TOP ACTIVATIONS
MAX = 4.113

that day that the best dessert for her was the one
bird worked hard until the mud was nice and soft .
it was all dry and mud ! He
even see other people having pic n ics .
When the fog was gone , all his
soon the dough was all back . The little
. As the dirt and mud washed away , Pe ep
sun was shining and the sand was warm . He felt
felt really sad because the mud had made her wool very
When the rain stopped , the farmer and
in need . We all belong to one big family and
and waited and soon the mud and the p udd les
Once they were all back home , Amy thanked her
was almost dark , the fog finally started to clear and
because she knew she was supposed to clean her room .
pretty flowers . But the mud was still in the way
When the rain stopped , they could still
and bright colors they were able to create .
. When the rain had stopped , the children
with the machine until the rain stopped pouring . Then the

MIN ACTIVATIONS
MIN = -5.388

mom and to the ost ric hes . They learned their
and run to the ost ric hes . "
should not tease the ost ric hes . They are not
and looked at the ost ric hes . They saw one
wanted to touch the ost ric hes . They reached out
loved to play make - bel ieve . Today she was
They do not pack ost ric hes anymore . They pack
" Please keep your seat bel ts on . We will
couldn 't get above the tre et ops . He was
selfish . She thanked her brothers and sisters for saving her
" What are you doing ?" The tube didn 't
cried . " The ost ric hes are mean ! They
together . They let their imag inations take over and soon
ostr ich pen . Ost ric hes are big birds with
but be careful . Ost ric hes can be gr umpy
a nearby tree watched him int ently . The
day , she would sit patiently and wait for her mom
mom said in a much gent ler voice , " It
He loved playing make - bel ieve with his friends .
but it stayed in their imag inations for many years to

INTERVAL 1.737 - 4.113
CONTAINS 2.201%

tired . He was looking for something in the sand .
better hotel tomorrow . They said they would try to make
The rat was delighted and said " Yes of course !"
He realised that it was all up to him and that
the bottle of ink , spilling it all over their drawings

INTERVAL -0.638 - 1.737
CONTAINS 76.431%

help . It 's important to use our own strength and
on her knee . Her mom took out a bottle of
. One day M imi decided to take a walk in
and said she liked to pretend . She told Max he
inside the door . It was dark and he couldn 't

INTERVAL -3.013 - -0.638
CONTAINS 21.307%

. It is delicious . She says thank you to her
and faces . They all laughed and had fun playing in
and Jack were very happy that they had cleaned up the
three and she loved to imagine . One of her favorite
. It was a pass to the swimming pool !

INTERVAL -5.388 - -3.013
CONTAINS 0.061%

so happy and hugged her daddy tight . She learned that
excited , she hugged the fairy and thanked her !
hugged Spot and thanked the man . They went back to
them ride on her back sometimes . One day
? How do they do that ?" Ben asked .
Token that
Token ID326
Feature activation-5.97e-01

Pos logit contributions
 Amen+0.002
 fires+0.002
stretched+0.002
 bears+0.002
 scar+0.002
Neg logit contributions
ork-0.003
oph-0.003
ally-0.002
way-0.002
handed-0.002
Token day
Token ID1110
Feature activation+6.39e-01

Pos logit contributions
 Amen+0.017
 fires+0.012
stretched+0.012
 bears+0.011
 smile+0.011
Neg logit contributions
ork-0.020
oph-0.020
way-0.017
ally-0.017
handed-0.017
Token that
Token ID326
Feature activation-1.05e+00

Pos logit contributions
oph+0.023
ork+0.023
handed+0.020
ally+0.020
way+0.020
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.011
 hope-0.010
 sometimes-0.010
Token the
Token ID262
Feature activation+9.33e-01

Pos logit contributions
 Amen+0.027
 fires+0.020
 sometimes+0.019
 bears+0.019
 hope+0.018
Neg logit contributions
ork-0.038
oph-0.036
ally-0.032
way-0.032
handed-0.032
Token best
Token ID1266
Feature activation+2.28e+00

Pos logit contributions
ork+0.026
oph+0.025
way+0.022
handed+0.022
ally+0.021
Neg logit contributions
 Amen-0.031
 fires-0.024
stretched-0.024
 bears-0.022
 scar-0.022
Token dessert
Token ID23084
Feature activation+4.11e+00

Pos logit contributions
ork+0.065
oph+0.063
ally+0.054
way+0.053
handed+0.053
Neg logit contributions
 Amen-0.076
 fires-0.059
stretched-0.056
 bears-0.055
 smile-0.054
Token for
Token ID329
Feature activation+1.91e+00

Pos logit contributions
ork+0.152
oph+0.150
way+0.134
ally+0.133
handed+0.132
Neg logit contributions
 Amen-0.098
 fires-0.069
stretched-0.064
 bears-0.063
 hope-0.060
Token her
Token ID607
Feature activation+1.79e+00

Pos logit contributions
ork+0.071
oph+0.067
way+0.064
handed+0.061
 doorstep+0.060
Neg logit contributions
 Amen-0.043
 bears-0.034
 fires-0.034
 scar-0.030
 hope-0.030
Token was
Token ID373
Feature activation-7.59e-01

Pos logit contributions
ork+0.056
oph+0.054
way+0.047
handed+0.047
ally+0.046
Neg logit contributions
 Amen-0.055
 fires-0.041
stretched-0.040
 bears-0.037
 passenger-0.037
Token the
Token ID262
Feature activation+1.68e+00

Pos logit contributions
 Amen+0.020
 fires+0.015
stretched+0.014
 bears+0.013
 smile+0.013
Neg logit contributions
ork-0.026
oph-0.026
way-0.023
ally-0.022
handed-0.022
Token one
Token ID530
Feature activation+1.12e+00

Pos logit contributions
ork+0.051
oph+0.050
way+0.044
handed+0.043
ally+0.043
Neg logit contributions
 Amen-0.052
 fires-0.039
stretched-0.039
 bears-0.035
 paddle-0.035
Token bird
Token ID6512
Feature activation+1.10e+00

Pos logit contributions
ork+0.043
oph+0.041
way+0.037
ally+0.037
handed+0.035
Neg logit contributions
 Amen-0.042
 fires-0.031
stretched-0.030
 bears-0.027
 paddle-0.026
Token worked
Token ID3111
Feature activation-1.42e+00

Pos logit contributions
ork+0.032
oph+0.031
way+0.028
ally+0.027
handed+0.027
Neg logit contributions
 Amen-0.036
 fires-0.027
stretched-0.026
 bears-0.024
 passenger-0.024
Token hard
Token ID1327
Feature activation-6.55e-01

Pos logit contributions
 Amen+0.040
 fires+0.025
 passenger+0.024
stretched+0.024
 bears+0.022
Neg logit contributions
ork-0.052
oph-0.047
way-0.047
ally-0.043
her-0.042
Token until
Token ID1566
Feature activation-1.68e+00

Pos logit contributions
 Amen+0.021
 fires+0.015
stretched+0.015
 bears+0.014
 passenger+0.014
Neg logit contributions
ork-0.020
oph-0.019
way-0.018
handed-0.017
ally-0.017
Token the
Token ID262
Feature activation+6.03e-01

Pos logit contributions
 Amen+0.051
 fires+0.038
stretched+0.037
 bears+0.035
 passenger+0.033
Neg logit contributions
ork-0.054
oph-0.053
way-0.046
ally-0.045
handed-0.045
Token mud
Token ID17492
Feature activation+4.07e+00

Pos logit contributions
oph+0.017
ork+0.017
handed+0.014
way+0.014
ally+0.014
Neg logit contributions
 Amen-0.020
 fires-0.016
stretched-0.015
 bears-0.015
 smile-0.014
Token was
Token ID373
Feature activation+3.12e-01

Pos logit contributions
oph+0.152
ork+0.137
handed+0.128
ally+0.124
Kat+0.122
Neg logit contributions
 Amen-0.077
 fires-0.070
 sometimes-0.069
 bears-0.068
 hope-0.067
Token nice
Token ID3621
Feature activation+1.19e+00

Pos logit contributions
ork+0.010
oph+0.010
handed+0.009
way+0.009
ally+0.009
Neg logit contributions
 Amen-0.009
 fires-0.007
stretched-0.007
 bears-0.006
 smile-0.006
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
ork+0.042
oph+0.042
ally+0.037
handed+0.036
way+0.036
Neg logit contributions
 Amen-0.029
 fires-0.022
stretched-0.022
 bears-0.020
 smile-0.019
Token soft
Token ID2705
Feature activation+6.57e-01

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.003
 passenger-0.003
Token.
Token ID13
Feature activation+5.20e-02

Pos logit contributions
ork+0.022
oph+0.021
way+0.018
ally+0.018
handed+0.018
Neg logit contributions
 Amen-0.019
 fires-0.014
stretched-0.014
 bears-0.013
 passenger-0.012
Token it
Token ID340
Feature activation+1.56e+00

Pos logit contributions
ork+0.008
oph+0.008
way+0.007
handed+0.007
ally+0.007
Neg logit contributions
 Amen-0.006
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token was
Token ID373
Feature activation+2.67e-01

Pos logit contributions
ork+0.051
oph+0.050
handed+0.044
ally+0.043
keeping+0.043
Neg logit contributions
 Amen-0.043
 fires-0.033
stretched-0.032
 bears-0.031
 paddle-0.029
Token all
Token ID477
Feature activation+2.19e+00

Pos logit contributions
ork+0.009
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.005
 bears-0.005
 passenger-0.005
Token dry
Token ID5894
Feature activation+2.11e+00

Pos logit contributions
ork+0.060
oph+0.059
way+0.053
handed+0.051
ally+0.050
Neg logit contributions
 Amen-0.074
 fires-0.056
stretched-0.055
 bears-0.052
 scar-0.050
Token and
Token ID290
Feature activation+7.94e-01

Pos logit contributions
ork+0.079
oph+0.077
ally+0.067
way+0.066
handed+0.066
Neg logit contributions
 Amen-0.049
 fires-0.037
stretched-0.035
 bears-0.034
 sometimes-0.031
Token mud
Token ID17492
Feature activation+4.05e+00

Pos logit contributions
ork+0.026
oph+0.026
way+0.023
ally+0.023
handed+0.022
Neg logit contributions
 Amen-0.023
 fires-0.016
stretched-0.016
 bears-0.015
 passenger-0.014
Token!
Token ID0
Feature activation-1.43e-01

Pos logit contributions
ork+0.136
oph+0.135
ally+0.117
way+0.116
handed+0.115
Neg logit contributions
 Amen-0.108
 fires-0.083
stretched-0.080
 bears-0.077
 scar-0.072
Token
Token ID220
Feature activation-1.20e+00

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 passenger+0.002
 nod+0.002
Neg logit contributions
ork-0.006
oph-0.006
ally-0.005
handed-0.005
way-0.005
Token
Token ID198
Feature activation+1.84e-01

Pos logit contributions
 Amen+0.027
 fires+0.021
 exc+0.019
stretched+0.019
 Sometimes+0.019
Neg logit contributions
oph-0.044
ork-0.040
 doorstep-0.036
ally-0.036
keeping-0.035
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
oph+0.006
ork+0.006
ally+0.005
way+0.005
handed+0.005
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 passenger-0.003
 paddle-0.003
TokenHe
Token ID1544
Feature activation-9.26e-01

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 bears+0.003
 scar+0.003
Neg logit contributions
ork-0.005
oph-0.004
way-0.004
handed-0.004
ally-0.004
Token even
Token ID772
Feature activation-6.02e-01

Pos logit contributions
ork+0.004
oph+0.004
 doorstep+0.004
ally+0.003
n+0.003
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.004
Does-0.004
Token see
Token ID766
Feature activation+5.28e-01

Pos logit contributions
 Amen+0.016
 fires+0.011
stretched+0.011
 bears+0.010
 spoiler+0.009
Neg logit contributions
ork-0.021
oph-0.021
way-0.019
handed-0.018
ally-0.018
Token other
Token ID584
Feature activation+1.92e+00

Pos logit contributions
ork+0.017
oph+0.017
way+0.015
handed+0.015
ally+0.015
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.011
 bears-0.010
 paddle-0.009
Token people
Token ID661
Feature activation+1.57e-02

Pos logit contributions
ork+0.061
oph+0.060
way+0.052
ally+0.052
handed+0.051
Neg logit contributions
 Amen-0.058
 fires-0.043
stretched-0.042
 bears-0.039
 passenger-0.037
Token having
Token ID1719
Feature activation+8.12e-01

Pos logit contributions
ork+0.000
oph+0.000
way+0.000
handed+0.000
ally+0.000
Neg logit contributions
 Amen-0.000
 fires-0.000
stretched-0.000
Does-0.000
 scar-0.000
Token pic
Token ID8301
Feature activation+4.03e+00

Pos logit contributions
ork+0.026
oph+0.026
way+0.022
ally+0.022
handed+0.022
Neg logit contributions
 Amen-0.024
 fires-0.018
stretched-0.017
 bears-0.017
 hope-0.016
Tokenn
Token ID77
Feature activation-1.89e-01

Pos logit contributions
oph+0.066
ork+0.064
handed+0.048
orman+0.043
anger+0.043
Neg logit contributions
 Amen-0.175
stretched-0.143
 yes-0.143
 smile-0.142
 laugh-0.141
Tokenics
Token ID873
Feature activation+1.91e+00

Pos logit contributions
 Amen+0.006
stretched+0.005
 fires+0.005
 exc+0.005
 smile+0.005
Neg logit contributions
oph-0.005
ork-0.005
handed-0.004
 doorstep-0.004
ally-0.004
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
ork+0.064
oph+0.062
way+0.054
ally+0.054
handed+0.054
Neg logit contributions
 Amen-0.054
 fires-0.040
stretched-0.038
 bears-0.036
 passenger-0.034
Token
Token ID198
Feature activation+6.57e-01

