0.008
efully+0.008
ishes+0.008
Neg logit contributions
ar-0.009
zed-0.009
t-0.009
rd-0.009
ake-0.009
Token rad
Token ID2511
Feature activation+4.76e+00

Pos logit contributions
nam+0.006
iring+0.006
efully+0.006
ble+0.006
uted+0.006
Neg logit contributions
ar-0.006
t-0.006
zed-0.006
 minutes-0.005
ake-0.005
Tokenish
Token ID680
Feature activation+2.12e+00

Pos logit contributions
uted+0.090
nam+0.084
iring+0.073
 blamed+0.068
ble+0.066
Neg logit contributions
ar-0.185
ake-0.173
z-0.172
t-0.164
 ever-0.164
Token,
Token ID11
Feature activation+1.29e+00

Pos logit contributions
nam+0.064
iring+0.061
ble+0.060
efully+0.059
uted+0.057
Neg logit contributions
ar-0.055
zed-0.054
t-0.053
rd-0.052
ake-0.052
Token it
Token ID340
Feature activation-3.34e-02

Pos logit contributions
nam+0.042
iring+0.040
ble+0.039
efully+0.039
uted+0.038
Neg logit contributions
ar-0.031
zed-0.030
t-0.029
ake-0.028
rd-0.028
Token's
Token ID338
Feature activation+7.17e-01

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
ake+0.001
rd+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
uted-0.001
Token too
Token ID1165
Feature activation-1.44e-01

Pos logit contributions
nam+0.022
iring+0.021
ble+0.020
efully+0.020
uted+0.020
Neg logit contributions
ar-0.018
zed-0.018
t-0.018
 minutes-0.017
ake-0.017
TokenI
Token ID40
Feature activation+5.16e-01

Pos logit contributions
zed+0.008
ar+0.008
ake+0.008
rd+0.007
 dreaming+0.007
Neg logit contributions
nam-0.007
efully-0.006
iring-0.006
ble-0.005
uted-0.005
Token saw
Token ID2497
Feature activation-6.23e-01

Pos logit contributions
 ot+0.009
ish+0.008
ble+0.008
efully+0.008
nam+0.008
Neg logit contributions
zed-0.019
stand-0.018
seek-0.018
rd-0.018
side-0.018
Token a
Token ID257
Feature activation+3.77e-01

Pos logit contributions
 ever+0.013
ar+0.013
 dreaming+0.012
t+0.012
zed+0.012
Neg logit contributions
nam-0.022
ble-0.021
iring-0.020
efully-0.020
bles-0.019
Token big
Token ID1263
Feature activation+2.92e-01

Pos logit contributions
nam+0.012
efully+0.011
iring+0.011
ishes+0.011
uted+0.011
Neg logit contributions
ar-0.010
t-0.010
 ever-0.009
 moment-0.009
 dreaming-0.009
Token all
Token ID477
Feature activation+1.49e+00

Pos logit contributions
nam+0.008
iring+0.008
efully+0.008
uted+0.007
ble+0.007
Neg logit contributions
ar-0.008
t-0.008
 minutes-0.008
ake-0.008
 ever-0.008
Tokenigator
Token ID23823
Feature activation+4.72e+00

Pos logit contributions
nam+0.019
efully+0.017
ble+0.016
iring+0.016
ishes+0.015
Neg logit contributions
t-0.064
ar-0.063
 ever-0.063
 minutes-0.062
rd-0.061
Token there
Token ID612
Feature activation-7.32e-01

Pos logit contributions
nam+0.142
iring+0.136
ble+0.134
efully+0.131
uted+0.128
Neg logit contributions
ar-0.123
zed-0.122
t-0.118
rd-0.116
ake-0.115
Token!"
Token ID2474
Feature activation+3.22e-01

Pos logit contributions
ar+0.020
t+0.020
 ever+0.019
ake+0.019
rd+0.019
Neg logit contributions
nam-0.021
iring-0.020
efully-0.019
ble-0.019
ishes-0.019
Token
Token ID198
Feature activation+4.83e-02

Pos logit contributions
ble+0.012
iring+0.012
nam+0.012
efully+0.011
bles+0.011
Neg logit contributions
t-0.007
 dreaming-0.006
ar-0.006
stand-0.006
zed-0.006
Token
Token ID198
Feature activation-2.10e-01

Pos logit contributions
nam+0.002
ishes+0.002
efully+0.002
ble+0.002
iring+0.002
Neg logit contributions
t-0.001
zed-0.001
ar-0.001
ake-0.001
z-0.001
TokenTim
Token ID14967
Feature activation+2.01e-01

Pos logit contributions
t+0.004
ar+0.004
rd+0.004
z+0.003
zed+0.003
Neg logit contributions
nam-0.008
ishes-0.008
ble-0.008
iring-0.007
efully-0.007
Token mom
Token ID1995
Feature activation-7.37e-01

Pos logit contributions
ar+0.003
zed+0.003
t+0.003
rd+0.003
ake+0.003
Neg logit contributions
nam-0.003
iring-0.003
ble-0.003
efully-0.003
uted-0.003
Token said
Token ID531
Feature activation-7.14e-01

Pos logit contributions
ar+0.022
zed+0.022
t+0.022
rd+0.021
ake+0.021
Neg logit contributions
nam-0.019
iring-0.018
ble-0.018
efully-0.018
uted-0.017
Token,
Token ID11
Feature activation-7.90e-01

Pos logit contributions
seek+0.020
rd+0.020
ar+0.019
 basis+0.019
ake+0.019
Neg logit contributions
nam-0.020
 rad-0.019
ble-0.019
 av-0.018
 ot-0.018
Token "
Token ID366
Feature activation-3.94e-01

Pos logit contributions
ar+0.028
rd+0.027
zed+0.027
ake+0.026
t+0.026
Neg logit contributions
nam-0.017
iring-0.015
ble-0.015
efully-0.014
uted-0.014
TokenAll
Token ID3237
Feature activation-3.51e-01

Pos logit contributions
ar+0.010
t+0.010
zed+0.009
ake+0.009
rd+0.009
Neg logit contributions
nam-0.013
iring-0.012
ble-0.012
efully-0.012
uted-0.011
Tokenigators
Token ID25975
Feature activation+4.71e+00

Pos logit contributions
ar+0.010
zed+0.010
t+0.010
ake+0.009
rd+0.009
Neg logit contributions
nam-0.010
iring-0.009
ble-0.009
efully-0.009
uted-0.009
Token are
Token ID389
Feature activation-2.30e-01

Pos logit contributions
nam+0.121
iring+0.112
ble+0.110
efully+0.109
uted+0.105
Neg logit contributions
ar-0.146
zed-0.142
t-0.141
ake-0.138
rd-0.137
Token not
Token ID407
Feature activation-7.03e-01

Pos logit contributions
ar+0.007
zed+0.007
rd+0.007
t+0.007
ake+0.007
Neg logit contributions
nam-0.006
iring-0.005
ble-0.005
ishes-0.005
efully-0.005
Token nice
Token ID3621
Feature activation+5.18e-03

Pos logit contributions
 ever+0.017
 dreaming+0.017
 minutes+0.016
ar+0.016
t+0.016
Neg logit contributions
nam-0.022
efully-0.021
iring-0.021
ble-0.021
uted-0.020
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
nam+0.000
iring+0.000
ishes+0.000
ble+0.000
uted+0.000
Neg logit contributions
zed-0.000
ar-0.000
t-0.000
rd-0.000
ake-0.000
Token They
Token ID1119
Feature activation-9.56e-02

Pos logit contributions
ar+0.029
t+0.028
zed+0.027
rd+0.027
ake+0.027
Neg logit contributions
nam-0.032
iring-0.030
ble-0.030
efully-0.029
uted-0.028
Token help
Token ID1037
Feature activation+8.72e-01

Pos logit contributions
ar+0.015
t+0.014
zed+0.014
ake+0.014
rd+0.014
Neg logit contributions
nam-0.019
ble-0.018
iring-0.018
efully-0.018
uted-0.017
Token her
Token ID607
Feature activation+1.43e+00

Pos logit contributions
efully+0.031
nam+0.031
uted+0.030
bles+0.030
iring+0.030
Neg logit contributions
ake-0.016
 Halloween-0.014
 ever-0.014
gh-0.014
stand-0.013
Token mom
Token ID1995
Feature activation+2.69e-01

Pos logit contributions
iring+0.045
efully+0.044
uted+0.044
nam+0.044
ble+0.041
Neg logit contributions
zed-0.034
 dreaming-0.033
ar-0.032
rd-0.032
t-0.031
Token put
Token ID1234
Feature activation+1.11e-01

Pos logit contributions
nam+0.010
efully+0.009
iring+0.009
uted+0.009
ble+0.009
Neg logit contributions
ake-0.005
t-0.005
ar-0.005
 dreaming-0.005
 ever-0.005
Token or
Token ID393
Feature activation-2.46e-01

Pos logit contributions
nam+0.003
iring+0.003
ble+0.003
efully+0.003
uted+0.003
Neg logit contributions
ar-0.003
zed-0.003
t-0.003
ake-0.003
 minutes-0.003
Tokennam
Token ID7402
Feature activation+4.70e+00

Pos logit contributions
ar+0.006
zed+0.006
 dreaming+0.006
t+0.006
 minutes+0.006
Neg logit contributions
iring-0.007
efully-0.007
nam-0.007
uted-0.007
ble-0.007
Tokenents
Token ID658
Feature activation+9.75e-01

Pos logit contributions
nam+0.096
 ot+0.091
ble+0.091
efully+0.089
uted+0.089
Neg logit contributions
t-0.163
ake-0.161
z-0.153
 ever-0.152
ar-0.151
Token on
Token ID319
Feature activation-2.03e-01

Pos logit contributions
nam+0.030
iring+0.029
efully+0.028
ble+0.028
uted+0.027
Neg logit contributions
ar-0.025
t-0.024
zed-0.024
ake-0.023
 ever-0.023
Token the
Token ID262
Feature activation+1.92e-01

Pos logit contributions
ar+0.007
t+0.006
zed+0.006
ake+0.006
rd+0.006
Neg logit contributions
nam-0.006
 av-0.005
 rad-0.005
efully-0.005
iring-0.004
Token tree
Token ID5509
Feature activation-2.82e-01

Pos logit contributions
efully+0.006
iring+0.006
uted+0.005
ins+0.005
ble+0.005
Neg logit contributions
 dreaming-0.005
t-0.005
 ever-0.005
zed-0.005
stand-0.005
Token.
Token ID13
Feature activation+6.26e-01

Pos logit contributions
ar+0.006
t+0.006
ake+0.005
zed+0.005
rd+0.005
Neg logit contributions
nam-0.010
iring-0.010
efully-0.010
ble-0.009
uted-0.009
Token got
Token ID1392
Feature activation+3.17e-02

Pos logit contributions
ar+0.015
zed+0.015
rd+0.015
ake+0.015
t+0.015
Neg logit contributions
nam-0.012
iring-0.011
ble-0.011
efully-0.011
uted-0.011
Token to
Token ID284
Feature activation-5.34e-01

Pos logit contributions
nam+0.001
iring+0.001
ble+0.001
efully+0.001
uted+0.001
Neg logit contributions
ar-0.001
t-0.001
zed-0.001
 ever-0.001
 dreaming-0.001
Token hold
Token ID1745
Feature activation-2.86e-01

Pos logit contributions
ar+0.012
zed+0.012
t+0.011
ake+0.011
rd+0.011
Neg logit contributions
nam-0.018
iring-0.018
ble-0.017
efully-0.017
uted-0.016
Token an
Token ID281
Feature activation+5.39e-01

Pos logit contributions
ar+0.008
zed+0.008
t+0.008
ake+0.008
rd+0.008
Neg logit contributions
nam-0.008
iring-0.007
ble-0.007
efully-0.007
uted-0.007
Token all
Token ID477
Feature activation+1.40e+00

Pos logit contributions
nam+0.013
iring+0.010
ishes+0.010
bles+0.010
ins+0.009
Neg logit contributions
 ever-0.018
 minutes-0.018
rd-0.018
 basis-0.018
ake-0.017
Tokenigator
Token ID23823
Feature activation+4.69e+00

Pos logit contributions
nam+0.030
iring+0.027
ble+0.027
efully+0.026
uted+0.025
Neg logit contributions
ar-0.049
zed-0.048
t-0.048
rd-0.047
ake-0.047
Token toy
Token ID13373
Feature activation+9.40e-01

Pos logit contributions
nam+0.136
iring+0.126
ble+0.124
efully+0.122
ishes+0.120
Neg logit contributions
ar-0.131
zed-0.130
t-0.125
rd-0.122
ake-0.122
Token.
Token ID13
Feature activation+3.05e-02

Pos logit contributions
nam+0.030
iring+0.028
ble+0.027
efully+0.027
uted+0.027
Neg logit contributions
ar-0.024
t-0.023
 ever-0.022
zed-0.022
ake-0.022
Token But
Token ID887
Feature activation-7.74e-01

Pos logit contributions
nam+0.001
iring+0.001
efully+0.001
ble+0.001
ishes+0.001
Neg logit contributions
ar-0.001
zed-0.001
t-0.001
ake-0.001
rd-0.001
Token M
Token ID337
Feature activation-4.21e-01

Pos logit contributions
ake+0.025
rd+0.025
seek+0.024
t+0.024
gh+0.024
Neg logit contributions
nam-0.021
iring-0.017
 rad-0.017
 ot-0.017
ble-0.016
Tokenomm
Token ID2002
Feature activation+8.18e-01

Pos logit contributions
ar+0.012
ake+0.012
t+0.012
rd+0.012
zed+0.011
Neg logit contributions
nam-0.013
efully-0.011
ble-0.011
uted-0.010
iring-0.010
Token and
Token ID290
Feature activation-2.13e-01

Pos logit contributions
zed+0.037
ar+0.037
rd+0.034
t+0.034
 minutes+0.034
Neg logit contributions
nam-0.023
ishes-0.021
iring-0.021
 rad-0.020
 ot-0.020
Token saw
Token ID2497
Feature activation-7.66e-01

Pos logit contributions
 dreaming+0.005
zed+0.004
t+0.004
 ever+0.004
ar+0.004
Neg logit contributions
iring-0.007
ble-0.007
efully-0.007
uted-0.007
nam-0.007
Token a
Token ID257
Feature activation+1.92e-01

Pos logit contributions
zed+0.012
 dreaming+0.012
ar+0.012
 ever+0.011
 minutes+0.011
Neg logit contributions
nam-0.029
iring-0.028
ble-0.028
efully-0.028
ishes-0.028
Token cute
Token ID13779
Feature activation+6.00e-01

Pos logit contributions
efully+0.006
nam+0.006
ishes+0.006
iring+0.006
uted+0.006
Neg logit contributions
ar-0.005
t-0.004
ake-0.004
 dreaming-0.004
 minutes-0.004
Token all
Token ID477
Feature activation+1.69e+00

Pos logit contributions
nam+0.016
iring+0.015
ble+0.014
efully+0.014
uted+0.014
Neg logit contributions
ar-0.018
zed-0.018
t-0.018
ake-0.017
rd-0.017
Tokenigator
Token ID23823
Feature activation+4.68e+00

Pos logit contributions
efully+0.024
nam+0.024
ble+0.023
iring+0.022
bles+0.021
Neg logit contributions
t-0.068
 ever-0.068
 dreaming-0.067
ar-0.067
rd-0.067
Token.
Token ID13
Feature activation+2.98e-01

Pos logit contributions
nam+0.148
iring+0.138
efully+0.137
ble+0.135
uted+0.133
Neg logit contributions
ar-0.117
zed-0.113
t-0.112
ake-0.110
 ever-0.109
Token
Token ID220
Feature activation+5.13e-01

Pos logit contributions
ble+0.010
nam+0.010
iring+0.010
efully+0.010
uted+0.010
Neg logit contributions
t-0.007
ar-0.007
stand-0.006
zed-0.006
 dreaming-0.006
Token
Token ID198
Feature activation-6.34e-01

Pos logit contributions
nam+0.020
ishes+0.019
 ot+0.019
 rad+0.018
efully+0.018
Neg logit contributions
t-0.011
ake-0.009
zed-0.009
rd-0.009
ar-0.009
Token
Token ID198
Feature activation-9.46e-01

Pos logit contributions
ar+0.020
zed+0.019
t+0.019
rd+0.019
ake+0.019
Neg logit contributions
nam-0.016
iring-0.015
ble-0.015
efully-0.014
uted-0.014
TokenL
Token ID43
Feature activation-6.42e-01

Pos logit contributions
ar+0.025
zed+0.025
ake+0.023
 ever+0.023
rd+0.023
Neg logit contributions
nam-0.029
iring-0.027
efully-0.026
ble-0.025
uted-0.025
Token start
Token ID923
Feature activation-5.65e-01

Pos logit contributions
nam+0.010
iring+0.009
ble+0.009
efully+0.009
uted+0.009
Neg logit contributions
ar-0.009
t-0.009
zed-0.009
ake-0.008
rd-0.008
Token with
Token ID351
Feature activation+2.02e-01