Pos logit contributions
ork+0.015
oph+0.013
handed+0.013
lor+0.013
anger+0.013
Neg logit contributions
 Amen-0.007
 Everyday-0.005
 wonder-0.005
 Sometimes-0.005
 nod-0.004
Token
Token ID198
Feature activation+2.75e-01

Pos logit contributions
oph+0.022
ork+0.021
keeping+0.019
handed+0.019
 doorstep+0.018
Neg logit contributions
 Amen-0.018
stretched-0.013
 fires-0.013
 wonder-0.012
 exc-0.012
Token
Token ID220
Feature activation-1.10e+00

Pos logit contributions
ork+0.017
oph+0.017
ally+0.015
ige+0.015
ilt+0.015
Neg logit contributions
 Amen-0.009
 fires-0.005
stretched-0.005
 smile-0.004
 nod-0.004
Token
Token ID198
Feature activation+9.25e-01

Pos logit contributions
 Amen+0.022
 Sometimes+0.015
 exc+0.014
stretched+0.014
 fires+0.014
Neg logit contributions
oph-0.045
ork-0.041
ally-0.037
 doorstep-0.037
keeping-0.036
Token
Token ID198
Feature activation+3.42e-01

Pos logit contributions
oph+0.033
ork+0.031
ally+0.028
ige+0.028
 doorstep+0.028
Neg logit contributions
 Amen-0.023
stretched-0.015
 fires-0.014
 sled-0.014
He-0.014
TokenWhen
Token ID2215
Feature activation-8.54e-01

Pos logit contributions
ork+0.011
oph+0.011
way+0.009
handed+0.009
ally+0.009
Neg logit contributions
 Amen-0.010
 fires-0.008
stretched-0.008
 bears-0.007
 scar-0.007
Token the
Token ID262
Feature activation+2.20e-01

Pos logit contributions
 Amen+0.020
 fires+0.013
stretched+0.013
 bears+0.012
 passenger+0.011
Neg logit contributions
ork-0.033
oph-0.032
way-0.029
ally-0.029
handed-0.029
Token fog
Token ID19558
Feature activation+3.96e+00

Pos logit contributions
ork+0.007
oph+0.007
way+0.006
handed+0.006
ally+0.006
Neg logit contributions
 Amen-0.006
 fires-0.005
stretched-0.004
 spoiler-0.004
 bears-0.004
Token was
Token ID373
Feature activation+5.29e-01

Pos logit contributions
oph+0.136
ork+0.130
handed+0.116
ige+0.113
ally+0.113
Neg logit contributions
 Amen-0.099
 bears-0.074
 fires-0.074
stretched-0.074
 paddle-0.072
Token gone
Token ID3750
Feature activation+1.12e+00

Pos logit contributions
ork+0.017
oph+0.017
handed+0.015
ally+0.014
way+0.014
Neg logit contributions
 Amen-0.015
 fires-0.012
stretched-0.012
 bears-0.011
 smile-0.011
Token,
Token ID11
Feature activation+1.25e+00

Pos logit contributions
ork+0.044
oph+0.043
handed+0.039
ally+0.038
way+0.038
Neg logit contributions
 Amen-0.025
 fires-0.017
stretched-0.016
 bears-0.015
 smile-0.014
Token all
Token ID477
Feature activation+1.14e+00

Pos logit contributions
ork+0.046
oph+0.045
way+0.040
handed+0.039
ally+0.039
Neg logit contributions
 Amen-0.032
 fires-0.022
stretched-0.021
 bears-0.019
 passenger-0.018
Token his
Token ID465
Feature activation+2.52e+00

Pos logit contributions
ork+0.036
oph+0.036
way+0.033
ally+0.032
handed+0.032
Neg logit contributions
 Amen-0.034
 fires-0.023
stretched-0.023
 scar-0.022
 argue-0.021
Token soon
Token ID2582
Feature activation-8.77e-01

Pos logit contributions
 Amen+0.001
 bears+0.001
 fires+0.001
 sometimes+0.001
 scar+0.001
Neg logit contributions
ork-0.004
oph-0.003
handed-0.003
way-0.003
lor-0.003
Token the
Token ID262
Feature activation+4.53e-01

Pos logit contributions
 Amen+0.009
 bears+0.008
 smile+0.008
 fires+0.008
 sometimes+0.007
Neg logit contributions
ork-0.038
handed-0.035
oph-0.035
way-0.035
 doorstep-0.035
Token dough
Token ID15756
Feature activation+1.63e+00

Pos logit contributions
ork+0.014
oph+0.014
handed+0.012
way+0.012
ally+0.012
Neg logit contributions
 Amen-0.014
 fires-0.010
 bears-0.010
stretched-0.010
 smile-0.010
Token was
Token ID373
Feature activation+3.98e-01

Pos logit contributions
oph+0.052
ork+0.052
handed+0.046
way+0.045
ally+0.045
Neg logit contributions
 Amen-0.043
stretched-0.033
 fires-0.033
 smile-0.032
 bears-0.032
Token all
Token ID477
Feature activation+2.04e+00

Pos logit contributions
oph+0.013
ork+0.013
handed+0.012
way+0.011
ally+0.011
Neg logit contributions
 Amen-0.011
stretched-0.009
 fires-0.009
 smile-0.008
 bears-0.008
Token back
Token ID736
Feature activation+3.94e+00

Pos logit contributions
ork+0.064
oph+0.061
ally+0.051
way+0.051
handed+0.051
Neg logit contributions
 Amen-0.062
 fires-0.050
stretched-0.048
 smile-0.046
 bears-0.046
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
ork+0.141
oph+0.140
ally+0.115
lor+0.114
handed+0.114
Neg logit contributions
 Amen-0.086
 smile-0.073
 fires-0.072
stretched-0.071
 hope-0.067
Token
Token ID198
Feature activation+5.97e-01

Pos logit contributions
ork+0.016
oph+0.016
way+0.015
handed+0.014
 doorstep+0.014
Neg logit contributions
 Amen-0.008
 Sometimes-0.005
 Everyday-0.004
stretched-0.004
 smile-0.004
Token
Token ID198
Feature activation+1.99e-01

Pos logit contributions
oph+0.020
ork+0.019
way+0.017
handed+0.017
ally+0.017
Neg logit contributions
 Amen-0.017
stretched-0.012
 fires-0.012
 exc-0.011
 smile-0.011
TokenThe
Token ID464
Feature activation-7.58e-01

Pos logit contributions
ork+0.006
oph+0.006
way+0.005
ally+0.005
handed+0.005
Neg logit contributions
 Amen-0.006
 fires-0.005
stretched-0.005
 bears-0.004
 scar-0.004
Token little
Token ID1310
Feature activation+1.15e+00

Pos logit contributions
 Amen+0.027
 fires+0.021
stretched+0.021
 bears+0.019
 paddle+0.019
Neg logit contributions
ork-0.020
oph-0.020
ally-0.017
way-0.017
handed-0.016
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
 Amen+0.011
 fires+0.008
stretched+0.008
 bears+0.007
 smile+0.007
Neg logit contributions
ork-0.018
oph-0.017
handed-0.015
ally-0.015
way-0.015
Token As
Token ID1081
Feature activation-1.63e+00

Pos logit contributions
ork+0.015
oph+0.015
way+0.013
handed+0.013
ally+0.013
Neg logit contributions
 Amen-0.013
 fires-0.009
stretched-0.009
 bears-0.008
 passenger-0.008
Token the
Token ID262
Feature activation+4.09e-01

Pos logit contributions
 Amen+0.039
 fires+0.027
stretched+0.026
 bears+0.024
 scar+0.022
Neg logit contributions
ork-0.062
oph-0.061
way-0.054
ally-0.054
handed-0.054
Token dirt
Token ID13647
Feature activation+3.23e+00

Pos logit contributions
ork+0.012
oph+0.011
way+0.010
ally+0.010
handed+0.010
Neg logit contributions
 Amen-0.014
 fires-0.010
stretched-0.010
 passenger-0.009
 bears-0.009
Token and
Token ID290
Feature activation+9.16e-01

Pos logit contributions
ork+0.102
oph+0.098
way+0.087
ally+0.085
handed+0.084
Neg logit contributions
 Amen-0.099
 fires-0.073
stretched-0.071
 bears-0.066
 passenger-0.065
Token mud
Token ID17492
Feature activation+3.92e+00

Pos logit contributions
oph+0.027
ork+0.026
ally+0.023
way+0.023
keeping+0.023
Neg logit contributions
 Amen-0.029
stretched-0.021
 fires-0.019
 passenger-0.019
 exc-0.018
Token washed
Token ID18989
Feature activation+1.13e+00

Pos logit contributions
ork+0.126
oph+0.122
way+0.107
ally+0.106
handed+0.105
Neg logit contributions
 Amen-0.117
 fires-0.086
stretched-0.084
 bears-0.078
 passenger-0.076
Token away
Token ID1497
Feature activation+1.57e+00

Pos logit contributions
ork+0.041
oph+0.041
way+0.036
handed+0.036
ally+0.035
Neg logit contributions
 Amen-0.028
 fires-0.021
stretched-0.019
 bears-0.019
 hope-0.017
Token,
Token ID11
Feature activation+7.36e-01

Pos logit contributions
ork+0.057
oph+0.056
way+0.050
ally+0.049
handed+0.049
Neg logit contributions
 Amen-0.040
 fires-0.028
stretched-0.027
 bears-0.025
 passenger-0.024
Token Pe
Token ID2631
Feature activation+4.17e-01

Pos logit contributions
ork+0.025
oph+0.025
way+0.022
ally+0.022
handed+0.021
Neg logit contributions
 Amen-0.020
 fires-0.015
stretched-0.014
 bears-0.014
 scar-0.013
Tokenep
Token ID538
Feature activation+8.10e-01

Pos logit contributions
ork+0.015
oph+0.015
way+0.013
handed+0.013
ally+0.012
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.007
 bears-0.007
 scar-0.007
Token sun
Token ID4252
Feature activation+1.96e+00

Pos logit contributions
 Amen+0.020
 fires+0.012
stretched+0.011
 bears+0.010
 passenger+0.009
Neg logit contributions
ork-0.045
oph-0.044
way-0.041
ally-0.040
handed-0.040
Token was
Token ID373
Feature activation+8.65e-01

Pos logit contributions
ork+0.060
oph+0.058
way+0.051
ally+0.050
handed+0.050
Neg logit contributions
 Amen-0.061
 fires-0.046
stretched-0.045
 bears-0.042
 passenger-0.041
Token shining
Token ID22751
Feature activation+3.45e-01

Pos logit contributions
ork+0.028
oph+0.028
way+0.025
ally+0.025
handed+0.024
Neg logit contributions
 Amen-0.024
 fires-0.017
stretched-0.016
 bears-0.016
 passenger-0.015
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
ork+0.011
oph+0.011
way+0.010
ally+0.010
handed+0.009
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.006
 passenger-0.006
Token the
Token ID262
Feature activation+9.11e-01

Pos logit contributions
ork+0.035
oph+0.033
handed+0.030
way+0.029
ally+0.029
Neg logit contributions
 Amen-0.029
 fires-0.022
stretched-0.020
 bears-0.020
 smile-0.019
Token sand
Token ID6450
Feature activation+3.91e+00

Pos logit contributions
ork+0.039
oph+0.037
ally+0.034
handed+0.033
way+0.033
Neg logit contributions
 Amen-0.017
 fires-0.011
 smile-0.011
 paddle-0.011
 wave-0.011
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
ork+0.122
oph+0.120
ally+0.103
handed+0.103
way+0.103
Neg logit contributions
 Amen-0.116
 fires-0.089
stretched-0.087
 bears-0.082
 smile-0.079
Token warm
Token ID5814
Feature activation+1.82e+00

Pos logit contributions
ork+0.035
oph+0.035
way+0.031
ally+0.030
handed+0.029
Neg logit contributions
 Amen-0.032
 fires-0.023
stretched-0.022
 bears-0.021
 passenger-0.021
Token.
Token ID13
Feature activation+3.52e-01

Pos logit contributions
ork+0.063
oph+0.061
way+0.054
handed+0.054
ally+0.054
Neg logit contributions
 Amen-0.049
 fires-0.036
stretched-0.035
 bears-0.033
 smile-0.031
Token He
Token ID679
Feature activation-6.93e-01

Pos logit contributions
ork+0.013
oph+0.012
anger+0.011
ally+0.011
ilt+0.011
Neg logit contributions
 Amen-0.010
 fires-0.006
stretched-0.006
 wonder-0.006
 smile-0.006
Token felt
Token ID2936
Feature activation-5.09e-01

Pos logit contributions
 Amen+0.020
 fires+0.015
stretched+0.014
 bears+0.013
 passenger+0.013
Neg logit contributions
ork-0.023
oph-0.022
way-0.019
ally-0.019
handed-0.019
Token felt
Token ID2936
Feature activation-8.53e-01

Pos logit contributions
 Amen+0.015
 fires+0.011
stretched+0.011
 bears+0.010
 passenger+0.009
Neg logit contributions
ork-0.016
oph-0.015
way-0.013
ally-0.013
handed-0.013
Token really
Token ID1107
Feature activation+3.92e-01

Pos logit contributions
 Amen+0.025
 fires+0.018
stretched+0.017
 bears+0.017
 passenger+0.017
Neg logit contributions
ork-0.027
oph-0.026
handed-0.024
way-0.024
ally-0.023
Token sad
Token ID6507
Feature activation-3.82e-01

Pos logit contributions
ork+0.015
oph+0.015
way+0.013
ally+0.013
handed+0.013
Neg logit contributions
 Amen-0.009
 fires-0.006
stretched-0.006
 bears-0.006
 passenger-0.005
Token because
Token ID780
Feature activation+5.69e-01

Pos logit contributions
 Amen+0.012
 fires+0.008
stretched+0.008
 bears+0.007
 passenger+0.007
Neg logit contributions
ork-0.012
oph-0.012
way-0.011
ally-0.010
handed-0.010
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
ork+0.020
oph+0.019
way+0.017
ally+0.017
handed+0.017
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.011
 bears-0.010
 smile-0.010
Token mud
Token ID17492
Feature activation+3.89e+00

Pos logit contributions
ork+0.041
oph+0.040
way+0.036
handed+0.035
ally+0.035
Neg logit contributions
 Amen-0.029
 fires-0.021
 bears-0.020
stretched-0.020
 scar-0.020
Token had
Token ID550
Feature activation+2.39e+00

Pos logit contributions
oph+0.124
ork+0.122
handed+0.105
way+0.104
ally+0.103
Neg logit contributions
 Amen-0.106
 fires-0.084
stretched-0.084
 bears-0.080
 smile-0.077
Token made
Token ID925
Feature activation+2.21e-01

Pos logit contributions
oph+0.071
ork+0.069
handed+0.062
ally+0.061
way+0.058
Neg logit contributions
 Amen-0.059
stretched-0.058
 fires-0.055
 hope-0.053
 smile-0.053
Token her
Token ID607
Feature activation+1.15e+00

Pos logit contributions
oph+0.008
ork+0.008
handed+0.007
way+0.007
ally+0.007
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.003
 hope-0.003
Token wool
Token ID25749
Feature activation+1.04e+00

Pos logit contributions
ork+0.040
oph+0.037
way+0.034
 doorstep+0.034
handed+0.033
Neg logit contributions
 Amen-0.034
 fires-0.024
stretched-0.022
 bears-0.020
 passenger-0.020
Token very
Token ID845
Feature activation+1.08e+00

Pos logit contributions
ork+0.032
oph+0.028
way+0.027
 doorstep+0.026
handed+0.026
Neg logit contributions
 Amen-0.035
 fires-0.024
stretched-0.023
 bears-0.022
 passenger-0.022
Token
Token ID220
Feature activation-1.19e+00

Pos logit contributions
ork+0.007
oph+0.007
ally+0.006
handed+0.006
way+0.006
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.002
 nod-0.002
 smile-0.002
Token
Token ID198
Feature activation+5.95e-01

Pos logit contributions
 Amen+0.025
 fires+0.017
 Sometimes+0.016
 exc+0.016
 sled+0.016
Neg logit contributions
oph-0.048
ork-0.043
ally-0.040
 doorstep-0.039
handed-0.038
Token
Token ID198
Feature activation+2.32e-01

Pos logit contributions
oph+0.021
ork+0.020
ally+0.018
way+0.017
handed+0.017
Neg logit contributions
 Amen-0.016
stretched-0.011
 fires-0.011
 exc-0.010
 smile-0.010
TokenWhen
Token ID2215
Feature activation-8.89e-01

Pos logit contributions
ork+0.007
oph+0.007
way+0.006
ally+0.006
handed+0.006
Neg logit contributions
 Amen-0.007
 fires-0.005
stretched-0.005
 bears-0.005
 passenger-0.005
Token the
Token ID262
Feature activation+4.84e-01

Pos logit contributions
 Amen+0.021
 fires+0.015
stretched+0.014
 bears+0.013
 hope+0.012
Neg logit contributions
ork-0.034
oph-0.033
handed-0.030
ally-0.030
way-0.029
Token rain
Token ID6290
Feature activation+3.85e+00

Pos logit contributions
ork+0.016
oph+0.016
way+0.014
handed+0.014
ally+0.014
Neg logit contributions
 Amen-0.014
 fires-0.010
stretched-0.010
 bears-0.009
 scar-0.009
Token stopped
Token ID5025
Feature activation+1.04e+00

Pos logit contributions
oph+0.142
ork+0.141
handed+0.137
ige+0.132
keeping+0.131
Neg logit contributions
 Amen-0.064
 smile-0.056
 sometimes-0.056
 ne-0.053
 hon-0.053
Token,
Token ID11
Feature activation+7.15e-01

Pos logit contributions
ork+0.033
oph+0.029
way+0.029
ally+0.028
handed+0.026
Neg logit contributions
 Amen-0.032
stretched-0.022
 fires-0.021
 passenger-0.021
 bears-0.020
Token the
Token ID262
Feature activation+4.85e-01

Pos logit contributions
ork+0.028
oph+0.027
handed+0.024
ally+0.024
way+0.024
Neg logit contributions
 Amen-0.016
 fires-0.011
stretched-0.010
 bears-0.010
 paddle-0.009
Token farmer
Token ID18739
Feature activation+3.62e-01

Pos logit contributions
ork+0.018
oph+0.017
way+0.015
handed+0.015
ally+0.015
Neg logit contributions
 Amen-0.013
 fires-0.009
 bears-0.008
stretched-0.008
 scar-0.008
Token and
Token ID290
Feature activation-4.08e-01

Pos logit contributions
ork+0.012
oph+0.012
way+0.011
handed+0.010
ally+0.010
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.007
 smile-0.006
Token in
Token ID287
Feature activation-1.13e+00

Pos logit contributions
 Amen+0.025
 fires+0.018
stretched+0.017
 bears+0.016
 passenger+0.015
Neg logit contributions
ork-0.033
oph-0.032
way-0.028
ally-0.028
handed-0.028
Token need
Token ID761
Feature activation-3.33e-01

Pos logit contributions
 Amen+0.028
stretched+0.019
 fires+0.019
 bears+0.017
 paddle+0.017
Neg logit contributions
ork-0.042
oph-0.040
handed-0.036
way-0.036
ally-0.035
Token.
Token ID13
Feature activation+3.17e-01

Pos logit contributions
 Amen+0.008
 fires+0.006
 hope+0.005
 sometimes+0.005
 bears+0.005
Neg logit contributions
oph-0.013
ork-0.012
ally-0.011
liv-0.011
way-0.011
Token We
Token ID775
Feature activation+1.16e+00

Pos logit contributions
ork+0.010
oph+0.010
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.007
 scar-0.006
Token all
Token ID477
Feature activation-5.05e-04

Pos logit contributions
ork+0.040
oph+0.037
way+0.035
n+0.034
ally+0.034
Neg logit contributions
 Amen-0.027
stretched-0.022
 fires-0.021
 sled-0.019
 spoiler-0.019
Token belong
Token ID5594
Feature activation+3.85e+00

Pos logit contributions
 Amen+0.000
stretched+0.000
 fires+0.000
 sled+0.000
 scar+0.000
Neg logit contributions
ork-0.000
oph-0.000
way-0.000
handed-0.000
ally-0.000
Token to
Token ID284
Feature activation+2.80e-02

Pos logit contributions
ork+0.124
oph+0.123
ally+0.106
way+0.105
handed+0.101
Neg logit contributions
 Amen-0.111
 fires-0.087
 hope-0.081
 bears-0.080
stretched-0.079
Token one
Token ID530
Feature activation-9.32e-01

Pos logit contributions
ork+0.001
oph+0.001
way+0.001
ally+0.001
handed+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
 bears-0.001
 hope-0.000
 sometimes-0.000
Token big
Token ID1263
Feature activation-1.88e-01

Pos logit contributions
 Amen+0.028
stretched+0.021
 fires+0.021
 bears+0.019
 paddle+0.019
Neg logit contributions
ork-0.029
oph-0.029
way-0.025
handed-0.025
ally-0.025
Token family
Token ID1641
Feature activation-1.04e+00

Pos logit contributions
 Amen+0.005
stretched+0.004
 paddle+0.003
 fires+0.003
Does+0.003
Neg logit contributions
ork-0.006
oph-0.005
handed-0.005
keeping-0.005
 doorstep-0.005
Token and
Token ID290
Feature activation-1.41e-01

Pos logit contributions
 Amen+0.032
stretched+0.024
 fires+0.024
 bears+0.021
 paddle+0.021
Neg logit contributions
ork-0.032
oph-0.031
way-0.027
handed-0.027
ally-0.027
Token and
Token ID290
Feature activation+5.76e-01

Pos logit contributions
 Amen+0.012
 fires+0.008
stretched+0.008
 bears+0.008
 passenger+0.008
Neg logit contributions
ork-0.012
oph-0.011
way-0.010
ally-0.010
handed-0.009
Token waited
Token ID13488
Feature activation-3.13e-01

Pos logit contributions
ork+0.021
oph+0.020
handed+0.018
way+0.018
ally+0.017
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.010
 hope-0.010
 bears-0.010
Token and
Token ID290
Feature activation+4.46e-01

Pos logit contributions
 Amen+0.009
 fires+0.007
stretched+0.006
 bears+0.006
 passenger+0.006
Neg logit contributions
ork-0.010
oph-0.010
way-0.009
ally-0.009
handed-0.009
Token soon
Token ID2582
Feature activation-6.05e-01

Pos logit contributions
ork+0.016
oph+0.015
handed+0.014
ally+0.014
way+0.014
Neg logit contributions
 Amen-0.012
 fires-0.009
 hope-0.008
stretched-0.008
 smile-0.008
Token the
Token ID262
Feature activation+1.76e-01

Pos logit contributions
 Amen+0.006
stretched+0.005
 smile+0.005
 fires+0.005
 bears+0.005
Neg logit contributions
ork-0.026
oph-0.026
handed-0.026
 doorstep-0.025
keeping-0.024
Token mud
Token ID17492
Feature activation+3.83e+00

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.006
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token and
Token ID290
Feature activation+9.58e-01

Pos logit contributions
oph+0.132
ork+0.126
handed+0.114
ally+0.110
way+0.107
Neg logit contributions
 Amen-0.092
 fires-0.077
stretched-0.075
 bears-0.071
 paddle-0.071
Token the
Token ID262
Feature activation+3.22e-01

Pos logit contributions
ork+0.033
oph+0.033
way+0.029
ally+0.029
handed+0.028
Neg logit contributions
 Amen-0.026
 fires-0.018
stretched-0.018
 bears-0.016
 passenger-0.016
Token p
Token ID279
Feature activation+1.81e+00

Pos logit contributions
ork+0.009
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.008
 bears-0.007
 passenger-0.007
Tokenudd
Token ID4185
Feature activation-7.12e-02

Pos logit contributions
oph+0.052
ork+0.045
keeping+0.042
handed+0.042
orman+0.040
Neg logit contributions
 Amen-0.050
stretched-0.045
 fires-0.045
 sled-0.042
 paddle-0.041
Tokenles
Token ID829
Feature activation+6.18e-01

Pos logit contributions
 Amen+0.002
 fires+0.002
 bears+0.001
stretched+0.001
 paddle+0.001
Neg logit contributions
oph-0.002
ork-0.002
 doorstep-0.002
handed-0.002
keeping-0.002
Token
Token ID198
Feature activation-3.54e-03

Pos logit contributions
ork+0.015
oph+0.014
anger+0.014
keeping+0.014
 doorstep+0.013
Neg logit contributions
 Amen-0.009
stretched-0.006
He-0.005
Every-0.005
 Everyday-0.005
TokenOnce
Token ID7454
Feature activation-1.04e+00

Pos logit contributions
 Amen+0.000
stretched+0.000
 fires+0.000
 sometimes+0.000
 yes+0.000
Neg logit contributions
ork-0.000
oph-0.000
keeping-0.000
anger-0.000
handed-0.000
Token they
Token ID484
Feature activation+7.56e-01

Pos logit contributions
 Amen+0.021
 fires+0.015
 sometimes+0.013
stretched+0.013
 smile+0.013
Neg logit contributions
ork-0.040
oph-0.040
handed-0.038
keeping-0.036
lor-0.035
Token were
Token ID547
Feature activation+1.04e+00

Pos logit contributions
ork+0.025
oph+0.024
way+0.021
handed+0.021
ally+0.020
Neg logit contributions
 Amen-0.022
 fires-0.017
stretched-0.016
 bears-0.015
 smile-0.015
Token all
Token ID477
Feature activation+8.64e-01

Pos logit contributions
ork+0.034
oph+0.033
ally+0.029
way+0.029
handed+0.028
Neg logit contributions
 Amen-0.030
 fires-0.023
stretched-0.022
 bears-0.022
 smile-0.021
Token back
Token ID736
Feature activation+3.82e+00

Pos logit contributions
ork+0.024
oph+0.024
way+0.022
handed+0.022
keeping+0.021
Neg logit contributions
 Amen-0.027
stretched-0.020
 fires-0.020
Does-0.019
 spoiler-0.018
Token home
Token ID1363
Feature activation+3.00e+00

Pos logit contributions
ork+0.135
oph+0.133
lor+0.111
handed+0.110
ally+0.110
Neg logit contributions
 Amen-0.088
 smile-0.077
 hope-0.072
 fires-0.071
stretched-0.069
Token,
Token ID11
Feature activation+7.16e-01

Pos logit contributions
ork+0.121
oph+0.121
ally+0.106
handed+0.106
way+0.105
Neg logit contributions
 Amen-0.059
stretched-0.039
 fires-0.038
 smile-0.037
 bears-0.035
Token Amy
Token ID14235
Feature activation+1.66e+00

Pos logit contributions
ork+0.018
oph+0.018
way+0.015
handed+0.015
ally+0.015
Neg logit contributions
 Amen-0.026
 fires-0.020
stretched-0.020
 bears-0.019
 smile-0.019
Token thanked
Token ID26280
Feature activation-9.10e-01

Pos logit contributions
ork+0.048
oph+0.047
way+0.040
ally+0.040
handed+0.040
Neg logit contributions
 Amen-0.054
 fires-0.041
stretched-0.040
 bears-0.038
 passenger-0.037
Token her
Token ID607
Feature activation-8.68e-01

Pos logit contributions
 Amen+0.029
 fires+0.022
stretched+0.022
 passenger+0.020
 paddle+0.020
Neg logit contributions
oph-0.027
ork-0.027
ally-0.023
way-0.022
handed-0.022
Token was
Token ID373
Feature activation+7.90e-01