Pos logit contributions
ar+0.016
zed+0.016
rd+0.015
t+0.015
ake+0.014
Neg logit contributions
nam-0.017
ble-0.015
iring-0.015
efully-0.015
ishes-0.014
Token the
Token ID262
Feature activation-6.74e-01

Pos logit contributions
nam+0.005
ble+0.005
iring+0.005
efully+0.005
ishes+0.005
Neg logit contributions
ar-0.006
t-0.006
zed-0.006
rd-0.006
ake-0.006
Token roller
Token ID24471
Feature activation-3.32e+00

Pos logit contributions
zed+0.022
ar+0.022
ake+0.022
rd+0.020
t+0.020
Neg logit contributions
nam-0.017
iring-0.015
 ot-0.015
ble-0.014
bles-0.014
Tokenco
Token ID1073
Feature activation-2.94e+00

Pos logit contributions
t+0.076
 ever+0.075
zed+0.075
ake+0.074
ar+0.074
Neg logit contributions
ble-0.096
nam-0.091
bles-0.089
 av-0.088
uted-0.088
Tokenaster
Token ID1603
Feature activation-5.05e+00

Pos logit contributions
ar+0.081
 dreaming+0.080
zed+0.079
 injuries+0.078
 payoff+0.076
Neg logit contributions
nam-0.075
ins-0.070
ble-0.070
ishes-0.069
uted-0.069
Token?
Token ID30
Feature activation-8.36e-01

Pos logit contributions
ar+0.156
zed+0.154
ake+0.146
t+0.145
rd+0.144
Neg logit contributions
nam-0.123
ble-0.114
iring-0.112
efully-0.111
ishes-0.109
Tokenâ
Token ID22940
Feature activation+1.30e+00

Pos logit contributions
ar+0.020
t+0.020
zed+0.019
rd+0.019
ake+0.019
Neg logit contributions
nam-0.027
iring-0.025
ble-0.025
efully-0.024
uted-0.024
Token
Token ID26391
Feature activation+2.42e-01

Pos logit contributions
nam+0.032
ble+0.030
iring+0.030
efully+0.030
uted+0.029
Neg logit contributions
ar-0.040
t-0.039
zed-0.039
 minutes-0.038
 ever-0.038
Token his
Token ID465
Feature activation-5.65e-01

Pos logit contributions
nam+0.005
ble+0.005
iring+0.005
uted+0.005
efully+0.005
Neg logit contributions
ar-0.008
 ever-0.007
zed-0.007
 minutes-0.007
 payoff-0.007
Token dad
Token ID9955
Feature activation-2.68e-01

Pos logit contributions
ar+0.021
t+0.020
ake+0.020
rd+0.019
seek+0.019
Neg logit contributions
nam-0.011
ble-0.010
iring-0.010
efully-0.010
 rad-0.009
Token puts
Token ID7584
Feature activation-1.55e+00

Pos logit contributions
nam+0.017
ble+0.016
efully+0.016
iring+0.016
ishes+0.016
Neg logit contributions
ar-0.017
rd-0.016
t-0.016
ake-0.016
zed-0.016
Token bread
Token ID8509
Feature activation+1.31e+00

Pos logit contributions
ar+0.048
rd+0.048
t+0.047
seek+0.046
zed+0.045
Neg logit contributions
nam-0.043
ble-0.037
ishes-0.037
 av-0.036
efully-0.036
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
nam+0.037
iring+0.035
ble+0.034
efully+0.034
uted+0.033
Neg logit contributions
ar-0.037
zed-0.036
t-0.035
ake-0.035
rd-0.034
Token the
Token ID262
Feature activation+7.88e-03

Pos logit contributions
nam+0.037
iring+0.033
ble+0.033
efully+0.032
 rad+0.031
Neg logit contributions
ar-0.047
t-0.045
zed-0.044
rd-0.043
ake-0.043
Token to
Token ID284
Feature activation-4.22e-01

Pos logit contributions
nam+0.000
iring+0.000
ble+0.000
efully+0.000
uted+0.000
Neg logit contributions
ar-0.000
zed-0.000
t-0.000
ake-0.000
rd-0.000
Tokenaster
Token ID1603
Feature activation-5.01e+00

Pos logit contributions
ar+0.007
t+0.007
rd+0.007
ake+0.007
zed+0.007
Neg logit contributions
nam-0.017
ble-0.016
iring-0.015
efully-0.015
 rad-0.015
Token and
Token ID290
Feature activation+1.02e-01

Pos logit contributions
ar+0.159
t+0.152
zed+0.148
rd+0.147
da+0.147
Neg logit contributions
nam-0.110
ble-0.106
ishes-0.105
ins-0.105
 av-0.101
Token waits
Token ID28364
Feature activation-9.89e-01

Pos logit contributions
nam+0.003
iring+0.003
ble+0.003
efully+0.003
ishes+0.003
Neg logit contributions
ar-0.003
t-0.003
zed-0.003
rd-0.003
ake-0.003
Token for
Token ID329
Feature activation+6.47e-01

Pos logit contributions
ar+0.027
rd+0.025
t+0.025
zed+0.025
ake+0.025
Neg logit contributions
nam-0.029
ble-0.029
iring-0.028
uted-0.026
efully-0.026
Token it
Token ID340
Feature activation-1.18e+00

Pos logit contributions
nam+0.017
ble+0.015
iring+0.014
 av+0.014
 rad+0.014
Neg logit contributions
ar-0.022
t-0.021
rd-0.021
ake-0.020
z-0.020
Token to
Token ID284
Feature activation-1.95e-01

Pos logit contributions
ar+0.028
rd+0.028
zed+0.027
 basis+0.027
ake+0.026
Neg logit contributions
nam-0.036
ishes-0.035
iring-0.035
bles-0.034
ble-0.034
Token down
Token ID866
Feature activation+3.97e-01

Pos logit contributions
nam+0.006
efully+0.005
iring+0.005
ishes+0.005
ble+0.005
Neg logit contributions
ar-0.014
zed-0.014
rd-0.014
ake-0.014
t-0.014
Token on
Token ID319
Feature activation-1.45e-01

Pos logit contributions
iring+0.009
nam+0.009
ble+0.008
efully+0.008
 vendors+0.008
Neg logit contributions
rd-0.013
ake-0.013
zed-0.013
ar-0.012
gh-0.012
Token the
Token ID262
Feature activation-1.23e-01

Pos logit contributions
t+0.006
rd+0.006
ar+0.006
zed+0.006
ake+0.006
Neg logit contributions
nam-0.002
 rad-0.002
efully-0.002
 vendors-0.002
iring-0.002
Token roller
Token ID24471
Feature activation-3.26e+00

Pos logit contributions
ar+0.004
t+0.004
ake+0.004
rd+0.004
zed+0.004
Neg logit contributions
nam-0.003
ble-0.003
iring-0.003
efully-0.003
uted-0.003
Tokenco
Token ID1073
Feature activation-2.70e+00

Pos logit contributions
ake+0.067
t+0.067
 payoff+0.067
 ever+0.067
 dreaming+0.066
Neg logit contributions
ble-0.096
uted-0.094
bles-0.090
efully-0.090
iring-0.089
Tokenaster
Token ID1603
Feature activation-4.96e+00

Pos logit contributions
ar+0.071
 dreaming+0.067
zed+0.066
t+0.065
 minutes+0.065
Neg logit contributions
nam-0.075
iring-0.072
ble-0.071
uted-0.071
efully-0.070
Token,
Token ID11
Feature activation+5.04e-01

Pos logit contributions
ar+0.148
ake+0.147
zed+0.147
da+0.142
 injuries+0.142
Neg logit contributions
nam-0.106
uted-0.102
ble-0.100
bles-0.100
iring-0.100
Token Lily
Token ID20037
Feature activation+1.99e-01

Pos logit contributions
nam+0.016
iring+0.014
ble+0.014
 ot+0.013
 rad+0.013
Neg logit contributions
ar-0.014
ake-0.013
rd-0.013
zed-0.013
t-0.013
Token shouted
Token ID17293
Feature activation-5.78e-01

Pos logit contributions
nam+0.006
iring+0.005
ble+0.005
efully+0.005
uted+0.005
Neg logit contributions
ar-0.006
zed-0.006
t-0.005
rd-0.005
ake-0.005
Token,
Token ID11
Feature activation-5.45e-01

Pos logit contributions
ar+0.018
zed+0.018
rd+0.018
t+0.018
 minutes+0.017
Neg logit contributions
nam-0.014
ble-0.013
iring-0.013
uted-0.013
efully-0.012
Token "
Token ID366
Feature activation-4.60e-01

Pos logit contributions
ar+0.019
rd+0.018
zed+0.018
ake+0.018
t+0.018
Neg logit contributions
nam-0.012
ble-0.011
iring-0.011
efully-0.011
uted-0.010
Token.
Token ID13
Feature activation+7.74e-02

Pos logit contributions
rd+0.002
zed+0.002
ar+0.002
 basis+0.002
seek+0.002
Neg logit contributions
ble-0.002
iring-0.002
uted-0.001
ishes-0.001
 ot-0.001
Token She
Token ID1375
Feature activation+5.02e-01

Pos logit contributions
nam+0.002
ble+0.002
iring+0.002
ishes+0.002
efully+0.002
Neg logit contributions
ar-0.002
t-0.002
zed-0.002
 minutes-0.002
 dreaming-0.002
Token grabbed
Token ID13176
Feature activation+1.70e-01

Pos logit contributions
nam+0.016
iring+0.016
ble+0.015
efully+0.015
ishes+0.015
Neg logit contributions
ar-0.012
zed-0.012
t-0.012
 minutes-0.012
 ever-0.011
Token the
Token ID262
Feature activation-9.57e-01

Pos logit contributions
nam+0.005
ble+0.004
iring+0.004
efully+0.004
ishes+0.004
Neg logit contributions
ar-0.005
rd-0.005
zed-0.005
t-0.005
ake-0.005
Token to
Token ID284
Feature activation-1.81e-01

Pos logit contributions
ar+0.034
zed+0.033
rd+0.033
t+0.032
ake+0.032
Neg logit contributions
nam-0.021
ble-0.019
iring-0.019
ishes-0.018
uted-0.017
Tokenaster
Token ID1603
Feature activation-4.89e+00

Pos logit contributions
ar+0.006
rd+0.006
t+0.005
ake+0.005
zed+0.005
Neg logit contributions
nam-0.005
ble-0.004
iring-0.004
efully-0.004
 rad-0.004
Token and
Token ID290
Feature activation+2.87e-01

Pos logit contributions
ar+0.180
t+0.173
da+0.169
 basis+0.168
rd+0.167
Neg logit contributions
ble-0.088
ins-0.082
uted-0.080
bles-0.076
ishes-0.075
Token threw
Token ID9617
Feature activation+5.14e-01

Pos logit contributions
nam+0.009
iring+0.008
ble+0.008
efully+0.008
uted+0.008
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
 minutes-0.007
rd-0.007
Token it
Token ID340
Feature activation-1.15e+00

Pos logit contributions
nam+0.014
efully+0.013
ble+0.013
iring+0.013
ishes+0.013
Neg logit contributions
ar-0.015
rd-0.015
zed-0.015
t-0.014
ake-0.014
Token in
Token ID287
Feature activation+1.53e+00

Pos logit contributions
ar+0.038
rd+0.037
zed+0.037
ake+0.036
t+0.035
Neg logit contributions
nam-0.027
ble-0.025
iring-0.025
efully-0.024
uted-0.023
Token the
Token ID262
Feature activation-1.68e-02

Pos logit contributions
nam+0.032
efully+0.029
 rad+0.028
ble+0.028
iring+0.028
Neg logit contributions
ar-0.058
zed-0.056
t-0.054
rd-0.054
ake-0.053
Token toast
Token ID27805
Feature activation-1.28e+00

Pos logit contributions
ar+0.020
zed+0.019
rd+0.019
t+0.019
ake+0.019
Neg logit contributions
nam-0.016
ble-0.015
iring-0.015
efully-0.014
ishes-0.014
Token out
Token ID503
Feature activation-4.64e-01

Pos logit contributions
ar+0.036
zed+0.035
t+0.034
rd+0.034
 minutes+0.033
Neg logit contributions
nam-0.036
ble-0.034
iring-0.034
efully-0.033
uted-0.032
Token of
Token ID286
Feature activation-3.30e-02

Pos logit contributions
ar+0.016
zed+0.015
seek+0.015
rd+0.015
t+0.014
Neg logit contributions
iring-0.011
ble-0.010
nam-0.010
efully-0.010
 rad-0.010
Token the
Token ID262
Feature activation-1.54e-01

Pos logit contributions
ar+0.001
t+0.001
zed+0.001
rd+0.001
ake+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
uted-0.001
Token to
Token ID284
Feature activation-5.60e-01

Pos logit contributions
ar+0.004
zed+0.004
 minutes+0.004
ake+0.004
t+0.004
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.004
uted-0.004
Tokenaster
Token ID1603
Feature activation-4.87e+00

Pos logit contributions
t+0.010
ar+0.009
rd+0.009
ake+0.008
zed+0.008
Neg logit contributions
nam-0.022
ble-0.021
 rad-0.021
efully-0.021
 av-0.021
Token and
Token ID290
Feature activation+1.23e-01

Pos logit contributions
ar+0.155
t+0.144
zed+0.143
rd+0.137
ake+0.137
Neg logit contributions
ble-0.108
nam-0.106
uted-0.105
iring-0.103
efully-0.103
Token put
Token ID1234
Feature activation-4.27e-01

Pos logit contributions
nam+0.004
iring+0.004
ble+0.004
efully+0.003
uted+0.003
Neg logit contributions
ar-0.003
zed-0.003
t-0.003
ake-0.003
rd-0.003
Token it
Token ID340
Feature activation-1.38e-01

Pos logit contributions
rd+0.013
seek+0.012
t+0.012
ar+0.012
zed+0.012
Neg logit contributions
nam-0.012
ishes-0.011
efully-0.011
ble-0.011
 rad-0.011
Token on
Token ID319
Feature activation+3.26e-01

Pos logit contributions
ar+0.004
zed+0.004
rd+0.004
t+0.004
ake+0.004
Neg logit contributions
nam-0.004
ble-0.004
iring-0.003
efully-0.003
ishes-0.003
Token a
Token ID257
Feature activation-4.23e-01

Pos logit contributions
nam+0.008
efully+0.008
ble+0.008
iring+0.008
 rad+0.007
Neg logit contributions
ar-0.010
t-0.010
zed-0.010
rd-0.010
ake-0.009
Token some
Token ID617
Feature activation+2.69e-01

Pos logit contributions
rd+0.052
seek+0.051
t+0.051
ar+0.051
zed+0.050
Neg logit contributions
nam-0.043
ishes-0.039
ble-0.037
efully-0.037
 av-0.036
Token bread
Token ID8509
Feature activation+1.42e+00

Pos logit contributions
nam+0.007
iring+0.007
ble+0.006
efully+0.006
uted+0.006
Neg logit contributions
ar-0.008
 minutes-0.008
t-0.008
zed-0.008
ake-0.008
Token in
Token ID287
Feature activation+1.40e+00

Pos logit contributions
nam+0.040
iring+0.038
ble+0.038
efully+0.037
ishes+0.036
Neg logit contributions
ar-0.040
zed-0.040
rd-0.038
t-0.038
ake-0.037
Token the
Token ID262
Feature activation-3.55e-02

Pos logit contributions
nam+0.030
 rad+0.026
ble+0.026
iring+0.024
 av+0.024
Neg logit contributions
ar-0.053
zed-0.052
rd-0.051
t-0.051
seek-0.050
Token to
Token ID284
Feature activation-3.28e-01

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
rd+0.001
ake+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Tokenaster
Token ID1603
Feature activation-4.87e+00

Pos logit contributions
ar+0.006
t+0.005
rd+0.005
ake+0.005
zed+0.005
Neg logit contributions
nam-0.013
ble-0.012
iring-0.012
efully-0.012
 rad-0.012
Token.
Token ID13
Feature activation+5.26e-01

Pos logit contributions
ar+0.162
t+0.155
zed+0.151
da+0.151
rd+0.147
Neg logit contributions
ins-0.093
ble-0.092
nam-0.091
ishes-0.091
uted-0.088
Token He
Token ID679
Feature activation+5.00e-01

Pos logit contributions
nam+0.017
iring+0.016
ble+0.016
efully+0.016
ishes+0.015
Neg logit contributions
ar-0.013
t-0.013
zed-0.013
 minutes-0.012
rd-0.012
Token goes
Token ID2925
Feature activation-8.00e-01

Pos logit contributions
nam+0.016
iring+0.015
ble+0.015
efully+0.015
uted+0.014
Neg logit contributions
ar-0.012
zed-0.012
t-0.012
 minutes-0.011
rd-0.011
Token to
Token ID284
Feature activation-2.06e-02