Pos logit contributions
oph+0.069
ork+0.069
keeping+0.062
handed+0.062
ally+0.060
Neg logit contributions
 Amen-0.059
stretched-0.045
 fires-0.044
 bears-0.043
 smile-0.042
Token almost
Token ID2048
Feature activation+1.74e+00

Pos logit contributions
ork+0.023
oph+0.021
handed+0.019
keeping+0.018
ally+0.018
Neg logit contributions
 Amen-0.026
 fires-0.022
stretched-0.021
 smile-0.020
 bears-0.019
Token dark
Token ID3223
Feature activation+2.03e+00

Pos logit contributions
ork+0.056
oph+0.053
handed+0.049
keeping+0.047
ally+0.046
Neg logit contributions
 Amen-0.050
 fires-0.041
stretched-0.040
 smile-0.038
 hope-0.035
Token,
Token ID11
Feature activation+1.35e+00

Pos logit contributions
ork+0.079
oph+0.077
handed+0.068
ally+0.068
way+0.067
Neg logit contributions
 Amen-0.045
 fires-0.033
stretched-0.031
 bears-0.029
 smile-0.027
Token the
Token ID262
Feature activation+5.22e-01

Pos logit contributions
ork+0.038
oph+0.037
way+0.032
ally+0.032
handed+0.031
Neg logit contributions
 Amen-0.046
 fires-0.035
stretched-0.034
 bears-0.032
 passenger-0.031
Token fog
Token ID19558
Feature activation+3.82e+00

Pos logit contributions
ork+0.016
oph+0.015
way+0.013
handed+0.013
ally+0.013
Neg logit contributions
 Amen-0.016
 fires-0.012
stretched-0.012
 bears-0.011
 scar-0.011
Token finally
Token ID3443
Feature activation+1.19e+00

Pos logit contributions
oph+0.122
ork+0.119
handed+0.104
ally+0.103
way+0.099
Neg logit contributions
 Amen-0.110
stretched-0.084
 fires-0.083
 smile-0.077
 bears-0.077
Token started
Token ID2067
Feature activation+1.85e+00

Pos logit contributions
ork+0.043
handed+0.042
keeping+0.041
oph+0.041
ally+0.038
Neg logit contributions
 wave-0.021
stretched-0.021
 smile-0.020
 Amen-0.020
 ne-0.018
Token to
Token ID284
Feature activation+5.65e-02

Pos logit contributions
ork+0.049
oph+0.047
way+0.041
ally+0.040
handed+0.039
Neg logit contributions
 Amen-0.066
 fires-0.051
stretched-0.049
 bears-0.047
 passenger-0.046
Token clear
Token ID1598
Feature activation+5.76e-01

Pos logit contributions
oph+0.002
ork+0.002
way+0.002
 doorstep+0.002
handed+0.002
Neg logit contributions
 Amen-0.002
stretched-0.001
 fires-0.001
 bears-0.001
 passenger-0.001
Token and
Token ID290
Feature activation-4.19e-01

Pos logit contributions
ork+0.017
oph+0.016
way+0.015
handed+0.014
ally+0.014
Neg logit contributions
 Amen-0.019
 fires-0.013
stretched-0.013
 passenger-0.013
 exc-0.013
Token because
Token ID780
Feature activation+1.52e-01

Pos logit contributions
ork+0.007
oph+0.007
way+0.006
ally+0.006
handed+0.006
Neg logit contributions
 Amen-0.006
 fires-0.004
stretched-0.004
 bears-0.004
 smile-0.004
Token she
Token ID673
Feature activation+9.91e-01

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.003
 passenger-0.003
Token knew
Token ID2993
Feature activation+4.28e-01

Pos logit contributions
ork+0.033
oph+0.032
way+0.028
ally+0.028
handed+0.028
Neg logit contributions
 Amen-0.028
 fires-0.021
stretched-0.020
 bears-0.019
 passenger-0.018
Token she
Token ID673
Feature activation+8.74e-01

Pos logit contributions
ork+0.015
oph+0.015
way+0.013
ally+0.013
handed+0.013
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.008
 bears-0.008
 hope-0.007
Token was
Token ID373
Feature activation-3.76e-01

Pos logit contributions
ork+0.029
oph+0.029
way+0.025
handed+0.025
ally+0.025
Neg logit contributions
 Amen-0.025
 fires-0.018
stretched-0.017
 bears-0.017
 hope-0.016
Token supposed
Token ID4385
Feature activation+3.82e+00

Pos logit contributions
 Amen+0.009
 fires+0.006
stretched+0.005
 bears+0.005
 smile+0.005
Neg logit contributions
ork-0.015
oph-0.015
way-0.013
ally-0.013
handed-0.013
Token to
Token ID284
Feature activation+4.63e-01

Pos logit contributions
ork+0.113
oph+0.111
ally+0.094
way+0.093
handed+0.092
Neg logit contributions
 Amen-0.122
 fires-0.096
stretched-0.091
 bears-0.087
 hope-0.085
Token clean
Token ID3424
Feature activation+3.78e-01

Pos logit contributions
ork+0.018
oph+0.018
way+0.016
ally+0.015
handed+0.015
Neg logit contributions
 Amen-0.011
 fires-0.007
stretched-0.007
 smile-0.007
 hope-0.007
Token her
Token ID607
Feature activation-7.71e-01

Pos logit contributions
ork+0.012
oph+0.011
way+0.010
ally+0.010
handed+0.010
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.008
 bears-0.008
 smile-0.008
Token room
Token ID2119
Feature activation-8.52e-01

Pos logit contributions
 Amen+0.025
 fires+0.020
stretched+0.019
 bears+0.018
 smile+0.017
Neg logit contributions
ork-0.022
oph-0.022
way-0.019
ally-0.018
handed-0.018
Token.
Token ID13
Feature activation+4.22e-01

Pos logit contributions
 Amen+0.026
 fires+0.019
stretched+0.018
 bears+0.017
 passenger+0.017
Neg logit contributions
ork-0.027
oph-0.026
way-0.023
handed-0.023
ally-0.023
Token pretty
Token ID2495
Feature activation+1.50e+00

Pos logit contributions
ork+0.047
oph+0.045
way+0.040
ally+0.039
handed+0.039
Neg logit contributions
 Amen-0.050
 fires-0.037
stretched-0.037
 bears-0.034
 passenger-0.033
Token flowers
Token ID12734
Feature activation+2.23e-01

Pos logit contributions
ork+0.042
oph+0.041
way+0.036
ally+0.035
handed+0.034
Neg logit contributions
 Amen-0.052
 fires-0.038
stretched-0.037
 passenger-0.035
 exc-0.034
Token.
Token ID13
Feature activation+5.13e-02

Pos logit contributions
ork+0.007
oph+0.006
way+0.006
handed+0.006
ally+0.006
Neg logit contributions
 Amen-0.007
 fires-0.005
stretched-0.005
 passenger-0.005
 spoiler-0.005
Token But
Token ID887
Feature activation-8.44e-01

Pos logit contributions
ork+0.002
oph+0.002
ally+0.002
way+0.002
handed+0.002
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.000
 passenger-0.000
Token the
Token ID262
Feature activation-6.41e-02

Pos logit contributions
 Amen+0.020
 fires+0.014
stretched+0.013
 bears+0.012
 passenger+0.011
Neg logit contributions
ork-0.032
oph-0.031
way-0.028
ally-0.028
handed-0.028
Token mud
Token ID17492
Feature activation+3.81e+00

Pos logit contributions
 Amen+0.002
 fires+0.002
stretched+0.002
 passenger+0.001
 spoiler+0.001
Neg logit contributions
ork-0.002
oph-0.002
way-0.002
ally-0.002
handed-0.002
Token was
Token ID373
Feature activation+7.70e-01

Pos logit contributions
oph+0.118
ork+0.117
handed+0.101
way+0.099
ally+0.099
Neg logit contributions
 Amen-0.108
 fires-0.086
stretched-0.084
 bears-0.082
 smile-0.077
Token still
Token ID991
Feature activation+9.74e-01

Pos logit contributions
ork+0.028
oph+0.027
way+0.024
ally+0.024
handed+0.023
Neg logit contributions
 Amen-0.020
 fires-0.014
stretched-0.013
 bears-0.012
 passenger-0.012
Token in
Token ID287
Feature activation+7.99e-01

Pos logit contributions
ork+0.032
oph+0.031
way+0.028
ally+0.027
handed+0.026
Neg logit contributions
 Amen-0.029
 fires-0.020
stretched-0.020
 passenger-0.018
 bears-0.018
Token the
Token ID262
Feature activation+7.12e-01

Pos logit contributions
ork+0.027
oph+0.027
way+0.024
handed+0.024
ally+0.023
Neg logit contributions
 Amen-0.022
 fires-0.015
stretched-0.015
 bears-0.014
 passenger-0.013
Token way
Token ID835
Feature activation+1.64e+00

Pos logit contributions
ork+0.020
oph+0.019
way+0.016
ally+0.016
handed+0.016
Neg logit contributions
 Amen-0.024
 fires-0.019
stretched-0.018
 bears-0.018
 passenger-0.017
Token
Token ID220
Feature activation-1.18e+00

Pos logit contributions
ork+0.011
oph+0.011
handed+0.010
way+0.009
anger+0.009
Neg logit contributions
 Amen-0.007
 fires-0.004
 Sometimes-0.004
stretched-0.004
 bears-0.004
Token
Token ID198
Feature activation+5.76e-01

Pos logit contributions
 Amen+0.023
 Sometimes+0.015
 fires+0.015
 exc+0.014
stretched+0.013
Neg logit contributions
oph-0.048
ork-0.043
 doorstep-0.041
ally-0.040
keeping-0.040
Token
Token ID198
Feature activation+1.86e-01

Pos logit contributions
oph+0.020
ork+0.019
ally+0.016
way+0.016
handed+0.016
Neg logit contributions
 Amen-0.017
stretched-0.011
 fires-0.011
 exc-0.010
Does-0.010
TokenWhen
Token ID2215
Feature activation-8.08e-01

Pos logit contributions
ork+0.006
oph+0.006
way+0.005
ally+0.005
handed+0.005
Neg logit contributions
 Amen-0.006
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
 Amen+0.021
 fires+0.015
 bears+0.014
stretched+0.014
 hope+0.013
Neg logit contributions
ork-0.029
oph-0.029
handed-0.026
ally-0.025
way-0.025
Token rain
Token ID6290
Feature activation+3.81e+00

Pos logit contributions
ork+0.011
oph+0.011
way+0.009
ally+0.009
handed+0.009
Neg logit contributions
 Amen-0.014
 fires-0.011
stretched-0.011
 passenger-0.010
 paddle-0.010
Token stopped
Token ID5025
Feature activation+1.06e+00

Pos logit contributions
ork+0.142
oph+0.139
handed+0.139
keeping+0.133
ige+0.128
Neg logit contributions
 Amen-0.063
 sometimes-0.060
 smile-0.057
stretched-0.054
 zoom-0.052
Token,
Token ID11
Feature activation+8.40e-01

Pos logit contributions
ork+0.034
oph+0.032
way+0.030
ally+0.030
handed+0.028
Neg logit contributions
 Amen-0.031
 fires-0.021
stretched-0.021
 passenger-0.020
 bears-0.019
Token they
Token ID484
Feature activation+6.79e-01

Pos logit contributions
ork+0.030
oph+0.029
handed+0.026
ally+0.026
way+0.026
Neg logit contributions
 Amen-0.022
 fires-0.016
stretched-0.015
 bears-0.015
 passenger-0.013
Token could
Token ID714
Feature activation+4.26e-01

Pos logit contributions
ork+0.025
oph+0.024
handed+0.021
way+0.021
ally+0.021
Neg logit contributions
 Amen-0.017
stretched-0.012
 fires-0.012
 smile-0.011
 bears-0.011
Token still
Token ID991
Feature activation-1.15e-01

Pos logit contributions
ork+0.016
oph+0.015
way+0.014
ally+0.013
handed+0.013
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.007
 bears-0.007
 scar-0.006
Token and
Token ID290
Feature activation+5.68e-01

Pos logit contributions
ork+0.011
oph+0.011
way+0.010
ally+0.010
handed+0.009
Neg logit contributions
 Amen-0.009
stretched-0.006
 fires-0.006
 bears-0.006
 passenger-0.006
Token bright
Token ID6016
Feature activation+2.26e-01

Pos logit contributions
ork+0.020
oph+0.020
way+0.017
handed+0.017
ally+0.017
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.010
 bears-0.009
 passenger-0.009
Token colors
Token ID7577
Feature activation-8.97e-02

Pos logit contributions
ork+0.006
oph+0.006
ally+0.005
way+0.005
handed+0.005
Neg logit contributions
 Amen-0.008
 fires-0.005
 exc-0.005
stretched-0.005
Does-0.005
Token they
Token ID484
Feature activation+9.41e-01

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 bears+0.002
 scar+0.002
Neg logit contributions
ork-0.003
oph-0.003
way-0.002
ally-0.002
handed-0.002
Token were
Token ID547
Feature activation+6.84e-01

Pos logit contributions
ork+0.028
oph+0.028
ally+0.024
way+0.024
handed+0.023
Neg logit contributions
 Amen-0.030
 fires-0.023
stretched-0.021
 bears-0.020
 sled-0.020
Token able
Token ID1498
Feature activation+3.81e+00

Pos logit contributions
ork+0.022
oph+0.022
way+0.019
ally+0.019
handed+0.019
Neg logit contributions
 Amen-0.020
 fires-0.014
stretched-0.014
 bears-0.013
 scar-0.012
Token to
Token ID284
Feature activation+8.48e-02

Pos logit contributions
oph+0.129
ork+0.125
ally+0.111
handed+0.108
anger+0.105
Neg logit contributions
 Amen-0.095
 fires-0.079
stretched-0.078
 smile-0.073
 hope-0.070
Token create
Token ID2251
Feature activation-1.35e+00

Pos logit contributions
ork+0.003
oph+0.003
ally+0.002
way+0.002
 doorstep+0.002
Neg logit contributions
 Amen-0.002
 fires-0.002
 bears-0.002
stretched-0.002
 scar-0.002
Token.
Token ID13
Feature activation+2.88e-01

Pos logit contributions
 Amen+0.037
 fires+0.028
stretched+0.026
 bears+0.025
 scar+0.024
Neg logit contributions
ork-0.045
oph-0.045
way-0.039
ally-0.039
handed-0.039
Token
Token ID198
Feature activation+5.41e-01

Pos logit contributions
ork+0.010
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.006
 bears-0.005
 passenger-0.005
Token
Token ID198
Feature activation+1.74e-01

Pos logit contributions
ork+0.016
oph+0.016
way+0.013
ally+0.013
handed+0.013
Neg logit contributions
 Amen-0.018
 fires-0.013
stretched-0.013
 bears-0.012
 smile-0.012
Token.
Token ID13
Feature activation+3.96e-01

Pos logit contributions
oph+0.056
ork+0.054
ally+0.049
handed+0.047
way+0.045
Neg logit contributions
 Amen-0.040
 fires-0.030
stretched-0.029
 bears-0.027
 smile-0.027
Token
Token ID198
Feature activation+7.19e-01

Pos logit contributions
ork+0.015
oph+0.015
anger+0.013
way+0.013
handed+0.013
Neg logit contributions
 Amen-0.010
 fires-0.005
 Sometimes-0.005
 nod-0.005
 Everyday-0.005
Token
Token ID198
Feature activation+3.74e-01

Pos logit contributions
oph+0.025
ork+0.024
keeping+0.022
way+0.022
ally+0.021
Neg logit contributions
 Amen-0.019
 fires-0.013
stretched-0.012
 sled-0.012
 smile-0.012
TokenWhen
Token ID2215
Feature activation-9.95e-01

Pos logit contributions
ork+0.013
oph+0.013
keeping+0.011
way+0.011
ally+0.011
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 passenger-0.006
Does-0.006
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
 Amen+0.021
 fires+0.015
 bears+0.013
stretched+0.012
 smile+0.011
Neg logit contributions
ork-0.040
oph-0.039
handed-0.037
ally-0.035
way-0.035
Token rain
Token ID6290
Feature activation+3.80e+00

Pos logit contributions
ork+0.007
oph+0.007
way+0.006
ally+0.006
handed+0.006
Neg logit contributions
 Amen-0.007
 fires-0.006
stretched-0.006
 bears-0.005
 passenger-0.005
Token had
Token ID550
Feature activation+1.72e+00

Pos logit contributions
oph+0.137
ork+0.136
handed+0.135
ige+0.131
keeping+0.127
Neg logit contributions
 Amen-0.062
 sometimes-0.056
 smile-0.056
 bears-0.052
 zoom-0.051
Token stopped
Token ID5025
Feature activation+8.51e-01

Pos logit contributions
ork+0.056
oph+0.054
handed+0.051
ally+0.049
anger+0.048
Neg logit contributions
 Amen-0.040
 fires-0.037
 smile-0.037
 hope-0.033
stretched-0.033
Token,
Token ID11
Feature activation+8.41e-01

Pos logit contributions
ork+0.028
oph+0.026
way+0.024
ally+0.024
handed+0.023
Neg logit contributions
 Amen-0.025
stretched-0.017
 fires-0.017
 bears-0.016
 passenger-0.015
Token the
Token ID262
Feature activation+3.42e-01

Pos logit contributions
ork+0.031
oph+0.031
way+0.027
ally+0.027
handed+0.027
Neg logit contributions
 Amen-0.021
 fires-0.015
stretched-0.014
 bears-0.013
 passenger-0.012
Token children
Token ID1751
Feature activation+7.96e-01

Pos logit contributions
ork+0.011
oph+0.011
way+0.009
ally+0.009
handed+0.009
Neg logit contributions
 Amen-0.010
 fires-0.008
stretched-0.008
 bears-0.007
 passenger-0.007
Token with
Token ID351
Feature activation-1.47e-01

Pos logit contributions
 Amen+0.020
 fires+0.014
stretched+0.014
 bears+0.013
 paddle+0.012
Neg logit contributions
ork-0.024
oph-0.023
way-0.020
ally-0.020
handed-0.019
Token the
Token ID262
Feature activation-5.81e-02

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 passenger+0.003
 bears+0.003
Neg logit contributions
ork-0.005
oph-0.005
way-0.004
handed-0.004
ally-0.004
Token machine
Token ID4572
Feature activation-6.00e-01

Pos logit contributions
 Amen+0.002
 fires+0.001
stretched+0.001
 bears+0.001
 passenger+0.001
Neg logit contributions
ork-0.002
oph-0.002
way-0.002
handed-0.002
ally-0.002
Token until
Token ID1566
Feature activation-1.42e+00

Pos logit contributions
 Amen+0.019
 fires+0.014
stretched+0.013
 bears+0.012
Does+0.012
Neg logit contributions
ork-0.018
oph-0.017
way-0.016
ally-0.015
handed-0.015
Token the
Token ID262
Feature activation+4.55e-01

Pos logit contributions
 Amen+0.043
 fires+0.032
stretched+0.031
 bears+0.029
 smile+0.028
Neg logit contributions
ork-0.045
oph-0.044
handed-0.038
ally-0.038
way-0.038
Token rain
Token ID6290
Feature activation+3.80e+00

Pos logit contributions
ork+0.014
oph+0.013
way+0.012
ally+0.012
handed+0.012
Neg logit contributions
 Amen-0.014
 fires-0.011
stretched-0.010
 bears-0.010
 passenger-0.009
Token stopped
Token ID5025
Feature activation+7.20e-01

Pos logit contributions
oph+0.138
ork+0.137
handed+0.136
keeping+0.123
ally+0.121
Neg logit contributions
 Amen-0.063
 smile-0.056
stretched-0.054
 wave-0.054
 sometimes-0.054
Token pouring
Token ID23147
Feature activation+7.31e-01

Pos logit contributions
ork+0.021
oph+0.019
way+0.018
ally+0.017
handed+0.016
Neg logit contributions
 Amen-0.024
 fires-0.017
stretched-0.017
 bears-0.016
 passenger-0.016
Token.
Token ID13
Feature activation+1.79e-01

Pos logit contributions
ork+0.024
oph+0.023
way+0.020
ally+0.020
handed+0.020
Neg logit contributions
 Amen-0.022
 fires-0.016
stretched-0.016
 bears-0.015
 passenger-0.014
Token Then
Token ID3244
Feature activation+4.51e-02

Pos logit contributions
oph+0.006
ork+0.006
handed+0.005
ally+0.005
keeping+0.005
Neg logit contributions
 Amen-0.005
 fires-0.003
stretched-0.003
 nod-0.003
 passenger-0.003
Token the
Token ID262
Feature activation+2.77e-03

Pos logit contributions
ork+0.002
oph+0.001
way+0.001
ally+0.001
handed+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token mom
Token ID1995
Feature activation-1.92e+00

Pos logit contributions
 Amen+0.010
stretched+0.008
 fires+0.007
 helmet+0.007
 bears+0.007
Neg logit contributions
ork-0.010
oph-0.009
ally-0.009
way-0.008
 doorstep-0.008
Token and
Token ID290
Feature activation-8.62e-01

Pos logit contributions
 Amen+0.065
stretched+0.049
 fires+0.046
 paddle+0.045
 spoiler+0.045
Neg logit contributions
ork-0.053
oph-0.051
ally-0.046
way-0.045
handed-0.044
Token to
Token ID284
Feature activation-4.31e-01

Pos logit contributions
 Amen+0.030
 fires+0.023
stretched+0.023
 bears+0.021
 spoiler+0.021
Neg logit contributions
ork-0.023
oph-0.022
way-0.019
ally-0.019
handed-0.018
Token the
Token ID262
Feature activation-9.50e-01

Pos logit contributions
 Amen+0.011
 fires+0.008
stretched+0.008
 bears+0.007
 scar+0.007
Neg logit contributions
ork-0.015
oph-0.015
way-0.013
ally-0.013
handed-0.013
Token ost
Token ID23619
Feature activation+1.24e-01

Pos logit contributions
 Amen+0.027
 fires+0.020
stretched+0.019
 bears+0.018
 passenger+0.017
Neg logit contributions
oph-0.032
ork-0.032
ally-0.028
way-0.027
handed-0.027
Tokenric
Token ID1173
Feature activation-5.39e+00

Pos logit contributions
ork+0.006
oph+0.006
way+0.005
handed+0.005
ally+0.005
Neg logit contributions
 Amen-0.002
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Tokenhes
Token ID956
Feature activation-1.48e+00

Pos logit contributions
 Amen+0.134
 fires+0.108
 bears+0.087
stretched+0.086
 exc+0.081
Neg logit contributions
oph-0.213
ork-0.188
ally-0.184
 doorstep-0.178
way-0.169
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
 Amen+0.046
stretched+0.033
 fires+0.033
 bears+0.031
 scar+0.030
Neg logit contributions
ork-0.047
oph-0.043
way-0.039
handed-0.038
ally-0.038
Token They
Token ID1119
Feature activation-5.92e-01

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.003
 paddle+0.003
Neg logit contributions
ork-0.006
oph-0.006
way-0.005
ally-0.005
handed-0.005
Token learned
Token ID4499
Feature activation-4.80e-01

Pos logit contributions
 Amen+0.019
 fires+0.015
stretched+0.014
 bears+0.013
 passenger+0.012
Neg logit contributions
oph-0.018
ork-0.017
ally-0.015
way-0.015
handed-0.015
Token their
Token ID511
Feature activation+2.25e-01

Pos logit contributions
 Amen+0.014
stretched+0.010
 fires+0.010
 bears+0.009
 spoiler+0.009
Neg logit contributions
ork-0.016
oph-0.015
way-0.014
handed-0.013
ally-0.013
Token and
Token ID290
Feature activation+6.66e-02

Pos logit contributions
ork+0.005
oph+0.005
way+0.005
handed+0.004
ally+0.004
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.003
 bears-0.003
 scar-0.003
Token run
Token ID1057
Feature activation+6.70e-01

Pos logit contributions
ork+0.002
oph+0.002
 doorstep+0.002
way+0.002
keeping+0.002
Neg logit contributions
 Amen-0.002
stretched-0.002
 fires-0.001
 bears-0.001
Does-0.001
Token to
Token ID284
Feature activation-5.10e-01

Pos logit contributions
ork+0.020
oph+0.019
way+0.017
ally+0.017
handed+0.017
Neg logit contributions
 Amen-0.021
 fires-0.016
stretched-0.016
 bears-0.015
 passenger-0.014
Token the
Token ID262
Feature activation-8.55e-01

Pos logit contributions
 Amen+0.014
 fires+0.010
stretched+0.010
 bears+0.009
 scar+0.008
Neg logit contributions
ork-0.018
oph-0.017
way-0.016
handed-0.015
ally-0.015
Token ost
Token ID23619
Feature activation+2.43e-01

Pos logit contributions
 Amen+0.025
 fires+0.020
 bears+0.019
 scar+0.018
stretched+0.018
Neg logit contributions
oph-0.027
ork-0.026
ally-0.023
way-0.023
handed-0.023
Tokenric
Token ID1173
Feature activation-5.25e+00

Pos logit contributions
ork+0.011
oph+0.011
handed+0.010
way+0.010
ally+0.010
Neg logit contributions
 Amen-0.004
 fires-0.002
stretched-0.002
 bears-0.002
 passenger-0.002
Tokenhes
Token ID956
Feature activation-1.15e+00

Pos logit contributions
 Amen+0.143
 fires+0.113
stretched+0.101
 bears+0.095
 exc+0.091
Neg logit contributions
oph-0.185
ork-0.171
ally-0.161
 doorstep-0.155
handed-0.152
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
 Amen+0.037
 fires+0.027
stretched+0.026
 bears+0.025
 scar+0.025
Neg logit contributions
ork-0.036
oph-0.032
way-0.030
handed-0.028
ally-0.028
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
oph+0.008
ork+0.008
ally+0.007
handed+0.007
way+0.007
Neg logit contributions
 Amen-0.005
 fires-0.003
stretched-0.003
 paddle-0.003
 hope-0.003
Token
Token ID198
Feature activation-2.42e-03

Pos logit contributions
oph+0.009
ork+0.008
ally+0.007
handed+0.007
 doorstep+0.007
Neg logit contributions
 Amen-0.007
 fires-0.005
stretched-0.005
 exc-0.005
 sled-0.005
Token"
Token ID1
Feature activation+3.62e-01

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 bears+0.000
 passenger+0.000
Neg logit contributions
ork-0.000
oph-0.000
way-0.000
ally-0.000
handed-0.000
Token should
Token ID815
Feature activation+2.75e-01

Pos logit contributions
 Amen+0.022
stretched+0.016
 fires+0.016
 passenger+0.014
 bears+0.014
Neg logit contributions
ork-0.026
oph-0.025
handed-0.022
ally-0.022
way-0.022
Token not
Token ID407
Feature activation+7.52e-01

Pos logit contributions
ork+0.009
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.005
 bears-0.005
 passenger-0.005
Token tease
Token ID34691
Feature activation+8.99e-01

Pos logit contributions
ork+0.029
oph+0.029
handed+0.025
way+0.025
ally+0.025
Neg logit contributions
 Amen-0.017
 fires-0.012
stretched-0.011
 bears-0.010
 smile-0.010
Token the
Token ID262
Feature activation+3.41e-02

Pos logit contributions
ork+0.030
oph+0.029
way+0.025
ally+0.025
handed+0.025
Neg logit contributions
 Amen-0.025
 fires-0.020
 bears-0.019
stretched-0.019
 scar-0.017
Token ost
Token ID23619
Feature activation+2.65e-01

Pos logit contributions
oph+0.001
ork+0.001
ally+0.001
handed+0.001
way+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
 bears-0.001
stretched-0.001
 passenger-0.001
Tokenric
Token ID1173
Feature activation-5.13e+00