Pos logit contributions
rd+0.020
zed+0.020
ar+0.020
gh+0.018
ake+0.018
Neg logit contributions
nam-0.025
ble-0.024
iring-0.024
bles-0.023
efully-0.023
Token his
Token ID465
Feature activation-8.19e-01

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
rd+0.001
ake+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
uted-0.001
Token the
Token ID262
Feature activation+2.72e-01

Pos logit contributions
rd+0.012
ar+0.011
seek+0.011
t+0.011
ake+0.011
Neg logit contributions
nam-0.010
ble-0.009
ishes-0.009
efully-0.009
iring-0.009
Token bread
Token ID8509
Feature activation+1.58e+00

Pos logit contributions
nam+0.006
iring+0.006
ble+0.005
efully+0.005
ishes+0.005
Neg logit contributions
ar-0.010
zed-0.009
t-0.009
rd-0.009
ake-0.009
Token in
Token ID287
Feature activation+1.80e+00

Pos logit contributions
nam+0.047
iring+0.045
efully+0.044
uted+0.043
ble+0.042
Neg logit contributions
ar-0.042
t-0.041
zed-0.040
ake-0.040
 ever-0.039
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
nam+0.044
ble+0.040
iring+0.039
 rad+0.038
efully+0.038
Neg logit contributions
ar-0.061
t-0.059
zed-0.058
rd-0.057
ake-0.056
Token to
Token ID284
Feature activation-2.81e-02

Pos logit contributions
nam+0.007
iring+0.006
ble+0.006
uted+0.006
efully+0.006
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
 minutes-0.007
ake-0.007
Tokenaster
Token ID1603
Feature activation-4.83e+00

Pos logit contributions
ar+0.000
t+0.000
zed+0.000
rd+0.000
ake+0.000
Neg logit contributions
nam-0.001
ble-0.001
iring-0.001
efully-0.001
uted-0.001
Token and
Token ID290
Feature activation+7.05e-01

Pos logit contributions
ar+0.161
t+0.152
zed+0.149
da+0.148
 basis+0.146
Neg logit contributions
ble-0.095
ins-0.092
nam-0.091
uted-0.089
ishes-0.087
Token pushed
Token ID7121
Feature activation-1.15e-02

Pos logit contributions
nam+0.022
iring+0.022
ble+0.021
efully+0.021
uted+0.020
Neg logit contributions
ar-0.018
zed-0.017
t-0.017
 minutes-0.016
 dreaming-0.016
Token the
Token ID262
Feature activation+5.81e-01

Pos logit contributions
ar+0.000
zed+0.000
t+0.000
rd+0.000
ake+0.000
Neg logit contributions
nam-0.000
ble-0.000
iring-0.000
efully-0.000
uted-0.000
Token button
Token ID4936
Feature activation-1.25e+00

Pos logit contributions
nam+0.015
iring+0.014
efully+0.014
ble+0.014
uted+0.014
Neg logit contributions
ar-0.017
zed-0.017
t-0.017
ake-0.017
 minutes-0.017
Token.
Token ID13
Feature activation+8.96e-01

Pos logit contributions
ar+0.038
zed+0.038
rd+0.038
ake+0.037
 basis+0.036
Neg logit contributions
nam-0.031
ble-0.030
iring-0.029
efully-0.028
bles-0.028
Token just
Token ID655
Feature activation-1.40e+00

Pos logit contributions
ar+0.012
t+0.012
zed+0.012
rd+0.011
ake+0.011
Neg logit contributions
nam-0.014
efully-0.013
ble-0.013
iring-0.013
uted-0.012
Token stuck
Token ID7819
Feature activation+1.80e-01

Pos logit contributions
ar+0.037
t+0.035
zed+0.035
ake+0.034
rd+0.034
Neg logit contributions
nam-0.044
efully-0.040
ble-0.039
iring-0.038
 rad-0.037
Token with
Token ID351
Feature activation+2.03e-01

Pos logit contributions
nam+0.005
ble+0.004
iring+0.004
efully+0.004
ishes+0.004
Neg logit contributions
ar-0.005
zed-0.005
rd-0.005
t-0.005
ake-0.005
Token the
Token ID262
Feature activation-6.17e-01

Pos logit contributions
nam+0.005
ishes+0.004
efully+0.004
 rad+0.004
iring+0.004
Neg logit contributions
ar-0.007
t-0.007
ake-0.006
rd-0.006
zed-0.006
Token to
Token ID284
Feature activation-4.15e-01

Pos logit contributions
ar+0.019
zed+0.019
t+0.019
rd+0.019
ake+0.018
Neg logit contributions
nam-0.016
iring-0.014
ble-0.014
efully-0.014
ishes-0.013
Tokenaster
Token ID1603
Feature activation-4.80e+00

Pos logit contributions
ar+0.014
rd+0.013
t+0.013
ake+0.013
zed+0.013
Neg logit contributions
nam-0.010
ble-0.009
iring-0.009
 ot-0.009
 rad-0.008
Token in
Token ID287
Feature activation+1.46e+00

Pos logit contributions
ar+0.143
da+0.138
zed+0.136
ake+0.133
t+0.129
Neg logit contributions
nam-0.110
uted-0.104
ishes-0.103
ins-0.102
iring-0.101
Token their
Token ID511
Feature activation-1.08e+00

Pos logit contributions
nam+0.022
 rad+0.019
efully+0.019
ble+0.019
iring+0.018
Neg logit contributions
seek-0.060
ar-0.060
zed-0.058
t-0.057
rd-0.056
Token modern
Token ID3660
Feature activation-4.89e-01

Pos logit contributions
t+0.037
ar+0.036
zed+0.035
ake+0.034
rd+0.034
Neg logit contributions
nam-0.025
ishes-0.022
efully-0.022
iring-0.022
 rad-0.021
Token home
Token ID1363
Feature activation-6.48e-01

Pos logit contributions
t+0.017
ar+0.017
zed+0.016
 ever+0.015
da+0.015
Neg logit contributions
nam-0.010
ishes-0.010
 rad-0.010
efully-0.009
 av-0.009
Token.
Token ID13
Feature activation+2.31e-01

Pos logit contributions
ar+0.020
zed+0.019
ake+0.019
t+0.018
da+0.018
Neg logit contributions
nam-0.017
iring-0.016
ble-0.016
bles-0.014
efully-0.014
Token more
Token ID517
Feature activation-5.54e-01

Pos logit contributions
rd+0.019
ar+0.019
t+0.019
zed+0.019
ake+0.018
Neg logit contributions
nam-0.022
efully-0.020
ble-0.020
ishes-0.020
iring-0.020
Token bread
Token ID8509
Feature activation+1.80e+00

Pos logit contributions
ar+0.017
zed+0.016
t+0.016
ake+0.016
rd+0.016
Neg logit contributions
nam-0.015
iring-0.014
ble-0.014
efully-0.013
ishes-0.013
Token in
Token ID287
Feature activation+1.12e+00

Pos logit contributions
nam+0.050
iring+0.047
ble+0.046
efully+0.045
ishes+0.045
Neg logit contributions
ar-0.052
zed-0.051
t-0.050
rd-0.050
ake-0.049
Token the
Token ID262
Feature activation-3.32e-02

Pos logit contributions
nam+0.027
ble+0.023
 rad+0.023
efully+0.022
 av+0.022
Neg logit contributions
ar-0.040
zed-0.039
t-0.039
rd-0.039
seek-0.038
Token to
Token ID284
Feature activation-5.84e-01

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
rd+0.001
ake+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Tokenaster
Token ID1603
Feature activation-4.79e+00

Pos logit contributions
t+0.010
ar+0.010
rd+0.009
ake+0.009
zed+0.009
Neg logit contributions
nam-0.023
ble-0.022
 rad-0.022
efully-0.021
 av-0.021
Token and
Token ID290
Feature activation-5.06e-02

Pos logit contributions
ar+0.155
t+0.153
da+0.148
 basis+0.148
rd+0.147
Neg logit contributions
ins-0.099
ishes-0.098
ble-0.095
nam-0.093
 av-0.091
Token turned
Token ID2900
Feature activation-2.42e-02

Pos logit contributions
ar+0.001
t+0.001
rd+0.001
ake+0.001
zed+0.001
Neg logit contributions
nam-0.002
ble-0.001
efully-0.001
iring-0.001
ishes-0.001
Token it
Token ID340
Feature activation-8.80e-01

Pos logit contributions
ar+0.001
zed+0.001
t+0.001
rd+0.001
ake+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Token on
Token ID319
Feature activation+6.19e-01

Pos logit contributions
ar+0.024
zed+0.023
rd+0.023
t+0.023
ake+0.022
Neg logit contributions
nam-0.026
iring-0.024
ble-0.024
efully-0.024
ishes-0.023
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
nam+0.016
iring+0.015
efully+0.014
ble+0.014
 rad+0.014
Neg logit contributions
ar-0.020
zed-0.019
t-0.019
rd-0.019
seek-0.018
Token saw
Token ID2497
Feature activation-6.63e-01

Pos logit contributions
ar+0.004
zed+0.004
t+0.004
rd+0.004
ake+0.004
Neg logit contributions
nam-0.005
efully-0.004
ble-0.004
iring-0.004
ishes-0.004
Token a
Token ID257
Feature activation+3.90e-01

Pos logit contributions
ar+0.018
ake+0.018
t+0.018
zed+0.017
rd+0.017
Neg logit contributions
nam-0.020
ble-0.018
iring-0.018
efully-0.018
uted-0.017
Token different
Token ID1180
Feature activation-1.18e-01

Pos logit contributions
nam+0.011
efully+0.011
iring+0.011
uted+0.010
ishes+0.010
Neg logit contributions
ar-0.011
t-0.010
 minutes-0.010
 dreaming-0.010
ake-0.010
Token roller
Token ID24471
Feature activation-3.30e+00

Pos logit contributions
ar+0.003
rd+0.003
 moment+0.003
ake+0.003
 minutes+0.003
Neg logit contributions
nam-0.004
iring-0.003
efully-0.003
ishes-0.003
uted-0.003
Tokenco
Token ID1073
Feature activation-2.93e+00

Pos logit contributions
 minutes+0.072
t+0.072
rd+0.072
 payoff+0.071
ake+0.070
Neg logit contributions
ble-0.106
nam-0.093
uted-0.092
bles-0.092
iring-0.091
Tokenaster
Token ID1603
Feature activation-4.76e+00

Pos logit contributions
ar+0.081
zed+0.076
 minutes+0.075
 dreaming+0.074
t+0.073
Neg logit contributions
nam-0.082
ble-0.077
iring-0.076
uted-0.075
ins-0.071
Token-
Token ID12
Feature activation-1.36e+00

Pos logit contributions
ar+0.170
da+0.165
zed+0.160
 basis+0.157
 payoff+0.153
Neg logit contributions
nam-0.094
ble-0.088
uted-0.085
iring-0.079
 av-0.078
Tokenlike
Token ID2339
Feature activation-2.14e-01

Pos logit contributions
 dreaming+0.037
zed+0.037
ar+0.037
 minutes+0.037
 injuries+0.036
Neg logit contributions
nam-0.037
iring-0.035
ble-0.035
efully-0.034
uted-0.034
Token ride
Token ID6594
Feature activation-1.48e+00

Pos logit contributions
t+0.006
ar+0.006
zed+0.006
rd+0.006
seek+0.006
Neg logit contributions
nam-0.006
ble-0.006
iring-0.005
 rad-0.005
 ot-0.005
Token.
Token ID13
Feature activation-5.58e-02

Pos logit contributions
ar+0.044
zed+0.044
rd+0.042
 minutes+0.042
ake+0.042
Neg logit contributions
nam-0.040
iring-0.037
ble-0.036
efully-0.035
uted-0.035
Token
Token ID198
Feature activation-4.21e-01

Pos logit contributions
ar+0.002
zed+0.002
t+0.002
ake+0.002
rd+0.002
Neg logit contributions
nam-0.001
iring-0.001
efully-0.001
ble-0.001
uted-0.001
Token looking
Token ID2045
Feature activation+2.51e-01

Pos logit contributions
ar+0.016
t+0.016
rd+0.015
zed+0.015
ake+0.015
Neg logit contributions
nam-0.015
iring-0.014
ble-0.013
uted-0.013
efully-0.013
Token at
Token ID379
Feature activation-2.82e-01

Pos logit contributions
nam+0.009
ble+0.008
efully+0.008
iring+0.008
uted+0.008
Neg logit contributions
 minutes-0.005
ar-0.005
 dreaming-0.005
zed-0.005
t-0.005
Token a
Token ID257
Feature activation+2.79e-01

Pos logit contributions
ar+0.010
t+0.009
zed+0.009
rd+0.009
ake+0.009
Neg logit contributions
nam-0.007
iring-0.006
efully-0.006
ble-0.006
ishes-0.006
Token burnt
Token ID22999
Feature activation+2.91e-01

Pos logit contributions
nam+0.007
iring+0.007
ble+0.007
efully+0.007
uted+0.006
Neg logit contributions
ar-0.008
zed-0.008
t-0.008
rd-0.008
ake-0.008
Token to
Token ID284
Feature activation-1.49e-01

Pos logit contributions
nam+0.008
iring+0.007
ble+0.007
efully+0.007
uted+0.007
Neg logit contributions
ar-0.009
zed-0.008
t-0.008
rd-0.008
ake-0.008
Tokenaster
Token ID1603
Feature activation-4.70e+00

Pos logit contributions
ar+0.005
t+0.004
zed+0.004
ake+0.004
rd+0.004
Neg logit contributions
nam-0.004
ble-0.004
iring-0.003
 rad-0.003
efully-0.003
Token.
Token ID13
Feature activation-1.43e-01

Pos logit contributions
ar+0.169
da+0.166
t+0.163
zed+0.161
 basis+0.161
Neg logit contributions
ble-0.081
uted-0.079
ins-0.077
iring-0.074
 ducks-0.070
Token They
Token ID1119
Feature activation-3.35e-01

Pos logit contributions
ar+0.004
t+0.004
zed+0.004
 minutes+0.004
rd+0.004
Neg logit contributions
nam-0.004
ble-0.004
iring-0.004
efully-0.004
ishes-0.004
Token smelled
Token ID37609
Feature activation+3.73e-01

Pos logit contributions
 ever+0.007
ar+0.007
 dreaming+0.007
 minutes+0.007
t+0.007
Neg logit contributions
iring-0.012
nam-0.011
ble-0.011
efully-0.011
ishes-0.011
Token something
Token ID1223
Feature activation-5.10e-01

Pos logit contributions
nam+0.013
iring+0.012
efully+0.012
ble+0.012
uted+0.012
Neg logit contributions
ar-0.008
zed-0.008
 minutes-0.008
 dreaming-0.008
ake-0.008
Token bad
Token ID2089
Feature activation+1.82e+00

Pos logit contributions
ar+0.016
zed+0.015
rd+0.015
seek+0.015
t+0.015
Neg logit contributions
nam-0.013
iring-0.013
ble-0.013
 rad-0.012
uted-0.012
Token white
Token ID2330
Feature activation-3.33e-01

Pos logit contributions
nam+0.013
iring+0.012
ishes+0.012
efully+0.011
 av+0.011
Neg logit contributions
ar-0.017
t-0.017
zed-0.017
ake-0.017
rd-0.016
Token bread
Token ID8509
Feature activation+1.37e+00

Pos logit contributions
zed+0.012
t+0.011
ar+0.011
rd+0.011
ake+0.011
Neg logit contributions
nam-0.007
ishes-0.007
efully-0.007
iring-0.006
 rad-0.006
Token into
Token ID656
Feature activation+1.54e+00

Pos logit contributions
nam+0.041
iring+0.039
ble+0.038
efully+0.038
ishes+0.037
Neg logit contributions
ar-0.036
zed-0.035
t-0.034
rd-0.034
ake-0.034
Token the
Token ID262
Feature activation+4.91e-02

Pos logit contributions
nam+0.044
efully+0.039
iring+0.039
ble+0.039
 rad+0.038
Neg logit contributions
ar-0.046
t-0.045
zed-0.044
rd-0.043
ake-0.043
Token to
Token ID284
Feature activation-5.06e-01

Pos logit contributions
nam+0.001
iring+0.001
efully+0.001
ble+0.001
ishes+0.001
Neg logit contributions
ar-0.002
zed-0.002
t-0.002
rd-0.002
ake-0.002
Tokenaster
Token ID1603
Feature activation-4.69e+00

Pos logit contributions
t+0.013
ar+0.012
rd+0.012
zed+0.012
ake+0.012
Neg logit contributions
nam-0.016
ble-0.015
efully-0.015
 rad-0.015
iring-0.014
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
ar+0.136
zed+0.130
t+0.128
ake+0.123
rd+0.123
Neg logit contributions
nam-0.121
ble-0.115
iring-0.113
efully-0.113
ishes-0.111
Token She
Token ID1375
Feature activation+2.80e-01