Pos logit contributions
oph+0.012
ork+0.012
handed+0.011
way+0.011
ally+0.011
Neg logit contributions
 Amen-0.004
 fires-0.002
stretched-0.002
 bears-0.002
 passenger-0.001
Tokenhes
Token ID956
Feature activation-1.46e+00

Pos logit contributions
 Amen+0.138
 fires+0.113
stretched+0.098
 bears+0.096
 exc+0.089
Neg logit contributions
oph-0.182
ork-0.168
ally-0.157
 doorstep-0.155
handed-0.148
Token.
Token ID13
Feature activation-4.14e-01

Pos logit contributions
 Amen+0.046
stretched+0.033
 fires+0.032
 bears+0.030
 scar+0.030
Neg logit contributions
ork-0.046
oph-0.042
way-0.038
handed-0.037
ally-0.037
Token They
Token ID1119
Feature activation-1.03e-01

Pos logit contributions
 Amen+0.012
 fires+0.009
stretched+0.009
 bears+0.008
 scar+0.008
Neg logit contributions
ork-0.014
oph-0.013
way-0.012
ally-0.012
handed-0.011
Token are
Token ID389
Feature activation+1.79e-01

Pos logit contributions
 Amen+0.003
stretched+0.002
 fires+0.002
 passenger+0.001
 bears+0.001
Neg logit contributions
ork-0.004
oph-0.004
way-0.003
handed-0.003
ally-0.003
Token not
Token ID407
Feature activation+7.36e-01

Pos logit contributions
ork+0.006
oph+0.005
way+0.005
ally+0.005
handed+0.005
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token and
Token ID290
Feature activation-1.47e-01

Pos logit contributions
 Amen+0.019
 spoiler+0.013
 fires+0.013
stretched+0.013
 helmet+0.013
Neg logit contributions
ork-0.014
way-0.013
oph-0.012
ally-0.012
handed-0.011
Token looked
Token ID3114
Feature activation-1.45e+00

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 bears+0.002
 paddle+0.002
Neg logit contributions
ork-0.005
oph-0.005
way-0.005
handed-0.005
ally-0.005
Token at
Token ID379
Feature activation-5.59e-01

Pos logit contributions
 Amen+0.051
stretched+0.038
 fires+0.036
 passenger+0.035
Does+0.035
Neg logit contributions
ork-0.038
oph-0.036
way-0.033
ally-0.031
handed-0.030
Token the
Token ID262
Feature activation-3.69e-01

Pos logit contributions
 Amen+0.017
stretched+0.012
 fires+0.012
 bears+0.010
 passenger+0.010
Neg logit contributions
ork-0.018
oph-0.017
way-0.015
ally-0.015
handed-0.015
Token ost
Token ID23619
Feature activation+4.81e-01

Pos logit contributions
 Amen+0.010
 fires+0.007
stretched+0.007
 bears+0.007
 passenger+0.006
Neg logit contributions
oph-0.013
ork-0.013
ally-0.012
handed-0.011
way-0.011
Tokenric
Token ID1173
Feature activation-5.12e+00

Pos logit contributions
ork+0.022
oph+0.022
handed+0.020
way+0.020
ally+0.020
Neg logit contributions
 Amen-0.007
 fires-0.004
stretched-0.004
 bears-0.003
 passenger-0.003
Tokenhes
Token ID956
Feature activation-1.35e+00

Pos logit contributions
 Amen+0.139
 fires+0.109
stretched+0.098
 bears+0.092
 exc+0.087
Neg logit contributions
oph-0.182
ork-0.169
ally-0.159
 doorstep-0.152
handed-0.149
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
 Amen+0.041
 fires+0.030
stretched+0.029
 bears+0.027
 scar+0.026
Neg logit contributions
ork-0.043
oph-0.041
way-0.037
ally-0.036
handed-0.035
Token They
Token ID1119
Feature activation+1.42e-02

Pos logit contributions
 Amen+0.003
 fires+0.002
 bears+0.002
stretched+0.002
 whine+0.002
Neg logit contributions
oph-0.008
ork-0.008
handed-0.008
ally-0.008
way-0.007
Token saw
Token ID2497
Feature activation-2.91e-01

Pos logit contributions
ork+0.000
oph+0.000
ally+0.000
way+0.000
handed+0.000
Neg logit contributions
 Amen-0.000
 fires-0.000
stretched-0.000
 bears-0.000
 passenger-0.000
Token one
Token ID530
Feature activation+1.06e-01

Pos logit contributions
 Amen+0.009
stretched+0.006
 fires+0.006
 bears+0.005
 passenger+0.005
Neg logit contributions
ork-0.010
oph-0.009
way-0.008
handed-0.008
ally-0.008
Token wanted
Token ID2227
Feature activation+2.26e-01

Pos logit contributions
 Amen+0.010
 fires+0.008
stretched+0.007
 bears+0.007
 passenger+0.006
Neg logit contributions
oph-0.010
ork-0.010
ally-0.009
way-0.009
handed-0.008
Token to
Token ID284
Feature activation+4.90e-02

Pos logit contributions
oph+0.007
ork+0.007
way+0.006
ally+0.006
handed+0.006
Neg logit contributions
 Amen-0.007
 fires-0.005
 bears-0.005
stretched-0.005
 hope-0.005
Token touch
Token ID3638
Feature activation+6.04e-01

Pos logit contributions
ork+0.002
oph+0.002
way+0.002
ally+0.002
handed+0.002
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token the
Token ID262
Feature activation+6.97e-02

Pos logit contributions
ork+0.019
oph+0.018
way+0.016
handed+0.016
ally+0.016
Neg logit contributions
 Amen-0.018
stretched-0.013
 fires-0.012
 passenger-0.011
 exc-0.011
Token ost
Token ID23619
Feature activation+2.83e-01

Pos logit contributions
oph+0.003
ork+0.002
handed+0.002
ally+0.002
way+0.002
Neg logit contributions
 Amen-0.002
 fires-0.001
 bears-0.001
 scar-0.001
stretched-0.001
Tokenric
Token ID1173
Feature activation-5.06e+00

Pos logit contributions
oph+0.013
ork+0.013
handed+0.012
way+0.012
ally+0.012
Neg logit contributions
 Amen-0.004
 fires-0.002
stretched-0.002
 bears-0.002
 passenger-0.001
Tokenhes
Token ID956
Feature activation-1.52e+00

Pos logit contributions
 Amen+0.123
 fires+0.099
stretched+0.084
 bears+0.080
 exc+0.078
Neg logit contributions
oph-0.195
ork-0.174
ally-0.168
 doorstep-0.167
keeping-0.159
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
 Amen+0.048
 fires+0.034
stretched+0.034
 bears+0.031
 passenger+0.031
Neg logit contributions
ork-0.048
oph-0.045
way-0.040
ally-0.039
handed-0.038
Token They
Token ID1119
Feature activation-2.69e-01

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 hope+0.002
 sometimes+0.002
Neg logit contributions
oph-0.005
ork-0.005
handed-0.005
ally-0.005
way-0.004
Token reached
Token ID4251
Feature activation-5.81e-01

Pos logit contributions
 Amen+0.008
 fires+0.006
stretched+0.006
 bears+0.005
 passenger+0.005
Neg logit contributions
ork-0.009
oph-0.008
ally-0.007
way-0.007
handed-0.007
Token out
Token ID503
Feature activation-1.25e+00

Pos logit contributions
 Amen+0.022
 fires+0.017
stretched+0.017
 bears+0.015
 spoiler+0.015
Neg logit contributions
ork-0.014
oph-0.014
way-0.012
ally-0.011
 doorstep-0.011
Token loved
Token ID6151
Feature activation-1.29e+00

Pos logit contributions
ork+0.034
oph+0.033
way+0.029
ally+0.028
handed+0.028
Neg logit contributions
 Amen-0.033
 fires-0.025
stretched-0.024
 bears-0.022
 passenger-0.021
Token to
Token ID284
Feature activation-1.75e-01

Pos logit contributions
 Amen+0.046
stretched+0.035
 fires+0.035
 passenger+0.033
 spoiler+0.032
Neg logit contributions
ork-0.034
oph-0.033
way-0.028
ally-0.028
handed-0.027
Token play
Token ID711
Feature activation-1.07e+00

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 passenger+0.004
 bears+0.004
Neg logit contributions
ork-0.005
oph-0.005
ally-0.004
n-0.004
 doorstep-0.004
Token make
Token ID787
Feature activation-1.18e+00

Pos logit contributions
 Amen+0.037
stretched+0.029
 fires+0.029
 bears+0.026
 passenger+0.026
Neg logit contributions
ork-0.030
oph-0.028
way-0.024
ally-0.024
handed-0.023
Token-
Token ID12
Feature activation+5.88e-01

Pos logit contributions
 Amen+0.029
 fires+0.024
 bears+0.023
stretched+0.021
 scar+0.021
Neg logit contributions
oph-0.040
ork-0.040
way-0.035
ally-0.035
handed-0.034
Tokenbel
Token ID6667
Feature activation-4.80e+00

Pos logit contributions
ork+0.018
oph+0.017
way+0.015
handed+0.015
ally+0.015
Neg logit contributions
 Amen-0.018
 fires-0.014
stretched-0.014
 bears-0.013
 paddle-0.012
Tokenieve
Token ID12311
Feature activation-4.90e-01

Pos logit contributions
 Amen+0.118
stretched+0.080
 fires+0.078
 paddle+0.071
 bears+0.071
Neg logit contributions
ork-0.178
oph-0.172
handed-0.155
way-0.155
ally-0.151
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
 Amen+0.016
stretched+0.012
 fires+0.012
 paddle+0.011
 spoiler+0.011
Neg logit contributions
ork-0.015
oph-0.014
way-0.012
handed-0.012
ally-0.011
Token Today
Token ID6288
Feature activation+8.16e-01

Pos logit contributions
 Amen+0.011
 fires+0.008
stretched+0.007
 bears+0.007
 scar+0.007
Neg logit contributions
ork-0.015
oph-0.015
way-0.013
ally-0.013
handed-0.013
Token she
Token ID673
Feature activation+9.73e-01

Pos logit contributions
oph+0.035
ork+0.034
handed+0.032
keeping+0.032
ige+0.031
Neg logit contributions
 Amen-0.011
 sometimes-0.008
 smile-0.007
 fires-0.007
stretched-0.007
Token was
Token ID373
Feature activation-1.09e-01

Pos logit contributions
ork+0.030
oph+0.029
way+0.025
ally+0.025
handed+0.025
Neg logit contributions
 Amen-0.030
 fires-0.023
stretched-0.022
 bears-0.021
 passenger-0.020
Token They
Token ID1119
Feature activation-1.64e-01

Pos logit contributions
 Amen+0.002
stretched+0.002
 fires+0.002
 bears+0.001
 scar+0.001
Neg logit contributions
ork-0.003
oph-0.003
way-0.003
handed-0.002
ally-0.002
Token do
Token ID466
Feature activation-2.74e-01

Pos logit contributions
 Amen+0.005
stretched+0.004
 fires+0.003
 bears+0.003
 spoiler+0.003
Neg logit contributions
ork-0.005
oph-0.005
 doorstep-0.005
handed-0.005
ally-0.005
Token not
Token ID407
Feature activation+9.55e-01

Pos logit contributions
 Amen+0.010
stretched+0.008
 fires+0.007
 bears+0.007
 passenger+0.007
Neg logit contributions
ork-0.008
oph-0.007
way-0.006
handed-0.006
ally-0.006
Token pack
Token ID2353
Feature activation+8.23e-01

Pos logit contributions
ork+0.036
oph+0.034
way+0.032
ally+0.031
handed+0.031
Neg logit contributions
 Amen-0.023
stretched-0.016
 fires-0.015
 bears-0.014
 passenger-0.013
Token ost
Token ID23619
Feature activation+4.81e-01

Pos logit contributions
oph+0.031
ork+0.031
ally+0.027
way+0.027
handed+0.027
Neg logit contributions
 Amen-0.019
 fires-0.015
stretched-0.013
 bears-0.013
 hope-0.012
Tokenric
Token ID1173
Feature activation-4.48e+00

Pos logit contributions
oph+0.020
ork+0.020
way+0.018
handed+0.018
ally+0.018
Neg logit contributions
 Amen-0.009
 fires-0.006
stretched-0.006
 bears-0.005
 scar-0.005
Tokenhes
Token ID956
Feature activation-6.87e-01

Pos logit contributions
 Amen+0.125
 fires+0.103
stretched+0.090
 bears+0.090
 passenger+0.081
Neg logit contributions
oph-0.153
ork-0.146
ally-0.132
 doorstep-0.127
way-0.127
Token anymore
Token ID7471
Feature activation+3.77e-01

Pos logit contributions
 Amen+0.019
stretched+0.013
 fires+0.013
 bears+0.012
 passenger+0.012
Neg logit contributions
ork-0.024
oph-0.023
way-0.020
handed-0.020
ally-0.020
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
oph+0.014
ork+0.013
ally+0.012
way+0.012
handed+0.012
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.007
 exc-0.006
Token They
Token ID1119
Feature activation-1.79e-01

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 bears+0.002
 passenger+0.002
Neg logit contributions
ork-0.005
oph-0.005
ally-0.004
way-0.004
handed-0.004
Token pack
Token ID2353
Feature activation+1.05e+00

Pos logit contributions
 Amen+0.005
stretched+0.004
 fires+0.004
 bears+0.004
Does+0.003
Neg logit contributions
ork-0.005
oph-0.005
 doorstep-0.005
handed-0.005
n-0.005
Token "
Token ID366
Feature activation+1.36e-01

Pos logit contributions
ork+0.041
oph+0.039
way+0.034
ally+0.033
handed+0.031
Neg logit contributions
 Amen-0.047
 fires-0.037
stretched-0.036
 bears-0.034
 passenger-0.033
TokenPlease
Token ID5492
Feature activation-2.46e-01

Pos logit contributions
ork+0.004
oph+0.004
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.003
 passenger-0.003
Token keep
Token ID1394
Feature activation+7.26e-01

Pos logit contributions
 Amen+0.007
 fires+0.005
stretched+0.005
 bears+0.004
 passenger+0.004
Neg logit contributions
ork-0.009
oph-0.008
way-0.008
ally-0.007
handed-0.007
Token your
Token ID534
Feature activation+6.56e-01

Pos logit contributions
ork+0.024
oph+0.023
way+0.020
ally+0.020
handed+0.020
Neg logit contributions
 Amen-0.021
 fires-0.016
stretched-0.015
 bears-0.014
 passenger-0.014
Token seat
Token ID5852
Feature activation-6.84e-01

Pos logit contributions
ork+0.021
oph+0.018
way+0.017
 doorstep+0.017
handed+0.016
Neg logit contributions
 Amen-0.021
stretched-0.015
 fires-0.014
Does-0.014
 bears-0.014
Tokenbel
Token ID6667
Feature activation-4.47e+00

Pos logit contributions
 Amen+0.023
stretched+0.017
 fires+0.017
 bears+0.016
Does+0.016
Neg logit contributions
ork-0.020
oph-0.017
way-0.017
handed-0.016
 doorstep-0.016
Tokents
Token ID912
Feature activation-1.64e+00

Pos logit contributions
 Amen+0.109
 fires+0.075
stretched+0.074
 bears+0.068
 paddle+0.065
Neg logit contributions
ork-0.166
oph-0.160
way-0.145
handed-0.144
ally-0.141
Token on
Token ID319
Feature activation+4.04e-01

Pos logit contributions
 Amen+0.050
 fires+0.037
stretched+0.036
 bears+0.034
 passenger+0.032
Neg logit contributions
ork-0.051
oph-0.049
way-0.044
handed-0.043
ally-0.043
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
ork+0.013
oph+0.012
way+0.011
handed+0.011
ally+0.010
Neg logit contributions
 Amen-0.012
stretched-0.009
 fires-0.009
 bears-0.008
 scar-0.008
Token We
Token ID775
Feature activation+1.24e+00

Pos logit contributions
 Amen+0.007
stretched+0.006
 fires+0.006
 bears+0.006
 scar+0.006
Neg logit contributions
ork-0.006
oph-0.006
way-0.005
handed-0.005
 doorstep-0.005
Token will
Token ID481
Feature activation+6.92e-01

Pos logit contributions
ork+0.046
oph+0.040
way+0.040
n+0.038
handed+0.037
Neg logit contributions
 Amen-0.030
stretched-0.022
 fires-0.020
Does-0.019
 bears-0.018
Token couldn
Token ID3521
Feature activation-1.24e+00

Pos logit contributions
oph+0.018
ork+0.018
handed+0.016
keeping+0.016
way+0.016
Neg logit contributions
 Amen-0.013
stretched-0.010
 fires-0.010
 bears-0.010
 sometimes-0.009
Token't
Token ID470
Feature activation+1.07e-01

Pos logit contributions
 Amen+0.043
 fires+0.033
stretched+0.032
 bears+0.031
 passenger+0.029
Neg logit contributions
ork-0.034
oph-0.033
way-0.028
ally-0.028
handed-0.028
Token get
Token ID651
Feature activation+8.73e-01

Pos logit contributions
ork+0.004
oph+0.004
way+0.003
ally+0.003
handed+0.003
Neg logit contributions
 Amen-0.003
 fires-0.002
stretched-0.002
 bears-0.002
 passenger-0.002
Token above
Token ID2029
Feature activation-1.90e+00

Pos logit contributions
ork+0.028
oph+0.026
way+0.025
handed+0.024
ally+0.023
Neg logit contributions
 Amen-0.026
stretched-0.018
 fires-0.018
 passenger-0.017
 bears-0.016
Token the
Token ID262
Feature activation-6.65e-01

Pos logit contributions
 Amen+0.060
stretched+0.042
 passenger+0.040
 exc+0.039
 whine+0.039
Neg logit contributions
ork-0.060
oph-0.054
way-0.049
handed-0.048
ally-0.047
Token tre
Token ID2054
Feature activation-4.44e+00

Pos logit contributions
 Amen+0.019
 fires+0.014
stretched+0.014
 bears+0.013
 smile+0.013
Neg logit contributions
ork-0.022
oph-0.022
ally-0.019
way-0.019
handed-0.019
Tokenet
Token ID316
Feature activation-5.63e-01

Pos logit contributions
 Amen+0.136
 fires+0.104
stretched+0.098
 exc+0.090
 passenger+0.090
Neg logit contributions
ork-0.140
oph-0.135
way-0.115
handed-0.115
ally-0.115
Tokenops
Token ID2840
Feature activation-2.37e+00

Pos logit contributions
 Amen+0.018
 fires+0.013
stretched+0.012
 bears+0.012
 scar+0.012
Neg logit contributions
ork-0.018
oph-0.017
way-0.015
ally-0.015
handed-0.014
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
 Amen+0.066
 fires+0.049
stretched+0.047
 bears+0.044
 smile+0.042
Neg logit contributions
ork-0.079
oph-0.078
way-0.068
ally-0.068
handed-0.067
Token He
Token ID679
Feature activation-5.89e-01

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.003
 paddle+0.003
Neg logit contributions
ork-0.009
oph-0.009
ally-0.008
handed-0.008
way-0.008
Token was
Token ID373
Feature activation+8.32e-02

Pos logit contributions
 Amen+0.018
 fires+0.013
stretched+0.013
 bears+0.012
 passenger+0.011
Neg logit contributions
ork-0.019
oph-0.018
way-0.016
ally-0.016
handed-0.016
Token selfish
Token ID20363
Feature activation+4.06e-01

Pos logit contributions
ork+0.014
oph+0.013
way+0.012
ally+0.012
handed+0.012
Neg logit contributions
 Amen-0.013
stretched-0.010
 fires-0.010
 passenger-0.009
 sled-0.009
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
ork+0.013
oph+0.013
way+0.011
ally+0.011
handed+0.011
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.009
 bears-0.008
 passenger-0.008
Token She
Token ID1375
Feature activation-1.29e+00

Pos logit contributions
 Amen+0.007
 fires+0.005
stretched+0.005
 bears+0.004
 smile+0.004
Neg logit contributions
ork-0.012
oph-0.012
way-0.011
handed-0.011
ally-0.011
Token thanked
Token ID26280
Feature activation-1.01e+00

Pos logit contributions
 Amen+0.041
 fires+0.032
stretched+0.031
 passenger+0.028
 bears+0.027
Neg logit contributions
ork-0.039
oph-0.039
ally-0.033
way-0.032
handed-0.031
Token her
Token ID607
Feature activation-7.19e-01

Pos logit contributions
 Amen+0.029
 fires+0.022
stretched+0.021
 bears+0.020
 passenger+0.019
Neg logit contributions
ork-0.033
oph-0.032
ally-0.028
way-0.028
handed-0.028
Token brothers
Token ID9397
Feature activation-4.40e+00

Pos logit contributions
 Amen+0.026
stretched+0.020
 fires+0.019
 spoiler+0.018
 passenger+0.018
Neg logit contributions
ork-0.019
oph-0.018
ally-0.016
 doorstep-0.015
way-0.014
Token and
Token ID290
Feature activation-2.72e-01

Pos logit contributions
 Amen+0.145
 fires+0.108
stretched+0.106
 spoiler+0.098
Does+0.097
Neg logit contributions
ork-0.123
oph-0.121
way-0.110
ally-0.104
handed-0.102
Token sisters
Token ID15153
Feature activation-2.40e+00

Pos logit contributions
 Amen+0.008
 fires+0.006
stretched+0.006
 bears+0.005
 passenger+0.005
Neg logit contributions
oph-0.009
ork-0.009
ally-0.008
way-0.007
handed-0.007
Token for
Token ID329
Feature activation+1.21e+00

Pos logit contributions
 Amen+0.078
 fires+0.060
stretched+0.057
 bears+0.054
 scar+0.053
Neg logit contributions
ork-0.069
oph-0.067
way-0.061
handed-0.059
ally-0.057
Token saving
Token ID8914
Feature activation+1.69e-01

Pos logit contributions
ork+0.038
oph+0.037
way+0.033
handed+0.033
ally+0.033
Neg logit contributions
 Amen-0.036
 fires-0.026
stretched-0.026
 bears-0.024
 passenger-0.023
Token her
Token ID607
Feature activation-3.56e-01

Pos logit contributions
ork+0.007
oph+0.006
way+0.006
lor+0.006
ally+0.006
Neg logit contributions
 Amen-0.004
 fires-0.003
 bears-0.003
 hope-0.002
 scar-0.002
Token "
Token ID366
Feature activation-4.42e-01

Pos logit contributions
ork+0.046
oph+0.044
ally+0.041
way+0.040
handed+0.038
Neg logit contributions
 Amen-0.047
stretched-0.035
 spoiler-0.032
 scar-0.031
 fires-0.031
TokenWhat
Token ID2061
Feature activation-8.24e-01

Pos logit contributions
 Amen+0.012
 fires+0.009
stretched+0.009
 smile+0.008
 scar+0.007
Neg logit contributions
oph-0.015
ork-0.015
handed-0.013
ally-0.013
way-0.013
Token are
Token ID389
Feature activation-2.78e-01

Pos logit contributions
 Amen+0.022
 fires+0.016
stretched+0.015
 bears+0.014
 hope+0.013
Neg logit contributions
ork-0.029
oph-0.029
way-0.025
ally-0.025
handed-0.025
Token you
Token ID345
Feature activation-3.03e-01

Pos logit contributions
 Amen+0.010
 fires+0.008
stretched+0.007
 bears+0.007
 scar+0.007
Neg logit contributions
ork-0.008
oph-0.007
way-0.006
handed-0.006
ally-0.006
Token doing
Token ID1804
Feature activation-1.54e+00

Pos logit contributions
 Amen+0.008
 fires+0.005
 bears+0.005
 smile+0.005
stretched+0.005
Neg logit contributions
ork-0.011
oph-0.011
handed-0.010
way-0.010
ally-0.009
Token
Token ID220
Feature activation-4.35e+00

Pos logit contributions
 Amen+0.040
stretched+0.029
 fires+0.028
 bears+0.025
 passenger+0.025
Neg logit contributions
ork-0.054
oph-0.052
way-0.047
ally-0.046
handed-0.046
Token?"
Token ID1701
Feature activation+6.35e-01

Pos logit contributions
 Amen+0.148
 fires+0.117
stretched+0.115
 exc+0.107
 bears+0.104
Neg logit contributions
oph-0.111
ork-0.110
keeping-0.094
handed-0.093
ally-0.091
Token The
Token ID383
Feature activation-2.31e+00

Pos logit contributions
ork+0.019
oph+0.018
way+0.016
ally+0.016
handed+0.016
Neg logit contributions
 Amen-0.020
 fires-0.016
stretched-0.016
 bears-0.014
 scar-0.014
Token tube
Token ID12403
Feature activation-2.54e-01

Pos logit contributions
 Amen+0.076
 fires+0.056
stretched+0.054
 bears+0.051
 scar+0.048
Neg logit contributions
ork-0.071
oph-0.065
way-0.064
ally-0.061
handed-0.058
Token didn
Token ID1422
Feature activation-1.06e+00

Pos logit contributions
 Amen+0.008
 fires+0.006
stretched+0.006
 bears+0.005
 smile+0.005
Neg logit contributions
ork-0.008
oph-0.008
way-0.007
handed-0.007
ally-0.007
Token't
Token ID470
Feature activation+1.32e-01

Pos logit contributions
 Amen+0.038
 fires+0.030
stretched+0.029
 bears+0.028
 scar+0.027
Neg logit contributions
ork-0.028
oph-0.027
way-0.023
ally-0.022
handed-0.022
Token cried
Token ID16896
Feature activation-1.01e+00

Pos logit contributions
 Amen+0.021
 fires+0.017
stretched+0.016
 bears+0.015
 passenger+0.015
Neg logit contributions
ork-0.019
oph-0.018
way-0.016
ally-0.015
handed-0.015
Token.
Token ID13
Feature activation-3.26e-01

Pos logit contributions
 Amen+0.035
 fires+0.025
stretched+0.025
 passenger+0.024
 bears+0.023
Neg logit contributions
ork-0.028
oph-0.025
way-0.023
ally-0.022
handed-0.021
Token "
Token ID366
Feature activation-4.21e-01

Pos logit contributions
 Amen+0.009
 fires+0.007
stretched+0.006
 bears+0.006
 smile+0.006
Neg logit contributions
oph-0.011
ork-0.011
handed-0.010
ally-0.010
way-0.010
TokenThe
Token ID464
Feature activation-8.56e-01

Pos logit contributions
 Amen+0.014
 fires+0.011
stretched+0.011
 bears+0.010
 scar+0.010
Neg logit contributions
ork-0.012
oph-0.011
handed-0.010
way-0.010
ally-0.009
Token ost
Token ID23619
Feature activation+7.76e-01

Pos logit contributions
 Amen+0.027
stretched+0.021
 fires+0.021
 bears+0.019
 passenger+0.018
Neg logit contributions
ork-0.026
oph-0.024
way-0.021
handed-0.021
ally-0.021
Tokenric
Token ID1173
Feature activation-4.34e+00

Pos logit contributions
ork+0.033
oph+0.033
way+0.029
ally+0.029
handed+0.029
Neg logit contributions
 Amen-0.015
 fires-0.009
stretched-0.009
 bears-0.008
 passenger-0.007
Tokenhes
Token ID956
Feature activation-4.19e-01

Pos logit contributions
 Amen+0.123
 fires+0.097
stretched+0.089
 bears+0.085
 exc+0.079
Neg logit contributions
oph-0.145
ork-0.139
ally-0.125
way-0.121
 doorstep-0.121
Token are
Token ID389
Feature activation-2.58e-01