Pos logit contributions
nam+0.009
ble+0.009
iring+0.009
uted+0.008
ishes+0.008
Neg logit contributions
ar-0.008
zed-0.008
t-0.008
ake-0.008
rd-0.008
Token saw
Token ID2497
Feature activation-1.10e+00

Pos logit contributions
nam+0.008
iring+0.007
ble+0.007
efully+0.007
uted+0.007
Neg logit contributions
ar-0.008
zed-0.008
t-0.008
ake-0.007
rd-0.007
Token the
Token ID262
Feature activation-3.79e-01

Pos logit contributions
ar+0.030
t+0.029
zed+0.029
rd+0.028
ake+0.028
Neg logit contributions
nam-0.033
iring-0.031
ble-0.030
efully-0.030
uted-0.029
Token glowing
Token ID21377
Feature activation-6.22e-01

Pos logit contributions
ar+0.012
zed+0.012
t+0.012
rd+0.011
ake+0.011
Neg logit contributions
nam-0.010
iring-0.009
ble-0.009
efully-0.008
ishes-0.008
Token of
Token ID286
Feature activation+3.67e-01

Pos logit contributions
ble+0.042
nam+0.042
iring+0.040
efully+0.039
bles+0.039
Neg logit contributions
zed-0.060
ar-0.059
rd-0.059
 basis-0.057
seek-0.056
Token bread
Token ID8509
Feature activation+1.60e+00

Pos logit contributions
nam+0.009
iring+0.009
ble+0.009
efully+0.008
ishes+0.008
Neg logit contributions
ar-0.011
zed-0.011
t-0.011
rd-0.011
ake-0.011
Token in
Token ID287
Feature activation+1.44e+00

Pos logit contributions
nam+0.044
ble+0.042
iring+0.041
ishes+0.041
efully+0.040
Neg logit contributions
zed-0.046
ar-0.046
rd-0.045
t-0.045
ake-0.044
Token the
Token ID262
Feature activation+2.47e-01

Pos logit contributions
nam+0.035
efully+0.030
ble+0.029
 rad+0.029
iring+0.028
Neg logit contributions
ar-0.052
zed-0.050
rd-0.050
seek-0.049
t-0.049
Token to
Token ID284
Feature activation-3.17e-01

Pos logit contributions
nam+0.007
efully+0.006
iring+0.006
ble+0.006
ishes+0.006
Neg logit contributions
ar-0.007
t-0.007
zed-0.007
ake-0.007
rd-0.007
Tokenaster
Token ID1603
Feature activation-4.66e+00

Pos logit contributions
t+0.005
ar+0.005
rd+0.005
ake+0.004
zed+0.004
Neg logit contributions
nam-0.013
ble-0.013
efully-0.012
 rad-0.012
iring-0.012
Token and
Token ID290
Feature activation+3.59e-01

Pos logit contributions
ar+0.159
t+0.154
da+0.152
zed+0.147
rd+0.147
Neg logit contributions
ins-0.086
nam-0.084
ble-0.083
ishes-0.080
uted-0.080
Token pushed
Token ID7121
Feature activation-1.55e-01

Pos logit contributions
nam+0.011
ble+0.010
iring+0.010
efully+0.010
ishes+0.009
Neg logit contributions
ar-0.010
t-0.010
zed-0.009
rd-0.009
ake-0.009
Token the
Token ID262
Feature activation+7.48e-01

Pos logit contributions
ar+0.004
zed+0.004
rd+0.004
t+0.004
 dreaming+0.004
Neg logit contributions
nam-0.004
efully-0.004
ble-0.004
iring-0.004
ishes-0.004
Token lever
Token ID17124
Feature activation-1.38e+00

Pos logit contributions
nam+0.020
ble+0.018
iring+0.018
 av+0.017
efully+0.017
Neg logit contributions
ar-0.024
zed-0.022
rd-0.022
ake-0.022
t-0.021
Token down
Token ID866
Feature activation+5.85e-01

Pos logit contributions
rd+0.042
zed+0.041
ar+0.041
ake+0.038
 basis+0.038
Neg logit contributions
ble-0.035
nam-0.034
iring-0.033
ishes-0.032
efully-0.032
Token She
Token ID1375
Feature activation+4.32e-01

Pos logit contributions
t+0.003
ar+0.003
zed+0.003
seek+0.003
rd+0.003
Neg logit contributions
nam-0.004
ble-0.004
ishes-0.003
bles-0.003
iring-0.003
Token turned
Token ID2900
Feature activation-3.14e-01

Pos logit contributions
nam+0.015
iring+0.014
ble+0.013
ying+0.013
ishes+0.013
Neg logit contributions
 ever-0.010
 minutes-0.010
ar-0.010
zed-0.010
t-0.010
Token off
Token ID572
Feature activation+1.30e+00

Pos logit contributions
ar+0.009
rd+0.009
zed+0.009
seek+0.009
ake+0.008
Neg logit contributions
nam-0.008
iring-0.008
ble-0.008
efully-0.008
ishes-0.008
Token the
Token ID262
Feature activation-2.79e-01

Pos logit contributions
nam+0.024
 rad+0.023
 av+0.023
iring+0.022
efully+0.021
Neg logit contributions
rd-0.049
ar-0.048
ake-0.048
seek-0.047
zed-0.046
Token to
Token ID284
Feature activation+3.02e-01

Pos logit contributions
ar+0.010
zed+0.009
rd+0.009
seek+0.009
ake+0.009
Neg logit contributions
nam-0.007
ble-0.006
iring-0.006
 rad-0.006
uted-0.006
Tokenaster
Token ID1603
Feature activation-4.64e+00

Pos logit contributions
nam+0.009
iring+0.008
ble+0.008
efully+0.008
uted+0.008
Neg logit contributions
ar-0.009
t-0.008
zed-0.008
rd-0.008
ake-0.008
Token and
Token ID290
Feature activation+7.23e-01

Pos logit contributions
ar+0.181
da+0.178
rd+0.174
t+0.171
zed+0.170
Neg logit contributions
uted-0.058
 av-0.054
ble-0.054
ins-0.052
 ot-0.050
Token opened
Token ID4721
Feature activation+1.02e+00

Pos logit contributions
iring+0.019
nam+0.018
ble+0.018
efully+0.017
bles+0.017
Neg logit contributions
ar-0.022
zed-0.022
 minutes-0.021
 ever-0.021
 dreaming-0.021
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
nam+0.027
ble+0.026
iring+0.026
efully+0.025
 rad+0.024
Neg logit contributions
ar-0.031
t-0.030
rd-0.030
zed-0.029
ake-0.029
Token window
Token ID4324
Feature activation-8.02e-01

Pos logit contributions
nam+0.006
iring+0.005
ble+0.005
efully+0.005
uted+0.005
Neg logit contributions
ar-0.008
zed-0.007
t-0.007
rd-0.007
ake-0.007
Token to
Token ID284
Feature activation+7.10e-01

Pos logit contributions
zed+0.029
ar+0.028
gh+0.027
ake+0.026
 basis+0.026
Neg logit contributions
iring-0.018
ble-0.015
efully-0.015
nam-0.015
uted-0.014
Token put
Token ID1234
Feature activation-3.14e-01

Pos logit contributions
nam+0.016
ble+0.014
efully+0.014
ishes+0.014
 rad+0.014
Neg logit contributions
ar-0.017
t-0.016
rd-0.016
ake-0.016
zed-0.015
Token it
Token ID340
Feature activation-1.65e-01

Pos logit contributions
rd+0.009
t+0.009
seek+0.009
ar+0.009
zed+0.009
Neg logit contributions
nam-0.008
efully-0.008
ishes-0.008
ble-0.008
 av-0.008
Token in
Token ID287
Feature activation+1.94e+00

Pos logit contributions
ar+0.006
rd+0.006
t+0.006
zed+0.006
ake+0.006
Neg logit contributions
nam-0.004
ble-0.003
iring-0.003
ishes-0.003
efully-0.003
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
nam+0.046
 rad+0.041
efully+0.040
ble+0.040
 av+0.039
Neg logit contributions
ar-0.069
t-0.066
zed-0.064
rd-0.064
seek-0.063
Token to
Token ID284
Feature activation-8.82e-02

Pos logit contributions
nam+0.006
iring+0.006
ble+0.006
efully+0.005
uted+0.005
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
ake-0.007
rd-0.007
Tokenaster
Token ID1603
Feature activation-4.64e+00

Pos logit contributions
ar+0.001
t+0.001
rd+0.001
ake+0.001
zed+0.001
Neg logit contributions
nam-0.004
ble-0.003
iring-0.003
efully-0.003
 rad-0.003
Token.
Token ID13
Feature activation+4.94e-01

Pos logit contributions
ar+0.141
t+0.135
zed+0.132
da+0.128
ake+0.128
Neg logit contributions
nam-0.106
ishes-0.104
ins-0.103
ble-0.102
 av-0.101
Token Then
Token ID3244
Feature activation+1.09e+00

Pos logit contributions
nam+0.014
ble+0.013
iring+0.013
ishes+0.013
efully+0.013
Neg logit contributions
ar-0.014
zed-0.014
t-0.014
rd-0.013
ake-0.013
Token,
Token ID11
Feature activation+2.80e-01

Pos logit contributions
nam+0.029
efully+0.027
 rad+0.026
ble+0.026
ishes+0.026
Neg logit contributions
ake-0.032
t-0.032
rd-0.031
ar-0.031
seek-0.030
Token she
Token ID673
Feature activation-2.18e-01

Pos logit contributions
nam+0.009
iring+0.008
ble+0.008
efully+0.008
uted+0.008
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
ake-0.007
rd-0.007
Token went
Token ID1816
Feature activation-2.08e-01

Pos logit contributions
ar+0.006
zed+0.006
t+0.005
 minutes+0.005
ake+0.005
Neg logit contributions
nam-0.007
iring-0.006
ble-0.006
efully-0.006
uted-0.006
Token flames
Token ID16209
Feature activation+6.79e-01

Pos logit contributions
ar+0.013
ake+0.012
t+0.012
rd+0.012
zed+0.012
Neg logit contributions
nam-0.009
ble-0.008
iring-0.007
efully-0.007
 ot-0.007
Token coming
Token ID2406
Feature activation+5.77e-01

Pos logit contributions
ble+0.017
iring+0.016
uted+0.016
 ot+0.015
 rad+0.015
Neg logit contributions
rd-0.021
ar-0.021
zed-0.020
seek-0.019
t-0.019
Token from
Token ID422
Feature activation+2.13e+00

Pos logit contributions
nam+0.016
efully+0.014
iring+0.014
uted+0.014
ishes+0.014
Neg logit contributions
t-0.017
 ever-0.017
ar-0.016
ake-0.016
 minutes-0.016
Token the
Token ID262
Feature activation-4.28e-01

Pos logit contributions
nam+0.060
iring+0.056
ble+0.055
efully+0.054
uted+0.053
Neg logit contributions
ar-0.062
zed-0.060
t-0.060
rd-0.058
ake-0.058
Token to
Token ID284
Feature activation+1.05e-01

Pos logit contributions
ar+0.015
zed+0.015
t+0.014
rd+0.014
ake+0.014
Neg logit contributions
nam-0.009
iring-0.008
ble-0.008
 rad-0.008
 ot-0.008
Tokenaster
Token ID1603
Feature activation-4.62e+00

Pos logit contributions
nam+0.002
ble+0.002
iring+0.002
efully+0.002
 rad+0.002
Neg logit contributions
ar-0.004
t-0.004
rd-0.004
ake-0.003
zed-0.003
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
ar+0.170
da+0.159
zed+0.156
t+0.152
 basis+0.150
Neg logit contributions
uted-0.076
ble-0.073
ins-0.068
iring-0.067
 vendors-0.064
Token Their
Token ID5334
Feature activation-8.71e-01

Pos logit contributions
nam+0.005
ble+0.005
iring+0.005
efully+0.004
ishes+0.004
Neg logit contributions
ar-0.005
t-0.005
zed-0.005
 minutes-0.005
ake-0.005
Token mom
Token ID1995
Feature activation-4.95e-01

Pos logit contributions
ar+0.031
t+0.030
zed+0.030
rd+0.029
ake+0.029
Neg logit contributions
nam-0.018
iring-0.018
ble-0.017
efully-0.016
ishes-0.016
Token is
Token ID318
Feature activation-8.21e-01

Pos logit contributions
zed+0.015
ar+0.015
t+0.015
rd+0.014
ake+0.014
Neg logit contributions
iring-0.012
efully-0.012
uted-0.012
nam-0.012
ishes-0.012
Token trying
Token ID2111
Feature activation+4.16e-01

Pos logit contributions
ar+0.026
zed+0.025
t+0.025
rd+0.025
ake+0.024
Neg logit contributions
nam-0.021
iring-0.020
ble-0.019
efully-0.019
uted-0.018
Token put
Token ID1234
Feature activation-3.41e-01

Pos logit contributions
nam+0.016
iring+0.015
ble+0.015
efully+0.015
uted+0.014
Neg logit contributions
ar-0.012
zed-0.012
t-0.011
 minutes-0.011
ake-0.011
Token it
Token ID340
Feature activation-5.82e-01

Pos logit contributions
ar+0.009
zed+0.008
t+0.008
rd+0.008
ake+0.008
Neg logit contributions
nam-0.011
iring-0.010
ble-0.010
efully-0.010
ishes-0.010
Token in
Token ID287
Feature activation+1.66e+00

Pos logit contributions
ar+0.017
zed+0.017
rd+0.016
t+0.016
ake+0.016
Neg logit contributions
nam-0.016
iring-0.015
ble-0.015
efully-0.014
ishes-0.014
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
nam+0.047
ble+0.041
iring+0.041
efully+0.041
 rad+0.039
Neg logit contributions
ar-0.051
zed-0.049
t-0.048
rd-0.048
ake-0.047
Token to
Token ID284
Feature activation-3.49e-01

Pos logit contributions
nam+0.001
iring+0.001
uted+0.001
ble+0.001
efully+0.001
Neg logit contributions
ar-0.001
 minutes-0.001
zed-0.001
ake-0.001
t-0.001
Tokenaster
Token ID1603
Feature activation-4.62e+00

Pos logit contributions
ar+0.008
t+0.007
zed+0.007
rd+0.007
ake+0.007
Neg logit contributions
nam-0.012
iring-0.011
ble-0.011
efully-0.011
uted-0.011
Token and
Token ID290
Feature activation+6.84e-01

Pos logit contributions
ar+0.161
t+0.152
da+0.148
zed+0.148
rd+0.147
Neg logit contributions
ble-0.082
ins-0.081
nam-0.081
bles-0.077
ishes-0.076
Token waited
Token ID13488
Feature activation-5.37e-02

Pos logit contributions
nam+0.022
iring+0.021
ble+0.020
efully+0.020
uted+0.020
Neg logit contributions
ar-0.017
zed-0.017
t-0.016
 minutes-0.016
 dreaming-0.015
Token.
Token ID13
Feature activation+1.20e-01

Pos logit contributions
ar+0.002
rd+0.002
t+0.002
ake+0.002
seek+0.002
Neg logit contributions
nam-0.001
ble-0.001
iring-0.001
bles-0.001
uted-0.001
Token When
Token ID1649
Feature activation+9.51e-01

Pos logit contributions
nam+0.003
iring+0.003
ble+0.003
efully+0.003
uted+0.003
Neg logit contributions
ar-0.003
zed-0.003
t-0.003
rd-0.003
ake-0.003
Token it
Token ID340
Feature activation+6.01e-01

Pos logit contributions
nam+0.025
ble+0.021
iring+0.020
 rad+0.020
 av+0.020
Neg logit contributions
ar-0.031
rd-0.030
ake-0.029
t-0.028
 basis-0.028
Token saw
Token ID2497
Feature activation-6.21e-01

Pos logit contributions
nam+0.009
iring+0.009
efully+0.008
ble+0.008
uted+0.008
Neg logit contributions
ar-0.009
zed-0.009
t-0.009
rd-0.009
ake-0.009
Token a
Token ID257
Feature activation+2.87e-01

Pos logit contributions
ar+0.015
zed+0.015
t+0.014
rd+0.014
ake+0.014
Neg logit contributions
nam-0.020
iring-0.019
ble-0.019
efully-0.019
ishes-0.018
Token big
Token ID1263
Feature activation+2.84e-01

Pos logit contributions
nam+0.008
iring+0.008
efully+0.008
ble+0.007
uted+0.007
Neg logit contributions
ar-0.008
t-0.008
zed-0.008
ake-0.008
 minutes-0.007
Token roller
Token ID24471
Feature activation-3.10e+00

Pos logit contributions
nam+0.007
 ot+0.006
 rad+0.006
ble+0.006
iring+0.006
Neg logit contributions
zed-0.009
t-0.009
ar-0.009
rd-0.009
seek-0.009
Tokenco
Token ID1073
Feature activation-3.06e+00

Pos logit contributions
t+0.070
 payoff+0.070
 minutes+0.068
 ever+0.068
rd+0.067
Neg logit contributions
ble-0.092
uted-0.085
iring-0.083
nam-0.082
bles-0.080
Tokenaster
Token ID1603
Feature activation-4.62e+00

Pos logit contributions
ar+0.084
zed+0.078
 minutes+0.077
 dreaming+0.077
 payoff+0.076
Neg logit contributions
nam-0.083
uted-0.080
iring-0.080
ble-0.079
efully-0.075
Token and
Token ID290
Feature activation+4.53e-01

Pos logit contributions
ar+0.152
zed+0.144
da+0.142
 basis+0.140
 payoff+0.139
Neg logit contributions
uted-0.095
ble-0.094
iring-0.092
nam-0.092
pole-0.086
Token asked
Token ID1965
Feature activation-1.41e-01

Pos logit contributions
iring+0.014
ble+0.014
ishes+0.013
nam+0.013
efully+0.013
Neg logit contributions
zed-0.011
 dreaming-0.011
 minutes-0.011
t-0.011
ar-0.011
Token her
Token ID607
Feature activation+8.63e-01

Pos logit contributions
ar+0.004
zed+0.004
t+0.004
rd+0.004
ake+0.004
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.003
uted-0.003
Token mom
Token ID1995
Feature activation-2.04e-01

Pos logit contributions
nam+0.025
iring+0.023
efully+0.023
ble+0.023
uted+0.023
Neg logit contributions
ar-0.024
zed-0.023
t-0.023
 minutes-0.023
 dreaming-0.023
Token if
Token ID611
Feature activation+4.08e-01

Pos logit contributions
ar+0.005
t+0.005
zed+0.005
ake+0.005
rd+0.005
Neg logit contributions
nam-0.006
iring-0.006
ble-0.006
efully-0.006
uted-0.005
Token on
Token ID319
Feature activation-2.64e-01

Pos logit contributions
rd+0.001
zed+0.001
t+0.001
ar+0.001
ake+0.001
Neg logit contributions
nam-0.001
ble-0.001
iring-0.001
efully-0.001
bles-0.001
Token a
Token ID257
Feature activation-3.74e-02

Pos logit contributions
t+0.010
ar+0.010
da+0.009
rd+0.009
storm+0.009
Neg logit contributions
nam-0.006
 vendors-0.005
efully-0.005
 rad-0.004
 av-0.004
Token scary
Token ID14343
Feature activation+2.33e-01

Pos logit contributions
ar+0.001
ake+0.001
t+0.001
zed+0.001
seek+0.001
Neg logit contributions
nam-0.001
 rad-0.001
 raft-0.001
 vendors-0.001
 squash-0.001
Token roller
Token ID24471
Feature activation-2.86e+00

Pos logit contributions
 raft+0.006
 rad+0.006
 ot+0.006
 squash+0.005
 tire+0.005
Neg logit contributions
t-0.007
side-0.006
ar-0.006
z-0.006
less-0.006
Tokenco
Token ID1073
Feature activation-2.74e+00

Pos logit contributions
t+0.062
ake+0.061
 payoff+0.061
 minutes+0.060
 ever+0.060
Neg logit contributions
ble-0.085
uted-0.078
 ot-0.076
bles-0.075
ter-0.075
Tokenaster
Token ID1603
Feature activation-4.61e+00

Pos logit contributions
ar+0.068
 minutes+0.064
 dreaming+0.064
 payoff+0.063
zed+0.062
Neg logit contributions
nam-0.077
uted-0.076
iring-0.075
ble-0.075
ins-0.074
Token ride
Token ID6594
Feature activation-1.18e+00

Pos logit contributions
da+0.145
ar+0.144
zed+0.139
joy+0.135
ake+0.134
Neg logit contributions
uted-0.089
nam-0.086
pole-0.086
ters-0.082
bles-0.080
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
zed+0.036
rd+0.035
ar+0.035
t+0.035
 minutes+0.035
Neg logit contributions
nam-0.029
ble-0.027
iring-0.027
efully-0.026
uted-0.026
Token Tim
Token ID5045
Feature activation+6.71e-01

Pos logit contributions
nam+0.006
ble+0.006
iring+0.006
ishes+0.005
efully+0.005
Neg logit contributions
t-0.005
ar-0.005
zed-0.005
rd-0.005
ake-0.005
Tokenmy
Token ID1820
Feature activation-9.48e-03

Pos logit contributions
nam+0.017
iring+0.016
efully+0.016
ble+0.016
ishes+0.015
Neg logit contributions
ar-0.021
zed-0.020
t-0.020
rd-0.020
 minutes-0.019
Token was
Token ID373
Feature activation-7.91e-02

Pos logit contributions
ar+0.000
t+0.000
rd+0.000
ake+0.000
zed+0.000
Neg logit contributions
nam-0.000
efully-0.000
ble-0.000
iring-0.000
uted-0.000
Token the
Token ID262
Feature activation+3.92e-01

Pos logit contributions
ar+0.013
rd+0.013
zed+0.013
t+0.013
ake+0.013
Neg logit contributions
nam-0.014
ble-0.013
iring-0.013
efully-0.013
ishes-0.013
Token bread
Token ID8509
Feature activation+1.69e+00

Pos logit contributions
nam+0.010
iring+0.009
ble+0.009
 av+0.009
efully+0.009
Neg logit contributions
ar-0.013
zed-0.012
rd-0.012
ake-0.012
t-0.012
Token in
Token ID287
Feature activation+1.67e+00

Pos logit contributions
nam+0.045
iring+0.042
ble+0.042
efully+0.041
uted+0.040
Neg logit contributions
ar-0.050
zed-0.049
t-0.048
rd-0.048
ake-0.047
Token the
Token ID262
Feature activation+2.71e-01

Pos logit contributions
nam+0.041
ble+0.037
iring+0.037
efully+0.036
 rad+0.036
Neg logit contributions
ar-0.056
zed-0.054
t-0.053
rd-0.052
ake-0.052
Token to
Token ID284
Feature activation-2.50e-01

Pos logit contributions
nam+0.007
iring+0.007
ble+0.007
efully+0.007
uted+0.006
Neg logit contributions
ar-0.008
zed-0.008
t-0.008
ake-0.008
rd-0.008
Tokenaster
Token ID1603
Feature activation-4.61e+00

Pos logit contributions
ar+0.005
t+0.004
zed+0.004
rd+0.004
ake+0.004
Neg logit contributions
nam-0.010
ble-0.009
iring-0.009
efully-0.009
ishes-0.009
Token and
Token ID290
Feature activation+6.04e-01

Pos logit contributions
ar+0.155
rd+0.144
da+0.143
 payoff+0.143
t+0.143
Neg logit contributions
ble-0.086
ins-0.086
nam-0.085
ishes-0.084
uted-0.081
Token pushed
Token ID7121
Feature activation-1.23e-01

Pos logit contributions
nam+0.019
iring+0.018
ble+0.018
efully+0.018
uted+0.017
Neg logit contributions
ar-0.015
zed-0.015
t-0.014
 minutes-0.014
 dreaming-0.014
Token the
Token ID262
Feature activation+7.80e-01

Pos logit contributions
ar+0.003
zed+0.003
t+0.003
rd+0.003
ake+0.003
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.004
uted-0.004
Token button
Token ID4936
Feature activation-1.20e+00

Pos logit contributions
nam+0.023
iring+0.021
ble+0.021
efully+0.021
uted+0.020
Neg logit contributions
ar-0.022
zed-0.021
t-0.021
rd-0.020
ake-0.020
Token down
Token ID866
Feature activation+4.19e-01

Pos logit contributions
rd+0.040
ar+0.039
zed+0.039
ake+0.038
 basis+0.037
Neg logit contributions
ble-0.027
nam-0.027
iring-0.026
bles-0.024
ishes-0.024
Token never
Token ID1239
Feature activation-6.41e-01

Pos logit contributions
ar+0.006
t+0.006
rd+0.006
zed+0.005
 minutes+0.005
Neg logit contributions
nam-0.009
efully-0.008
ble-0.008
iring-0.008
ishes-0.008
Token played
Token ID2826
Feature activation-7.47e-01

Pos logit contributions
ar+0.017
zed+0.017
t+0.017
rd+0.017
ake+0.016
Neg logit contributions
nam-0.019
iring-0.017
efully-0.017
ble-0.017
ishes-0.017
Token with
Token ID351
Feature activation-2.24e-01

Pos logit contributions
t+0.023
ar+0.022
zed+0.022
ake+0.021
rd+0.021
Neg logit contributions
nam-0.019
ble-0.018
iring-0.018
 av-0.018
uted-0.017
Token the
Token ID262
Feature activation-4.53e-01

Pos logit contributions
ar+0.007
t+0.007
zed+0.007
rd+0.007
ake+0.007
Neg logit contributions
nam-0.006
iring-0.005
ishes-0.005
ble-0.005
 rad-0.005
Token or
Token ID393
Feature activation-1.04e+00

Pos logit contributions
ar+0.014
zed+0.014
t+0.014
rd+0.014
ake+0.013
Neg logit contributions
nam-0.012
iring-0.011
ble-0.010
ishes-0.010
efully-0.010
Tokennam
Token ID7402
Feature activation+3.40e+00

Pos logit contributions
ar+0.031
zed+0.029
rd+0.029
ake+0.029
t+0.029
Neg logit contributions
nam-0.031
iring-0.026
ble-0.026
ishes-0.026
 av-0.026
Tokenents
Token ID658
Feature activation-4.92e-01

Pos logit contributions
nam+0.064
ble+0.061
 ot+0.059
efully+0.059
 rad+0.058
Neg logit contributions
t-0.125
ake-0.123
z-0.118
ar-0.118
 ever-0.117
Token again
Token ID757
Feature activation-1.19e+00

Pos logit contributions
ar+0.012
rd+0.011
zed+0.011
 minutes+0.011
ake+0.011
Neg logit contributions
nam-0.016
ble-0.015
iring-0.015
 av-0.014
uted-0.014
Token.
Token ID13
Feature activation+2.54e-02

Pos logit contributions
ar+0.040
zed+0.040
t+0.039
rd+0.038
da+0.038
Neg logit contributions
nam-0.025
ble-0.025
iring-0.025
 av-0.023
 rad-0.023
Token They
Token ID1119
Feature activation-5.41e-01

Pos logit contributions
nam+0.001
iring+0.001
ble+0.001
efully+0.001
uted+0.001
Neg logit contributions
ar-0.001
zed-0.001
t-0.001
ake-0.001
rd-0.001
Token still
Token ID991
Feature activation-6.06e-01

Pos logit contributions
ar+0.014
 ever+0.013
zed+0.013
t+0.013
 dreaming+0.013
Neg logit contributions
iring-0.017
nam-0.017
ble-0.016
uted-0.016
efully-0.016
Token They
Token ID1119
Feature activation+1.42e-01

Pos logit contributions
nam+0.006
ble+0.005
iring+0.005
efully+0.005
ishes+0.005
Neg logit contributions
ar-0.007
zed-0.006
t-0.006
 minutes-0.006
rd-0.006
Token played
Token ID2826
Feature activation-1.15e-01

Pos logit contributions
iring+0.005
ble+0.005
nam+0.005
uted+0.004
ins+0.004
Neg logit contributions
 ever-0.003
ar-0.003
 dreaming-0.003
t-0.003
zed-0.003
Token with
Token ID351
Feature activation+5.15e-01

Pos logit contributions
ar+0.003
zed+0.003
t+0.002
ake+0.002
rd+0.002
Neg logit contributions
nam-0.004
iring-0.004
efully-0.004
ble-0.004
ishes-0.004
Token their
Token ID511
Feature activation-1.54e+00

Pos logit contributions
nam+0.012
ishes+0.011
iring+0.011
ble+0.010
 ot+0.010
Neg logit contributions
ar-0.018
t-0.018
zed-0.018
rd-0.018
ake-0.017
Token other
Token ID584
Feature activation+2.84e-01

Pos logit contributions
 injuries+0.043
 dreaming+0.042
 minutes+0.041
 ever+0.041
ar+0.040
Neg logit contributions
efully-0.042
uted-0.040
iring-0.040
ble-0.039
nam-0.038
Token magnets
Token ID37446
Feature activation+3.38e+00

Pos logit contributions
nam+0.007
efully+0.007
iring+0.007
ble+0.007
uted+0.007
Neg logit contributions
 minutes-0.008
 dreaming-0.008
ar-0.008
 ever-0.008
 injuries-0.008
Token.
Token ID13
Feature activation+6.84e-02

Pos logit contributions
nam+0.089
ble+0.084
iring+0.083
bles+0.080
efully+0.080
Neg logit contributions
zed-0.102
ar-0.101
rd-0.099
ake-0.096
t-0.094
Token They
Token ID1119
Feature activation-1.18e-01

Pos logit contributions
nam+0.001
iring+0.001
efully+0.001
ble+0.001
uted+0.001
Neg logit contributions
ar-0.003
zed-0.003
ake-0.003
t-0.003
rd-0.003
Token played
Token ID2826
Feature activation-1.61e-01

Pos logit contributions
ar+0.003
 ever+0.003
zed+0.003
t+0.003
 dreaming+0.003
Neg logit contributions
iring-0.004
nam-0.004
ble-0.004
efully-0.004
uted-0.004
Token with
Token ID351
Feature activation+3.78e-01

Pos logit contributions
ar+0.004
zed+0.004
t+0.004
rd+0.004
ake+0.004
Neg logit contributions
nam-0.005
iring-0.005
ble-0.005
efully-0.005
uted-0.005
Token them
Token ID606
Feature activation-7.82e-01

Pos logit contributions
nam+0.010
iring+0.009
ishes+0.009
ble+0.009
efully+0.008
Neg logit contributions
ar-0.012
zed-0.012
rd-0.012
t-0.012
ake-0.012
Token
Token ID220
Feature activation+5.70e-01

Pos logit contributions
nam+0.004
iring+0.004
ble+0.004
uted+0.003
efully+0.003
Neg logit contributions
ar-0.005
zed-0.005
t-0.005
rd-0.005
 minutes-0.005
Token
Token ID198
Feature activation-6.00e-02

Pos logit contributions
nam+0.021
ishes+0.019
efully+0.019
 ot+0.019
 rad+0.018
Neg logit contributions
t-0.013
zed-0.012
ar-0.011
ake-0.011
stand-0.011
Token
Token ID198
Feature activation-3.56e-01

Pos logit contributions
ar+0.002
t+0.002
zed+0.002
rd+0.002
ake+0.002
Neg logit contributions
nam-0.002
ishes-0.002
iring-0.002
efully-0.002
ble-0.002
TokenThe
Token ID464
Feature activation-4.24e-01

Pos logit contributions
ar+0.011
zed+0.011
t+0.011
ake+0.010
rd+0.010
Neg logit contributions
nam-0.009
iring-0.009
ble-0.008
efully-0.008
uted-0.008
Token all
Token ID477
Feature activation+1.52e+00

Pos logit contributions
 moment+0.013
 minutes+0.012
 ever+0.012
ar+0.012
 minute+0.012
Neg logit contributions
nam-0.011
uted-0.010
iring-0.010
asure-0.010
ishes-0.010
Tokenigator
Token ID23823
Feature activation+3.77e+00

Pos logit contributions
nam+0.030
iring+0.027
ble+0.026
uted+0.025
efully+0.024
Neg logit contributions
zed-0.057
ar-0.057
 ever-0.056
t-0.056
 minutes-0.055
Token ended
Token ID4444
Feature activation-7.17e-01

Pos logit contributions
nam+0.103
iring+0.096
ble+0.094
efully+0.093
uted+0.090
Neg logit contributions
ar-0.111
zed-0.108
t-0.107
rd-0.104
ake-0.104
Token his
Token ID465
Feature activation-1.13e+00

Pos logit contributions
zed+0.026
ar+0.026
 dreaming+0.025
ake+0.025
 ever+0.025
Neg logit contributions
nam-0.014
iring-0.012
efully-0.012
ble-0.012
ishes-0.012
Token journey
Token ID7002
Feature activation-2.74e-01

Pos logit contributions
t+0.029
ar+0.029
zed+0.028
da+0.027
ake+0.027
Neg logit contributions
nam-0.034
ble-0.031
iring-0.031
 rad-0.031
efully-0.031
Token at
Token ID379
Feature activation-9.57e-01

Pos logit contributions
ar+0.008
rd+0.008
zed+0.008
ake+0.008
 minutes+0.008
Neg logit contributions
nam-0.007
iring-0.007
ble-0.007
uted-0.006
efully-0.006
Token the
Token ID262
Feature activation-3.41e-02

Pos logit contributions
ar+0.029
t+0.028
zed+0.027
rd+0.027
ake+0.027
Neg logit contributions
nam-0.026
ble-0.024
iring-0.024
efully-0.023
uted-0.022
Token and
Token ID290
Feature activation+2.22e-01

Pos logit contributions
ar+0.007
zed+0.007
gh+0.006
ake+0.006
da+0.006
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
 rad-0.004
ins-0.004
Token ate
Token ID15063
Feature activation+2.10e-01

Pos logit contributions
nam+0.007
iring+0.006
ble+0.006
efully+0.006
uted+0.006
Neg logit contributions
ar-0.006
zed-0.006
t-0.006
ake-0.006
rd-0.006
Token their
Token ID511
Feature activation-8.85e-01

Pos logit contributions
nam+0.007
iring+0.007
efully+0.006
ble+0.006
uted+0.006
Neg logit contributions
ar-0.005
zed-0.005
 minutes-0.005
t-0.005
ake-0.005
Token sandwiches
Token ID29777
Feature activation+1.96e+00

Pos logit contributions
ar+0.023
zed+0.023
t+0.022
ake+0.022
rd+0.022
Neg logit contributions
nam-0.027
iring-0.025
ble-0.025
efully-0.025
ishes-0.024
Token and
Token ID290
Feature activation-2.30e-01

Pos logit contributions
nam+0.062
iring+0.059
ble+0.058
efully+0.057
uted+0.056
Neg logit contributions
ar-0.049
zed-0.047
t-0.047
rd-0.045
ake-0.045
Token carrots
Token ID34397
Feature activation+3.41e+00

Pos logit contributions
ar+0.006
zed+0.006
t+0.006
rd+0.006
ake+0.006
Neg logit contributions
nam-0.007
iring-0.006
ble-0.006
efully-0.006
uted-0.006
Token.
Token ID13
Feature activation+3.35e-01

Pos logit contributions
nam+0.118
iring+0.112
efully+0.109
ble+0.107
uted+0.106
Neg logit contributions
ar-0.076
t-0.074
zed-0.072
 ever-0.071
ake-0.071
Token They
Token ID1119
Feature activation+2.77e-03

Pos logit contributions
nam+0.006
iring+0.006
efully+0.006
uted+0.006
ble+0.005
Neg logit contributions
ar-0.012
ake-0.012
zed-0.012
rd-0.012
t-0.012
Token were
Token ID547
Feature activation-8.52e-01

Pos logit contributions
iring+0.000
nam+0.000
ble+0.000
efully+0.000
uted+0.000
Neg logit contributions
ar-0.000
 ever-0.000
zed-0.000
t-0.000
 minutes-0.000
Token very
Token ID845
Feature activation-6.35e-01

Pos logit contributions
 ever+0.022
 dreaming+0.022
 minutes+0.021
zed+0.020
 no+0.020
Neg logit contributions
nam-0.025
ishes-0.024
ble-0.024
iring-0.023
ada-0.023
Token hungry
Token ID14720
Feature activation+3.06e-01

Pos logit contributions
 ever+0.017
 minutes+0.017
zed+0.017
t+0.017
rd+0.016
Neg logit contributions
nam-0.018
efully-0.017
ishes-0.017
uted-0.017
ble-0.016
Token try
Token ID1949
Feature activation-2.91e-02

Pos logit contributions
ar+0.007
zed+0.007
t+0.007
ake+0.007
rd+0.007
Neg logit contributions
nam-0.009
iring-0.008
efully-0.008
ble-0.008
uted-0.008
Token the
Token ID262
Feature activation+1.41e+00

Pos logit contributions
ar+0.001
rd+0.001
t+0.001
zed+0.001
 minutes+0.001
Neg logit contributions
nam-0.001
ble-0.001
 rad-0.001
 av-0.001
iring-0.001
Token broccoli
Token ID44653
Feature activation+2.42e+00

Pos logit contributions
nam+0.032
iring+0.030
ble+0.029
efully+0.028
uted+0.027
Neg logit contributions
ar-0.049
zed-0.047
t-0.046
rd-0.046
ake-0.046
Token c
Token ID269
Feature activation+6.72e-01

Pos logit contributions
nam+0.068
ble+0.066
iring+0.065
efully+0.063
 rad+0.062
Neg logit contributions
ar-0.066
zed-0.065
rd-0.063
ake-0.062
t-0.062
Tokenasser
Token ID24929
Feature activation-4.20e-01

Pos logit contributions
nam+0.013
iring+0.013
ble+0.012
efully+0.012
uted+0.011
Neg logit contributions
ar-0.024
zed-0.024
t-0.024
rd-0.023
ake-0.023
Tokenole
Token ID2305
Feature activation+3.57e+00

Pos logit contributions
t+0.014
ar+0.013
ake+0.013
 ever+0.013
rd+0.013
Neg logit contributions
nam-0.011
efully-0.009
uted-0.009
iring-0.009
ishes-0.009
Token.
Token ID13
Feature activation-1.85e-03

Pos logit contributions
nam+0.103
iring+0.096
ble+0.093
 av+0.093
 rad+0.093
Neg logit contributions
zed-0.097
ar-0.097
ake-0.094
rd-0.092
 dreaming-0.092
Token He
Token ID679
Feature activation+2.67e-01

Pos logit contributions
ar+0.000
t+0.000
zed+0.000
rd+0.000
 dreaming+0.000
Neg logit contributions
nam-0.000
ble-0.000
iring-0.000
efully-0.000
uted-0.000
Token said
Token ID531
Feature activation-2.62e-02

Pos logit contributions
nam+0.008
iring+0.008
ble+0.008
uted+0.007
efully+0.007
Neg logit contributions
ar-0.007
zed-0.007
t-0.007
 ever-0.007
 minutes-0.007
Token,
Token ID11
Feature activation-3.69e-01

Pos logit contributions
ar+0.001
rd+0.001
zed+0.001
 minutes+0.001
ake+0.001
Neg logit contributions
nam-0.001
ble-0.001
 rad-0.001
iring-0.001
 av-0.001
Token "
Token ID366
Feature activation-3.03e-01

Pos logit contributions
ar+0.012
zed+0.012
rd+0.012
t+0.012
ake+0.012
Neg logit contributions
nam-0.009
iring-0.008
ble-0.008
efully-0.008
uted-0.008
Token."
Token ID526
Feature activation+8.32e-01

Pos logit contributions
nam+0.024
ble+0.023
iring+0.023
ishes+0.023
efully+0.022
Neg logit contributions
zed-0.015
ar-0.015
rd-0.015
ake-0.014
 minutes-0.014
Token
Token ID198
Feature activation+6.74e-01

Pos logit contributions
nam+0.024
iring+0.023
ble+0.023
efully+0.022
ishes+0.022
Neg logit contributions
ar-0.023
t-0.022
zed-0.022
rd-0.021
ake-0.021
Token
Token ID198
Feature activation+3.57e-01

Pos logit contributions
nam+0.020
iring+0.018
ishes+0.018
efully+0.018
ble+0.018
Neg logit contributions
ar-0.019
t-0.019
zed-0.019
ake-0.018
rd-0.018
TokenTom
Token ID13787
Feature activation-1.68e+00

Pos logit contributions
nam+0.012
iring+0.011
ble+0.011
efully+0.011
uted+0.011
Neg logit contributions
ar-0.009
zed-0.008
t-0.008
ake-0.008
rd-0.008
Token and
Token ID290
Feature activation-6.61e-01

Pos logit contributions
ar+0.047
zed+0.046
t+0.046
ake+0.045
rd+0.045
Neg logit contributions
nam-0.046
efully-0.044
iring-0.044
ble-0.044
uted-0.043
Token Lily
Token ID20037
Feature activation+7.11e-01

Pos logit contributions
ar+0.016
ake+0.016
t+0.015
zed+0.015
rd+0.015
Neg logit contributions
nam-0.022
efully-0.020
iring-0.020
ishes-0.020
ble-0.020
Token were
Token ID547
Feature activation-1.68e-01

Pos logit contributions
nam+0.023
iring+0.023
ble+0.021
ins+0.020
ishes+0.020
Neg logit contributions
ar-0.019
zed-0.017
t-0.017
 ever-0.017
 dreaming-0.016
Token shocked
Token ID11472
Feature activation-1.86e-02

Pos logit contributions
 dreaming+0.005
 minutes+0.005
zed+0.005
 ever+0.005
rd+0.005
Neg logit contributions
nam-0.004
ishes-0.004
 av-0.004
iring-0.004
 ot-0.004
Token and
Token ID290
Feature activation-9.07e-01

Pos logit contributions
zed+0.001
ar+0.001
rd+0.001
gh+0.001
t+0.001
Neg logit contributions
iring-0.000
ble-0.000
nam-0.000
uted-0.000
efully-0.000
Token scared
Token ID12008
Feature activation+3.93e-01

Pos logit contributions
ar+0.031
zed+0.031
 dreaming+0.031
 minutes+0.030
t+0.030
Neg logit contributions
nam-0.019
iring-0.019
ble-0.018
efully-0.018
ishes-0.017
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
iring+0.010
nam+0.009
efully+0.009
uted+0.009
ble+0.009
Neg logit contributions
zed-0.013
ar-0.013
rd-0.012
z-0.012
seek-0.012
Token drum
Token ID13026
Feature activation-1.29e+00

Pos logit contributions
t+0.033
ar+0.032
da+0.030
rd+0.030
z+0.029
Neg logit contributions
nam-0.024
ble-0.019
 av-0.019
uted-0.018
iring-0.017
Tokenming
Token ID2229
Feature activation-9.54e-01

Pos logit contributions
zed+0.038
ar+0.038
 minutes+0.038
da+0.037
ake+0.036
Neg logit contributions
nam-0.032
bles-0.030
ble-0.030
iring-0.029
ishes-0.029
Token with
Token ID351
Feature activation+2.26e-01

Pos logit contributions
ar+0.027
zed+0.026
t+0.026
ake+0.025
rd+0.025
Neg logit contributions
nam-0.027
ble-0.025
iring-0.025
efully-0.025
uted-0.024
Token his
Token ID465
Feature activation+8.87e-03

Pos logit contributions
nam+0.005
iring+0.005
ble+0.005
efully+0.005
 ot+0.004
Neg logit contributions
ar-0.008
rd-0.007
t-0.007
zed-0.007
ake-0.007
Token friends
Token ID2460
Feature activation+1.44e+00

Pos logit contributions
nam+0.000
ble+0.000
iring+0.000
efully+0.000
ishes+0.000
Neg logit contributions
ar-0.000
zed-0.000
t-0.000
rd-0.000
ake-0.000
Token.
Token ID13
Feature activation+4.39e-01

Pos logit contributions
nam+0.040
ble+0.035
iring+0.035
efully+0.035
uted+0.034
Neg logit contributions
zed-0.042
ar-0.042
t-0.040
rd-0.039
 minutes-0.039
Token And
Token ID843
Feature activation-1.16e-01

Pos logit contributions
nam+0.013
iring+0.012
ble+0.012
efully+0.011
ishes+0.011
Neg logit contributions
ar-0.013
zed-0.013
t-0.012
ake-0.012
rd-0.012
Token they
Token ID484
Feature activation-3.80e-01

Pos logit contributions
ar+0.003
zed+0.003
rd+0.003
t+0.003
ake+0.003
Neg logit contributions
nam-0.004
iring-0.003
efully-0.003
ble-0.003
uted-0.003
Token all
Token ID477
Feature activation+2.04e+00

Pos logit contributions
ar+0.012
zed+0.012
 ever+0.012
 dreaming+0.011
ake+0.011
Neg logit contributions
iring-0.010
nam-0.010
uted-0.009
ble-0.009
ins-0.009
Token lived
Token ID5615
Feature activation+2.99e-01

Pos logit contributions
nam+0.054
iring+0.053
ble+0.050
uted+0.048
efully+0.048
Neg logit contributions
ar-0.062
zed-0.061
 ever-0.059
t-0.059
ake-0.058
Token happily
Token ID18177
Feature activation+4.90e-01

Pos logit contributions
nam+0.006
iring+0.006
ble+0.005
uted+0.005
ishes+0.005
Neg logit contributions
ar-0.011
zed-0.011
 ever-0.011
ake-0.010
rd-0.010
Token playing
Token ID2712
Feature activation+2.53e-01

Pos logit contributions
ar+0.030
rd+0.029
t+0.028
zed+0.027
ake+0.027
Neg logit contributions
nam-0.025
uted-0.022
iring-0.022
ble-0.022
 rad-0.022
Token with
Token ID351
Feature activation+6.37e-01

Pos logit contributions
nam+0.007
ble+0.006
uted+0.006
iring+0.006
 av+0.006
Neg logit contributions
t-0.007
ar-0.007
ake-0.007
rd-0.007
zed-0.007
Token a
Token ID257
Feature activation-4.33e-01

Pos logit contributions
nam+0.016
iring+0.014
ble+0.014
 rad+0.014
 ot+0.013
Neg logit contributions
ar-0.021
t-0.020
rd-0.020
ake-0.020
zed-0.020
Token ball
Token ID2613
Feature activation+9.33e-01

Pos logit contributions
ar+0.013
zed+0.012
t+0.012
rd+0.012
ake+0.012
Neg logit contributions
nam-0.012
iring-0.011
ble-0.011
efully-0.011
uted-0.010
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
nam+0.023
iring+0.022
ble+0.022
 ot+0.021
uted+0.021
Neg logit contributions
zed-0.030
rd-0.028
ar-0.028
da-0.027
ake-0.026
Token Tim
Token ID5045
Feature activation+1.24e+00

Pos logit contributions
nam+0.005
ble+0.005
efully+0.005
ishes+0.005
iring+0.005
Neg logit contributions
t-0.004
ar-0.004
zed-0.004
rd-0.004
ake-0.004
Token laughed
Token ID13818
Feature activation+1.01e+00

Pos logit contributions
nam+0.037
iring+0.035
ble+0.034
efully+0.034
uted+0.033
Neg logit contributions
ar-0.034
zed-0.033
t-0.032
ake-0.031
rd-0.031
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
nam+0.024
iring+0.024
ble+0.024
uted+0.023
efully+0.023
Neg logit contributions
ar-0.032
rd-0.032
zed-0.032
t-0.031
ake-0.031
Token said
Token ID531
Feature activation+2.51e-01

Pos logit contributions
ar+0.014
zed+0.014
t+0.014
rd+0.014
ake+0.014
Neg logit contributions
nam-0.014
iring-0.013
ble-0.013
efully-0.013
uted-0.012
Token,
Token ID11
Feature activation-3.42e-01

Pos logit contributions
nam+0.008
ble+0.008
iring+0.008
efully+0.007
uted+0.007
Neg logit contributions
ar-0.006
zed-0.006
ake-0.006
t-0.006
rd-0.006
Token "
Token ID366
Feature activation-3.86e-02

Pos logit contributions
ar+0.012
rd+0.011
zed+0.011
ake+0.011
t+0.011
Neg logit contributions
nam-0.008
ble-0.007
iring-0.007
uted-0.007
efully-0.007
Token in
Token ID287
Feature activation+1.09e+00

Pos logit contributions
ar+0.034
zed+0.033
t+0.033
rd+0.032
ake+0.032
Neg logit contributions
nam-0.036
iring-0.034
ble-0.033
efully-0.033
uted-0.031
Token front
Token ID2166
Feature activation-1.17e+00

Pos logit contributions
nam+0.023
efully+0.021
 rad+0.020
iring+0.019
 av+0.018
Neg logit contributions
ar-0.042
t-0.041
zed-0.040
ake-0.039
seek-0.039
Token of
Token ID286
Feature activation+3.45e-01

Pos logit contributions
ar+0.043
zed+0.043
gh+0.040
t+0.040
ake+0.040
Neg logit contributions
iring-0.023
nam-0.021
efully-0.021
uted-0.019
ble-0.019
Token him
Token ID683
Feature activation-5.53e-01

Pos logit contributions
nam+0.006
 av+0.006
efully+0.005
 rad+0.005
iring+0.005
Neg logit contributions
ar-0.014
t-0.014
z-0.013
rd-0.013
seek-0.013
Token.
Token ID13
Feature activation+4.07e-01

Pos logit contributions
zed+0.017
ar+0.017
t+0.016
rd+0.016
 minutes+0.016
Neg logit contributions
nam-0.014
iring-0.014
ble-0.014
efully-0.013
uted-0.012
Token She
Token ID1375
Feature activation+5.18e-01

Pos logit contributions
nam+0.013
ble+0.012
ishes+0.012
iring+0.012
bles+0.011
Neg logit contributions
t-0.011
ar-0.011
zed-0.010
rd-0.010
 dreaming-0.010
Token smiled
Token ID13541
Feature activation+7.32e-01

Pos logit contributions
nam+0.014
iring+0.013
efully+0.013
ble+0.013
uted+0.012
Neg logit contributions
ar-0.015
t-0.015
zed-0.015
rd-0.015
ake-0.015
Token and
Token ID290
Feature activation+8.21e-02

Pos logit contributions
iring+0.019
nam+0.018
ble+0.018
efully+0.018
uted+0.017
Neg logit contributions
ar-0.023
zed-0.023
t-0.022
rd-0.022
ake-0.022
Token said
Token ID531
Feature activation+2.94e-01

Pos logit contributions
nam+0.002
iring+0.002
efully+0.002
ble+0.002
uted+0.001
Neg logit contributions
ar-0.003
t-0.003
ake-0.003
rd-0.003
zed-0.003
Token "
Token ID366
Feature activation-3.06e-01

Pos logit contributions
nam+0.009
iring+0.009
ble+0.009
efully+0.008
uted+0.008
Neg logit contributions
ar-0.007
t-0.007
zed-0.007
ake-0.007
rd-0.007
TokenWelcome
Token ID14618
Feature activation+2.66e-01

Pos logit contributions
zed+0.010
ar+0.010
 minutes+0.009
rd+0.009
 injuries+0.009
Neg logit contributions
nam-0.007
efully-0.007
iring-0.007
ble-0.007
uted-0.007
Token ball
Token ID2613
Feature activation+1.40e+00

Pos logit contributions
nam+0.021
iring+0.020
efully+0.020
ble+0.019
uted+0.019
Neg logit contributions
ar-0.021
t-0.020
zed-0.020
ake-0.020
rd-0.020
Token very
Token ID845
Feature activation+1.35e+00

Pos logit contributions
nam+0.041
iring+0.039
ble+0.038
efully+0.038
uted+0.037
Neg logit contributions
zed-0.037
ar-0.037
rd-0.036
ake-0.035
t-0.034
Token high
Token ID1029
Feature activation+1.19e-01

Pos logit contributions
nam+0.043
iring+0.041
ble+0.040
efully+0.039
uted+0.038
Neg logit contributions
ar-0.034
zed-0.033
ake-0.032
rd-0.032
t-0.032
Token and
Token ID290
Feature activation+6.23e-01

Pos logit contributions
nam+0.003
iring+0.003
ble+0.003
efully+0.003
uted+0.003
Neg logit contributions
zed-0.003
ar-0.003
t-0.003
rd-0.003
ake-0.003
Token far
Token ID1290
Feature activation+6.26e-01

Pos logit contributions
nam+0.019
ble+0.017
efully+0.017
iring+0.017
uted+0.016
Neg logit contributions
ar-0.017
ake-0.017
rd-0.016
zed-0.016
t-0.016
Token with
Token ID351
Feature activation+7.38e-01

Pos logit contributions
nam+0.016
iring+0.015
ble+0.015
efully+0.014
uted+0.014
Neg logit contributions
zed-0.019
rd-0.019
ar-0.019
ake-0.019
t-0.018
Token her
Token ID607
Feature activation+4.10e-01

Pos logit contributions
nam+0.017
efully+0.015
iring+0.015
uted+0.014
 rad+0.014
Neg logit contributions
ar-0.026
ake-0.025
zed-0.025
t-0.025
rd-0.025
Token foot
Token ID2366
Feature activation-1.14e+00

Pos logit contributions
nam+0.010
iring+0.009
efully+0.009
ble+0.009
uted+0.009
Neg logit contributions
ar-0.013
zed-0.013
t-0.013
rd-0.012
 ever-0.012
Token.
Token ID13
Feature activation+3.28e-01

Pos logit contributions
ar+0.034
zed+0.033
rd+0.033
ake+0.032
 basis+0.032
Neg logit contributions
ble-0.029
nam-0.029
bles-0.027
iring-0.027
efully-0.026
Token Her
Token ID2332
Feature activation+3.49e-01

Pos logit contributions
nam+0.011
iring+0.010
ble+0.010
ishes+0.010
uted+0.010
Neg logit contributions
ar-0.008
zed-0.008
t-0.008
rd-0.008
 minutes-0.008
Token friends
Token ID2460
Feature activation+1.49e+00

Pos logit contributions
nam+0.008
iring+0.008
ble+0.008
efully+0.008
uted+0.007
Neg logit contributions
ar-0.011
zed-0.011
t-0.011
rd-0.011
ake-0.011
Token eating
Token ID6600
Feature activation+4.24e-01

Pos logit contributions
iring+0.026
nam+0.026
ble+0.025
efully+0.025
ins+0.024
Neg logit contributions
ar-0.032
zed-0.032
t-0.031
da-0.030
gh-0.030
Token it
Token ID340
Feature activation-7.06e-01

Pos logit contributions
nam+0.013
iring+0.013
ble+0.012
efully+0.012
uted+0.012
Neg logit contributions
ar-0.011
zed-0.010
 minutes-0.010
 ever-0.010
t-0.010
Token together
Token ID1978
Feature activation-3.01e-01

Pos logit contributions
ar+0.019
zed+0.018
t+0.018
ake+0.018
rd+0.018
Neg logit contributions
nam-0.021
ble-0.019
iring-0.019
efully-0.019
ishes-0.018
Token.
Token ID13
Feature activation+3.26e-01

Pos logit contributions
ar+0.009
zed+0.008
t+0.008
ake+0.008
rd+0.008
Neg logit contributions
nam-0.008
iring-0.008
ble-0.008
efully-0.007
 rad-0.007
Token<|endoftext|>
Token ID50256
Feature activation+3.80e-01

Pos logit contributions
nam+0.010
ble+0.010
iring+0.010
ishes+0.009
bles+0.009
Neg logit contributions
ar-0.008
t-0.008
zed-0.008
rd-0.008
ake-0.008
TokenOnce
Token ID7454
Feature activation+1.21e-01

Pos logit contributions
nam+0.011
iring+0.010
ble+0.009
efully+0.009
ishes+0.009
Neg logit contributions
ar-0.011
t-0.011
zed-0.011
ake-0.011
rd-0.011
Token upon
Token ID2402
Feature activation+8.13e-01

Pos logit contributions
nam+0.003
efully+0.003
uted+0.003
iring+0.003
ishes+0.003
Neg logit contributions
t-0.004
ar-0.004
zed-0.004
 ever-0.004
ake-0.004
Token a
Token ID257
Feature activation-4.41e-01

Pos logit contributions
nam+0.025
iring+0.024
ble+0.023
efully+0.023
uted+0.023
Neg logit contributions
ar-0.021
zed-0.020
t-0.020
ake-0.020
rd-0.019
Token time
Token ID640
Feature activation+2.05e-01

Pos logit contributions
ar+0.011
seek+0.010
t+0.010
zed+0.010
 payoff+0.010
Neg logit contributions
efully-0.013
 rad-0.012
iring-0.012
nam-0.012
uted-0.012
Token,
Token ID11
Feature activation-7.74e-01

Pos logit contributions
nam+0.006
iring+0.006
ble+0.006
uted+0.005
efully+0.005
Neg logit contributions
zed-0.005
ar-0.005
 minutes-0.005
rd-0.005
ake-0.005
Token there
Token ID612
Feature activation-2.54e-01

Pos logit contributions
ar+0.019
zed+0.018
t+0.018
ake+0.017
rd+0.017
Neg logit contributions
nam-0.025
iring-0.024
ble-0.023
efully-0.023
uted-0.023
Token time
Token ID640
Feature activation+3.71e-01

Pos logit contributions
ar+0.003
seek+0.003
 payoff+0.003
zed+0.003
t+0.003
Neg logit contributions
efully-0.003
iring-0.003
uted-0.003
 rad-0.003
 idea-0.003
Token,
Token ID11
Feature activation-5.49e-01

Pos logit contributions
nam+0.011
iring+0.010
ble+0.010
uted+0.009
 rad+0.009
Neg logit contributions
zed-0.010
ar-0.010
 minutes-0.009
ake-0.009
 dreaming-0.009
Token there
Token ID612
Feature activation-1.03e-01

Pos logit contributions
ar+0.012
zed+0.012
t+0.012
ake+0.012
rd+0.011
Neg logit contributions
nam-0.019
iring-0.018
efully-0.017
ble-0.017
uted-0.017
Token was
Token ID373
Feature activation+4.16e-01

Pos logit contributions
ar+0.003
zed+0.003
t+0.003
ake+0.003
rd+0.003
Neg logit contributions
nam-0.003
iring-0.003
ble-0.003
efully-0.003
uted-0.003
Token a
Token ID257
Feature activation-3.36e-01

Pos logit contributions
nam+0.015
iring+0.014
ble+0.014
ishes+0.014
efully+0.014
Neg logit contributions
zed-0.008
ar-0.008
t-0.008
ake-0.008
rd-0.008
Token pengu
Token ID38373
Feature activation-9.30e-01

Pos logit contributions
ar+0.010
 minutes+0.009
 dreaming+0.009
zed+0.009
t+0.009
Neg logit contributions
nam-0.009
efully-0.009
iring-0.009
uted-0.009
ishes-0.008
Tokenin
Token ID259
Feature activation-8.11e-02

Pos logit contributions
ar+0.031
t+0.030
ake+0.030
zed+0.029
rd+0.029
Neg logit contributions
nam-0.022
efully-0.020
iring-0.019
ishes-0.019
uted-0.018
Token who
Token ID508
Feature activation-1.50e+00

Pos logit contributions
ar+0.002
zed+0.002
t+0.002
rd+0.002
ake+0.002
Neg logit contributions
nam-0.002
iring-0.002
ble-0.002
efully-0.002
uted-0.002
Token lived
Token ID5615
Feature activation-2.29e-01

Pos logit contributions
 minutes+0.061
ar+0.061
 injuries+0.060
 payoff+0.060
t+0.059
Neg logit contributions
nam-0.021
 ot-0.019
efully-0.018
ble-0.017
 rad-0.017
Token in
Token ID287
Feature activation-8.88e-02

Pos logit contributions
 ever+0.006
 dreaming+0.006
t+0.005
ar+0.005
ake+0.005
Neg logit contributions
nam-0.007
ishes-0.007
efully-0.007
uted-0.007
iring-0.007
Token a
Token ID257
Feature activation-1.11e+00

Pos logit contributions
ar+0.003
t+0.003
rd+0.003
ake+0.003
gh+0.003
Neg logit contributions
nam-0.002
 rad-0.002
 ot-0.002
ble-0.002
efully-0.002
Token gray
Token ID12768
Feature activation-4.21e-01

Pos logit contributions
ar+0.017
zed+0.016
t+0.016
ake+0.016
rd+0.016
Neg logit contributions
nam-0.018
iring-0.016
ble-0.016
efully-0.016
ishes-0.015
Token.
Token ID13
Feature activation+5.37e-01

Pos logit contributions
ar+0.011
zed+0.011
t+0.011
rd+0.011
ake+0.011
Neg logit contributions
nam-0.012
iring-0.012
ble-0.012
efully-0.012
uted-0.011
Token They
Token ID1119
Feature activation+1.20e-01

Pos logit contributions
nam+0.017
iring+0.015
ble+0.015
efully+0.015
uted+0.015
Neg logit contributions
ar-0.014
t-0.014
zed-0.013
 minutes-0.013
ake-0.013
Token want
Token ID765
Feature activation+3.45e-01

Pos logit contributions
iring+0.004
nam+0.004
ins+0.004
uted+0.004
ble+0.004
Neg logit contributions
 ever-0.003
t-0.002
ar-0.002
 minutes-0.002
 dreaming-0.002
Token to
Token ID284
Feature activation+2.07e-01

Pos logit contributions
nam+0.012
iring+0.012
ble+0.011
 rad+0.011
efully+0.011
Neg logit contributions
ar-0.007
zed-0.007
rd-0.007
t-0.007
ake-0.007
Token see
Token ID766
Feature activation+3.77e-02

Pos logit contributions
nam+0.008
iring+0.008
ins+0.008
ishes+0.007
uted+0.007
Neg logit contributions
 ever-0.004
ar-0.004
zed-0.004
t-0.004
 blast-0.004
Token what
Token ID644
Feature activation+4.25e-01

Pos logit contributions
nam+0.001
efully+0.001
iring+0.001
ble+0.001
bles+0.001
Neg logit contributions
 ever-0.001
 minutes-0.001
 dreaming-0.001
ar-0.001
 moment-0.001
Token is
Token ID318
Feature activation+1.84e+00

Pos logit contributions
nam+0.013
iring+0.012
ble+0.012
efully+0.012
ishes+0.012
Neg logit contributions
ar-0.011
zed-0.011
t-0.010
ake-0.010
rd-0.010
Token in
Token ID287
Feature activation+1.57e+00

Pos logit contributions
nam+0.052
iring+0.048
ble+0.048
efully+0.047
uted+0.046
Neg logit contributions
ar-0.053
zed-0.052
t-0.051
rd-0.050
ake-0.050
Token the
Token ID262
Feature activation+4.91e-01

Pos logit contributions
nam+0.037
ble+0.034
iring+0.033
 rad+0.030
efully+0.029
Neg logit contributions
ar-0.057
zed-0.056
rd-0.056
seek-0.055
t-0.054
Token pond
Token ID16723
Feature activation+1.27e+00

Pos logit contributions
nam+0.013
uted+0.012
iring+0.011
efully+0.011
ishes+0.011
Neg logit contributions
ar-0.016
 minutes-0.015
t-0.015
 ever-0.015
 moment-0.015
Token One
Token ID1881
Feature activation-6.06e-01

Pos logit contributions
nam+0.010
iring+0.009
ble+0.009
efully+0.009
uted+0.009
Neg logit contributions
ar-0.009
t-0.009
zed-0.009
rd-0.009
ake-0.009
Token day
Token ID1110
Feature activation-5.49e-01

Pos logit contributions
ar+0.018
seek+0.016
zed+0.016
 injuries+0.015
z+0.015
Neg logit contributions
nam-0.016
ble-0.016
 rad-0.016
iring-0.015
 ot-0.015
Token,
Token ID11
Feature activation-2.26e-02

Pos logit contributions
ar+0.013
zed+0.012
t+0.012
rd+0.012
ake+0.012
Neg logit contributions
nam-0.018
iring-0.017
ble-0.017
efully-0.017
uted-0.017
Token Tim
Token ID5045
Feature activation+6.43e-01

Pos logit contributions
ar+0.001
zed+0.001
rd+0.001
ake+0.001
t+0.001
Neg logit contributions
nam-0.001
iring-0.001
ble-0.001
efully-0.001
ishes-0.001
Token's
Token ID338
Feature activation-1.93e-01

Pos logit contributions
nam+0.022
iring+0.021
ble+0.020
efully+0.020
uted+0.019
Neg logit contributions
ar-0.015
t-0.015
zed-0.015
ake-0.014
 ever-0.014
Token mom
Token ID1995
Feature activation-4.74e-01

Pos logit contributions
zed+0.007
ar+0.007
rd+0.006
t+0.006
ake+0.006
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
ishes-0.004
 ot-0.004
Token made
Token ID925
Feature activation-1.17e+00

Pos logit contributions
ar+0.014
zed+0.014
t+0.014
ake+0.013
rd+0.013
Neg logit contributions
nam-0.013
iring-0.012
ble-0.012
efully-0.012
uted-0.011
Token some
Token ID617
Feature activation+5.57e-02

Pos logit contributions
ar+0.029
zed+0.028
t+0.028
rd+0.027
ake+0.027
Neg logit contributions
nam-0.037
iring-0.035
ble-0.035
efully-0.034
uted-0.033
Token pasta
Token ID26296
Feature activation+4.04e-02

Pos logit contributions
nam+0.002
efully+0.002
uted+0.002
iring+0.002
ble+0.002
Neg logit contributions
 minutes-0.001
rd-0.001
t-0.001
 dreaming-0.001
 ever-0.001
Token for
Token ID329
Feature activation-8.58e-01

Pos logit contributions
nam+0.001
ble+0.001
iring+0.001
bles+0.001
ishes+0.001
Neg logit contributions
ar-0.001
zed-0.001
rd-0.001
t-0.001
ake-0.001
Token dinner
Token ID8073
Feature activation-8.03e-01

Pos logit contributions
ar+0.023
t+0.023
rd+0.022
ake+0.022
zed+0.021
Neg logit contributions
nam-0.026
ble-0.024
iring-0.024
efully-0.024
 rad-0.023
Token out
Token ID503
Feature activation+7.86e-01

Pos logit contributions
nam+0.023
iring+0.021
ble+0.021
efully+0.021
uted+0.020
Neg logit contributions
ar-0.026
zed-0.025
t-0.025
rd-0.024
ake-0.024
Token.
Token ID13
Feature activation+5.10e-02

Pos logit contributions
nam+0.021
iring+0.019
ble+0.018
efully+0.018
ishes+0.017
Neg logit contributions
ar-0.025
t-0.024
ake-0.023
zed-0.023
rd-0.023
Token She
Token ID1375
Feature activation+7.02e-01

Pos logit contributions
nam+0.002
ble+0.002
iring+0.001
ishes+0.001
efully+0.001
Neg logit contributions
t-0.001
ar-0.001
 minutes-0.001
 dreaming-0.001
rd-0.001
Token said
Token ID531
Feature activation-3.02e-01

Pos logit contributions
nam+0.019
iring+0.018
ble+0.017
efully+0.016
uted+0.016
Neg logit contributions
ar-0.021
 ever-0.021
zed-0.021
t-0.021
 minutes-0.021
Token they
Token ID484
Feature activation-1.39e+00

Pos logit contributions
ar+0.008
ake+0.008
rd+0.008
zed+0.008
t+0.008
Neg logit contributions
nam-0.009
 av-0.008
 rad-0.008
 ot-0.008
iring-0.008
Token were
Token ID547
Feature activation-4.15e-01

Pos logit contributions
ar+0.041
t+0.040
zed+0.040
 ever+0.038
ake+0.038
Neg logit contributions
nam-0.038
iring-0.036
ble-0.035
efully-0.035
uted-0.034
Token impressive
Token ID8036
Feature activation-4.91e-01

Pos logit contributions
 dreaming+0.011
 ever+0.011
 minutes+0.010
zed+0.010
ar+0.009
Neg logit contributions
iring-0.012
ishes-0.012
uted-0.012
ble-0.012
nam-0.012
Token twins
Token ID20345
Feature activation+4.95e-01

Pos logit contributions
zed+0.017
t+0.016
ar+0.016
gh+0.016
ake+0.015
Neg logit contributions
iring-0.012
nam-0.011
efully-0.011
ishes-0.011
ins-0.011
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
nam+0.009
iring+0.008
ter+0.008
 friends+0.008
efully+0.007
Neg logit contributions
zed-0.018
ar-0.018
gh-0.017
z-0.017
ake-0.017
Token She
Token ID1375
Feature activation+8.28e-01

Pos logit contributions
nam+0.004
ble+0.003
iring+0.003
ishes+0.003
efully+0.003
Neg logit contributions
t-0.003
ar-0.003
 minutes-0.003
 dreaming-0.003
rd-0.003
Token cl
Token ID537
Feature activation+7.51e-01

Pos logit contributions
nam+0.022
iring+0.020
ble+0.019
efully+0.018
ishes+0.018
Neg logit contributions
ar-0.026
 ever-0.026
t-0.025
zed-0.025
 minutes-0.024
Token the
Token ID262
Feature activation+2.33e-01

Pos logit contributions
nam+0.029
iring+0.027
ble+0.026
 rad+0.024
uted+0.024
Neg logit contributions
ar-0.039
t-0.038
ake-0.036
rd-0.036
seek-0.035
Token ugly
Token ID13400
Feature activation+1.29e+00

Pos logit contributions
nam+0.005
iring+0.004
ble+0.004
 av+0.004
 rad+0.004
Neg logit contributions
ar-0.009
zed-0.009
ake-0.009
seek-0.008
rd-0.008
Token things
Token ID1243
Feature activation+8.71e-01

Pos logit contributions
nam+0.025
ble+0.023
iring+0.023
 av+0.021
 rad+0.021
Neg logit contributions
ar-0.049
zed-0.048
ake-0.047
t-0.046
rd-0.046
Token she
Token ID673
Feature activation-9.58e-01

Pos logit contributions
nam+0.024
iring+0.023
ble+0.023
efully+0.021
uted+0.021
Neg logit contributions
ar-0.025
rd-0.024
zed-0.024
ake-0.024
 minutes-0.023
Token had
Token ID550
Feature activation-7.01e-01

Pos logit contributions
ar+0.027
ake+0.027
rd+0.027
zed+0.026
stand+0.026
Neg logit contributions
nam-0.025
efully-0.023
iring-0.023
ble-0.022
ishes-0.022
Token glimps
Token ID41226
Feature activation-2.51e+00

Pos logit contributions
ar+0.018
ake+0.017
rd+0.016
zed+0.016
storm+0.016
Neg logit contributions
nam-0.021
iring-0.019
uted-0.019
ble-0.019
efully-0.019
Tokened
Token ID276
Feature activation+4.16e-01

Pos logit contributions
ar+0.071
 minutes+0.067
zed+0.067
 payoff+0.066
rd+0.066
Neg logit contributions
ble-0.069
iring-0.067
nam-0.067
uted-0.064
bles-0.064
Token.
Token ID13
Feature activation+2.38e-01

Pos logit contributions
iring+0.010
nam+0.010
ble+0.009
ishes+0.008
 rad+0.008
Neg logit contributions
zed-0.014
ar-0.014
rd-0.013
t-0.013
seek-0.013
Token With
Token ID2080
Feature activation+1.62e-01

Pos logit contributions
nam+0.007
ble+0.007
iring+0.007
ishes+0.006
bles+0.006
Neg logit contributions
ar-0.006
t-0.006
zed-0.006
rd-0.006
ake-0.006
Token that
Token ID326
Feature activation+4.83e-01

Pos logit contributions
nam+0.004
efully+0.004
 rad+0.003
iring+0.003
 av+0.003
Neg logit contributions
ar-0.006
t-0.005
rd-0.005
ake-0.005
seek-0.005
Token,
Token ID11
Feature activation+8.34e-01

Pos logit contributions
nam+0.013
 rad+0.011
ble+0.011
iring+0.011
efully+0.010
Neg logit contributions
ake-0.015
seek-0.015
ar-0.015
storm-0.014
zed-0.014
Token things
Token ID1243
Feature activation+1.55e+00

Pos logit contributions
ar+0.045
zed+0.043
t+0.043
rd+0.042
ake+0.042
Neg logit contributions
nam-0.042
iring-0.040
ble-0.039
efully-0.039
uted-0.038
Token look
Token ID804
Feature activation-4.90e-01

Pos logit contributions
nam+0.045
iring+0.043
ble+0.043
efully+0.041
uted+0.040
Neg logit contributions
ar-0.043
zed-0.041
rd-0.040
t-0.040
ake-0.040
Token different
Token ID1180
Feature activation+1.64e+00

Pos logit contributions
ar+0.016
zed+0.016
rd+0.015
ake+0.015
t+0.015
Neg logit contributions
nam-0.013
iring-0.012
ble-0.011
ishes-0.011
uted-0.011
Token for
Token ID329
Feature activation-3.67e-01

Pos logit contributions
nam+0.048
iring+0.045
ble+0.044
efully+0.044
uted+0.042
Neg logit contributions
ar-0.045
zed-0.044
t-0.044
ake-0.042
rd-0.042
Token a
Token ID257
Feature activation-1.35e-01

Pos logit contributions
ar+0.010
zed+0.010
t+0.010
rd+0.010
ake+0.010
Neg logit contributions
nam-0.011
iring-0.010
ble-0.010
efully-0.009
uted-0.009
Token while
Token ID981
Feature activation-2.97e+00

Pos logit contributions
ar+0.004
zed+0.004
t+0.004
rd+0.004
ake+0.004
Neg logit contributions
nam-0.004
ble-0.003
iring-0.003
 rad-0.003
efully-0.003
Token."
Token ID526
Feature activation-3.31e-02

Pos logit contributions
zed+0.097
ar+0.096
seek+0.092
z+0.090
rd+0.090
Neg logit contributions
nam-0.065
iring-0.065
ble-0.065
 ot-0.060
 rad-0.060
Token
Token ID198
Feature activation-8.80e-03

Pos logit contributions
t+0.001
 dreaming+0.001
 minutes+0.001
ar+0.001
stand+0.001
Neg logit contributions
nam-0.001
iring-0.001
ishes-0.001
ble-0.001
efully-0.001
Token
Token ID198
Feature activation-3.01e-01

Pos logit contributions
ake+0.000
t+0.000
zed+0.000
stand+0.000
ar+0.000
Neg logit contributions
nam-0.000
ishes-0.000
efully-0.000
iring-0.000
ish-0.000
TokenBen
Token ID11696
Feature activation-1.23e+00

Pos logit contributions
ar+0.006
zed+0.006
t+0.006
ake+0.006
rd+0.006
Neg logit contributions
nam-0.011
iring-0.010
ble-0.010
efully-0.010
uted-0.010
Token and
Token ID290
Feature activation-7.52e-01

Pos logit contributions
ar+0.036
zed+0.035
t+0.035
ake+0.034
rd+0.034
Neg logit contributions
nam-0.033
iring-0.031
efully-0.030
ble-0.030
uted-0.029
Token Sometimes
Token ID8975
Feature activation-5.56e-01

Pos logit contributions
nam+0.017
ble+0.016
iring+0.016
uted+0.015
efully+0.015
Neg logit contributions
ar-0.011
t-0.011
rd-0.011
zed-0.011
ake-0.011
Token,
Token ID11
Feature activation+3.59e-01

Pos logit contributions
ake+0.018
ar+0.017
zed+0.017
t+0.017
seek+0.017
Neg logit contributions
nam-0.013
iring-0.013
 ot-0.012
 rad-0.012
ishes-0.012
Token Sam
Token ID3409
Feature activation-5.01e-01

Pos logit contributions
nam+0.009
iring+0.008
ble+0.008
 ot+0.008
ishes+0.008
Neg logit contributions
ar-0.012
zed-0.012
ake-0.012
rd-0.011
t-0.011
Token goes
Token ID2925
Feature activation-1.07e+00

Pos logit contributions
ar+0.014
rd+0.014
ake+0.013
t+0.013
zed+0.013
Neg logit contributions
nam-0.013
ishes-0.013
iring-0.013
uted-0.012
ble-0.012
Token with
Token ID351
Feature activation+2.36e-02

Pos logit contributions
rd+0.034
zed+0.033
ake+0.031
gh+0.030
 basis+0.029
Neg logit contributions
nam-0.027
iring-0.026
bles-0.025
ishes-0.024
ble-0.024
Token Jen
Token ID13364
Feature activation-2.45e+00

Pos logit contributions
nam+0.001
 ot+0.000
 av+0.000
 rad+0.000
ishes+0.000
Neg logit contributions
ar-0.001
ake-0.001
t-0.001
zed-0.001
rd-0.001
Token to
Token ID284
Feature activation-6.11e-01

Pos logit contributions
ar+0.073
zed+0.071
rd+0.070
t+0.069
 minutes+0.069
Neg logit contributions
nam-0.063
ishes-0.061
iring-0.057
ish-0.055
uted-0.055
Token the
Token ID262
Feature activation-3.84e-01

Pos logit contributions
ar+0.019
t+0.019
ake+0.019
rd+0.018
zed+0.018
Neg logit contributions
nam-0.017
ble-0.014
iring-0.014
efully-0.014
 rad-0.014
Token lab
Token ID2248
Feature activation-2.48e-02

Pos logit contributions
zed+0.013
ar+0.012
ake+0.012
rd+0.012
t+0.012
Neg logit contributions
nam-0.009
iring-0.009
ble-0.008
 ot-0.008
efully-0.008
Token,
Token ID11
Feature activation-3.33e-01

Pos logit contributions
zed+0.001
ake+0.001
rd+0.001
da+0.001
gh+0.001
Neg logit contributions
nam-0.001
iring-0.001
 vendors-0.001
ishes-0.000
 ot-0.000
Token and
Token ID290
Feature activation-3.24e-01

Pos logit contributions
ar+0.011
rd+0.011
ake+0.011
t+0.010
gh+0.010
Neg logit contributions
nam-0.009
iring-0.007
 ot-0.007
ishes-0.007
 rad-0.007
Token,
Token ID11
Feature activation-1.23e-01

Pos logit contributions
ar+0.010
zed+0.010
rd+0.009
ake+0.009
t+0.009
Neg logit contributions
nam-0.012
ble-0.011
iring-0.011
efully-0.011
 rad-0.011
Token a
Token ID257
Feature activation+2.85e-01

Pos logit contributions
ar+0.003
zed+0.003
t+0.003
rd+0.003
ake+0.003
Neg logit contributions
nam-0.004
iring-0.004
ble-0.004
efully-0.004
uted-0.004
Token little
Token ID1310
Feature activation+1.22e+00

Pos logit contributions
nam+0.007
iring+0.006
ble+0.006
efully+0.006
uted+0.006
Neg logit contributions
ar-0.009
zed-0.009
t-0.009
rd-0.009
ake-0.009
Token vehicle
Token ID4038
Feature activation-3.32e-01

Pos logit contributions
nam+0.025
iring+0.023
ble+0.022
efully+0.022
uted+0.021
Neg logit contributions
ar-0.044
zed-0.044
t-0.043
rd-0.042
ake-0.042
Token named
Token ID3706
Feature activation-1.77e+00

Pos logit contributions
ar+0.010
 minutes+0.010
rd+0.010
zed+0.009
ake+0.009
Neg logit contributions
nam-0.008
ble-0.008
iring-0.008
 ot-0.008
uted-0.007
Token V
Token ID569
Feature activation-2.53e+00

Pos logit contributions
ar+0.057
zed+0.057
rd+0.055
 dreaming+0.055
 minutes+0.055
Neg logit contributions
nam-0.042
iring-0.039
efully-0.038
ble-0.038
uted-0.036
Tokenicky
Token ID17479
Feature activation+1.56e-01

Pos logit contributions
 dreaming+0.076
 payoff+0.074
 minutes+0.073
ar+0.072
zed+0.072
Neg logit contributions
ble-0.062
iring-0.061
uted-0.060
efully-0.058
ins-0.058
Token was
Token ID373
Feature activation+2.03e-01

Pos logit contributions
 ot+0.003
ble+0.003
 rad+0.003
uted+0.003
iring+0.003
Neg logit contributions
 payoff-0.005
 injuries-0.005
ar-0.005
 dreaming-0.005
stand-0.005
Token driving
Token ID5059
Feature activation-1.46e+00

Pos logit contributions
nam+0.006
iring+0.006
ble+0.006
efully+0.005
uted+0.005
Neg logit contributions
ar-0.006
zed-0.005
t-0.005
rd-0.005
ake-0.005
Token down
Token ID866
Feature activation-1.91e-01

Pos logit contributions
ar+0.038
zed+0.037
t+0.036
rd+0.035
ake+0.035
Neg logit contributions
nam-0.045
iring-0.042
ble-0.042
efully-0.041
uted-0.040
Token a
Token ID257
Feature activation+1.36e-01

Pos logit contributions
ar+0.005
zed+0.005
t+0.005
rd+0.005
ake+0.005
Neg logit contributions
nam-0.005
iring-0.005
ble-0.005
efully-0.005
uted-0.005
Token dream
Token ID4320
Feature activation-2.22e+00

Pos logit contributions
nam+0.005
ble+0.004
iring+0.004
 friends+0.004
bles+0.004
Neg logit contributions
ar-0.008
ake-0.007
t-0.007
zed-0.007
rd-0.007
Token was
Token ID373
Feature activation+4.97e-01

Pos logit contributions
rd+0.074
ake+0.072
ar+0.072
 basis+0.070
 minutes+0.069
Neg logit contributions
ble-0.045
iring-0.044
bles-0.040
nam-0.040
ying-0.039
Token not
Token ID407
Feature activation-1.24e+00

Pos logit contributions
nam+0.011
iring+0.010
ble+0.010
 rad+0.009
 av+0.009
Neg logit contributions
ar-0.018
rd-0.017
ake-0.017
z-0.016
 basis-0.016
Token just
Token ID655
Feature activation-2.30e+00

Pos logit contributions
ar+0.036
zed+0.034
t+0.034
rd+0.034
ake+0.033
Neg logit contributions
nam-0.036
iring-0.033
ble-0.032
efully-0.032
ishes-0.031
Token a
Token ID257
Feature activation-2.84e-01

Pos logit contributions
ar+0.081
t+0.078
ake+0.076
z+0.075
rd+0.074
Neg logit contributions
nam-0.060
iring-0.051
 ot-0.048
 rad-0.048
 av-0.047
Token dream
Token ID4320
Feature activation-2.74e+00

Pos logit contributions
zed+0.010
ar+0.010
ake+0.010
rd+0.009
seek+0.009
Neg logit contributions
nam-0.006
 rad-0.006
 ot-0.006
 friends-0.005
 idea-0.005
Token.
Token ID13
Feature activation-7.03e-02

Pos logit contributions
rd+0.091
ar+0.091
zed+0.090
joy+0.090
z+0.089
Neg logit contributions
iring-0.053
ble-0.051
ying-0.050
uted-0.045
ters-0.045
Token It
Token ID632
Feature activation-5.47e-01

Pos logit contributions
t+0.002
ar+0.002
zed+0.002
 dreaming+0.002
ake+0.002
Neg logit contributions
nam-0.002
ble-0.002
iring-0.002
ishes-0.002
efully-0.002
Token was
Token ID373
Feature activation-2.65e-01

Pos logit contributions
ar+0.018
ake+0.017
rd+0.017
zed+0.017
 minutes+0.017
Neg logit contributions
nam-0.012
iring-0.012
efully-0.012
ble-0.012
uted-0.011
Token a
Token ID257
Feature activation-6.94e-01

Pos logit contributions
ar+0.009
rd+0.008
t+0.008
ake+0.008
zed+0.008
Neg logit contributions
nam-0.007
iring-0.007
ble-0.006
efully-0.006
 rad-0.006
Token goal
Token ID3061
Feature activation-1.02e+00

Pos logit contributions
zed+0.024
ar+0.023
rd+0.023
seek+0.023
t+0.023
Neg logit contributions
nam-0.016
 rad-0.015
 ot-0.014
ble-0.014
 rob-0.013