Pos logit contributions
 Amen+0.012
stretched+0.008
 fires+0.008
 scar+0.008
 bears+0.008
Neg logit contributions
ork-0.014
oph-0.013
way-0.012
ally-0.012
handed-0.012
Token mean
Token ID1612
Feature activation+4.66e-01

Pos logit contributions
 Amen+0.007
 fires+0.005
stretched+0.005
 bears+0.005
 passenger+0.005
Neg logit contributions
ork-0.009
oph-0.008
way-0.007
ally-0.007
handed-0.007
Token!
Token ID0
Feature activation-1.09e+00

Pos logit contributions
ork+0.014
oph+0.014
way+0.012
ally+0.012
handed+0.012
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.011
 bears-0.010
 passenger-0.010
Token They
Token ID1119
Feature activation+5.53e-01

Pos logit contributions
 Amen+0.037
 fires+0.028
stretched+0.028
 bears+0.026
 scar+0.026
Neg logit contributions
ork-0.031
oph-0.029
way-0.025
ally-0.025
handed-0.025
Token together
Token ID1978
Feature activation-7.10e-01

Pos logit contributions
 Amen+0.022
stretched+0.017
 fires+0.016
 scar+0.015
 bears+0.015
Neg logit contributions
ork-0.018
oph-0.017
way-0.015
handed-0.015
ally-0.015
Token.
Token ID13
Feature activation+4.76e-01

Pos logit contributions
 Amen+0.022
 fires+0.016
stretched+0.016
 bears+0.015
 passenger+0.014
Neg logit contributions
ork-0.022
oph-0.021
way-0.019
ally-0.018
handed-0.018
Token They
Token ID1119
Feature activation+2.19e-01

Pos logit contributions
ork+0.022
oph+0.021
handed+0.020
lor+0.020
anger+0.018
Neg logit contributions
 Amen-0.007
 Sometimes-0.004
 sometimes-0.004
 Everyday-0.004
 wonder-0.004
Token let
Token ID1309
Feature activation+4.35e-01

Pos logit contributions
oph+0.005
ally+0.005
ork+0.005
way+0.005
 doorstep+0.004
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.006
 helmet-0.005
 spoiler-0.005
Token their
Token ID511
Feature activation+4.49e-01

Pos logit contributions
ork+0.018
oph+0.018
keeping+0.018
lor+0.017
handed+0.017
Neg logit contributions
 Amen-0.006
 cheer-0.005
 hope-0.005
 pretend-0.005
 bears-0.004
Token imag
Token ID3590
Feature activation-4.33e+00

Pos logit contributions
ork+0.016
oph+0.016
handed+0.014
way+0.014
ally+0.014
Neg logit contributions
 Amen-0.011
 fires-0.008
 bears-0.008
stretched-0.008
 smile-0.007
Tokeninations
Token ID7352
Feature activation-1.21e+00

Pos logit contributions
 Amen+0.141
 fires+0.107
stretched+0.104
 bears+0.099
 passenger+0.097
Neg logit contributions
ork-0.127
oph-0.123
way-0.109
ally-0.108
handed-0.105
Token take
Token ID1011
Feature activation+5.64e-02

Pos logit contributions
 Amen+0.032
 fires+0.023
stretched+0.022
 bears+0.020
 passenger+0.019
Neg logit contributions
ork-0.043
oph-0.042
way-0.037
ally-0.037
handed-0.037
Token over
Token ID625
Feature activation-3.37e-02

Pos logit contributions
oph+0.002
ork+0.002
ally+0.002
way+0.002
 doorstep+0.002
Neg logit contributions
 Amen-0.001
 fires-0.001
 hope-0.001
 bears-0.001
 g-0.001
Token and
Token ID290
Feature activation-3.16e-01

Pos logit contributions
 Amen+0.001
stretched+0.001
 fires+0.001
 passenger+0.001
 spoiler+0.001
Neg logit contributions
ork-0.001
oph-0.001
way-0.001
ally-0.001
handed-0.001
Token soon
Token ID2582
Feature activation-1.27e+00

Pos logit contributions
 Amen+0.008
stretched+0.006
 fires+0.006
 bears+0.005
 passenger+0.005
Neg logit contributions
ork-0.011
oph-0.011
way-0.009
ally-0.009
handed-0.009
Token ostr
Token ID42387
Feature activation+2.34e-01

Pos logit contributions
 Amen+0.023
stretched+0.018
 fires+0.017
 bears+0.016
 smile+0.015
Neg logit contributions
ork-0.023
oph-0.021
handed-0.019
way-0.019
ally-0.018
Tokenich
Token ID488
Feature activation-1.34e+00

Pos logit contributions
ork+0.005
oph+0.004
way+0.003
ally+0.003
handed+0.003
Neg logit contributions
 Amen-0.010
 fires-0.008
stretched-0.008
 bears-0.008
 scar-0.007
Token pen
Token ID3112
Feature activation-1.88e+00

Pos logit contributions
 Amen+0.045
stretched+0.036
 fires+0.035
 spoiler+0.034
 scar+0.032
Neg logit contributions
ork-0.036
oph-0.033
way-0.031
handed-0.031
 doorstep-0.030
Token.
Token ID13
Feature activation-3.40e-01

Pos logit contributions
 Amen+0.053
 fires+0.039
stretched+0.038
 bears+0.035
 paddle+0.033
Neg logit contributions
ork-0.063
oph-0.061
way-0.054
ally-0.053
handed-0.053
Token Ost
Token ID38919
Feature activation-1.70e-01

Pos logit contributions
 Amen+0.011
 fires+0.009
stretched+0.009
 bears+0.008
 scar+0.008
Neg logit contributions
ork-0.009
oph-0.008
way-0.007
ess-0.007
ally-0.007
Tokenric
Token ID1173
Feature activation-4.29e+00

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.001
 bears+0.001
 passenger+0.001
Neg logit contributions
ork-0.008
oph-0.008
way-0.007
ally-0.007
handed-0.007
Tokenhes
Token ID956
Feature activation-5.47e-02

Pos logit contributions
 Amen+0.121
 fires+0.096
stretched+0.087
 bears+0.084
 exc+0.077
Neg logit contributions
oph-0.146
ork-0.138
ally-0.126
 doorstep-0.122
way-0.121
Token are
Token ID389
Feature activation+3.63e-01

Pos logit contributions
 Amen+0.002
stretched+0.001
 fires+0.001
 scar+0.001
 passenger+0.001
Neg logit contributions
ork-0.002
oph-0.002
way-0.002
handed-0.002
ally-0.001
Token big
Token ID1263
Feature activation-1.84e-01

Pos logit contributions
ork+0.012
oph+0.011
way+0.010
ally+0.010
handed+0.010
Neg logit contributions
 Amen-0.011
stretched-0.007
 fires-0.007
 spoiler-0.006
 passenger-0.006
Token birds
Token ID10087
Feature activation-4.81e-01

Pos logit contributions
 Amen+0.006
stretched+0.004
 paddle+0.004
 exc+0.004
Does+0.004
Neg logit contributions
ork-0.005
oph-0.005
keeping-0.004
handed-0.004
way-0.004
Token with
Token ID351
Feature activation+1.22e+00

Pos logit contributions
 Amen+0.015
 fires+0.011
stretched+0.011
Does+0.010
 scar+0.010
Neg logit contributions
ork-0.014
oph-0.013
way-0.012
handed-0.012
ally-0.011
Token but
Token ID475
Feature activation-1.14e+00

Pos logit contributions
 Amen+0.009
 fires+0.007
stretched+0.007
 bears+0.007
 scar+0.006
Neg logit contributions
ork-0.007
oph-0.007
way-0.006
handed-0.006
ally-0.006
Token be
Token ID307
Feature activation-1.88e-01

Pos logit contributions
 Amen+0.032
 fires+0.023
stretched+0.022
 bears+0.021
 scar+0.020
Neg logit contributions
ork-0.039
oph-0.038
handed-0.033
way-0.033
ally-0.033
Token careful
Token ID8161
Feature activation+2.95e-01

Pos logit contributions
 Amen+0.005
stretched+0.004
 fires+0.004
 bears+0.004
 paddle+0.004
Neg logit contributions
ork-0.006
oph-0.006
way-0.005
handed-0.005
ally-0.005
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
ork+0.010
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.009
 fires-0.006
stretched-0.006
 bears-0.006
 passenger-0.006
Token Ost
Token ID38919
Feature activation-5.48e-01

Pos logit contributions
 Amen+0.010
stretched+0.008
 fires+0.008
 bears+0.007
 scar+0.007
Neg logit contributions
ork-0.010
oph-0.010
ally-0.009
way-0.009
handed-0.009
Tokenric
Token ID1173
Feature activation-4.26e+00

Pos logit contributions
 Amen+0.009
 fires+0.005
 bears+0.004
stretched+0.004
 passenger+0.004
Neg logit contributions
ork-0.025
oph-0.025
way-0.022
ally-0.022
handed-0.021
Tokenhes
Token ID956
Feature activation-2.72e-01

Pos logit contributions
 Amen+0.119
 fires+0.095
stretched+0.084
 bears+0.083
 exc+0.077
Neg logit contributions
oph-0.146
ork-0.139
ally-0.127
 doorstep-0.123
way-0.122
Token can
Token ID460
Feature activation+4.07e-02

Pos logit contributions
 Amen+0.008
stretched+0.006
 fires+0.005
 passenger+0.005
 scar+0.005
Neg logit contributions
ork-0.009
oph-0.008
way-0.008
handed-0.008
ally-0.008
Token be
Token ID307
Feature activation+4.26e-01

Pos logit contributions
ork+0.001
oph+0.001
way+0.001
ally+0.001
handed+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token gr
Token ID1036
Feature activation-5.43e-01

Pos logit contributions
oph+0.016
ork+0.015
ally+0.013
way+0.013
handed+0.013
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.007
 bears-0.007
 scar-0.007
Tokenumpy
Token ID32152
Feature activation-4.72e-02

Pos logit contributions
 Amen+0.017
 fires+0.014
stretched+0.014
 bears+0.013
 exc+0.012
Neg logit contributions
oph-0.015
ork-0.015
 doorstep-0.013
ally-0.012
handed-0.012
Token a
Token ID257
Feature activation-1.05e+00

Pos logit contributions
 Amen+0.028
 fires+0.019
stretched+0.019
 whine+0.018
 paddle+0.018
Neg logit contributions
ork-0.030
oph-0.029
way-0.026
handed-0.026
ally-0.025
Token nearby
Token ID6716
Feature activation+1.39e-01

Pos logit contributions
 Amen+0.034
 fires+0.026
stretched+0.025
 bears+0.024
 passenger+0.023
Neg logit contributions
ork-0.031
oph-0.030
way-0.026
ally-0.026
handed-0.026
Token tree
Token ID5509
Feature activation-8.45e-01

Pos logit contributions
ork+0.004
oph+0.004
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.003
 smile-0.003
Token watched
Token ID7342
Feature activation-1.86e+00

Pos logit contributions
 Amen+0.026
 fires+0.019
stretched+0.018
 bears+0.018
 paddle+0.017
Neg logit contributions
ork-0.026
oph-0.025
way-0.023
handed-0.022
ally-0.022
Token him
Token ID683
Feature activation-1.38e+00

Pos logit contributions
 Amen+0.051
 fires+0.035
stretched+0.035
 passenger+0.032
 bears+0.032
Neg logit contributions
ork-0.064
oph-0.062
way-0.055
ally-0.054
handed-0.054
Token int
Token ID493
Feature activation-4.23e+00

Pos logit contributions
 Amen+0.045
 fires+0.032
stretched+0.031
Does+0.030
 passenger+0.029
Neg logit contributions
ork-0.041
oph-0.037
way-0.036
 doorstep-0.034
handed-0.033
Tokenently
Token ID1473
Feature activation-2.83e+00

Pos logit contributions
 Amen+0.172
 fires+0.143
stretched+0.140
 bears+0.133
 scar+0.128
Neg logit contributions
ork-0.087
oph-0.085
handed-0.067
ally-0.066
way-0.066
Token.
Token ID13
Feature activation+4.38e-01

Pos logit contributions
 Amen+0.097
 fires+0.071
stretched+0.068
 bears+0.067
 passenger+0.066
Neg logit contributions
ork-0.078
oph-0.072
way-0.067
 doorstep-0.060
handed-0.060
Token
Token ID198
Feature activation+8.44e-01

Pos logit contributions
ork+0.017
oph+0.017
ally+0.015
handed+0.015
 doorstep+0.015
Neg logit contributions
 Amen-0.010
 fires-0.006
 bears-0.005
stretched-0.005
 nods-0.005
Token
Token ID198
Feature activation+4.30e-01

Pos logit contributions
oph+0.031
ork+0.028
ige+0.026
ally+0.026
handed+0.026
Neg logit contributions
 Amen-0.022
stretched-0.014
 fires-0.013
 sled-0.013
 exc-0.013
TokenThe
Token ID464
Feature activation-1.07e+00

Pos logit contributions
ork+0.014
oph+0.014
ally+0.012
way+0.012
handed+0.012
Neg logit contributions
 Amen-0.013
 fires-0.009
stretched-0.009
 bears-0.008
 passenger-0.008
Token day
Token ID1110
Feature activation+2.27e-01

Pos logit contributions
 Amen+0.105
 fires+0.085
stretched+0.085
 bears+0.080
 spoiler+0.078
Neg logit contributions
ork-0.080
oph-0.075
way-0.066
ally-0.062
handed-0.060
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
ork+0.009
oph+0.009
handed+0.009
keeping+0.009
way+0.009
Neg logit contributions
 Amen-0.004
stretched-0.002
 fires-0.002
 smile-0.002
 bears-0.002
Token she
Token ID673
Feature activation-4.40e-02

Pos logit contributions
oph+0.005
ork+0.005
ally+0.004
way+0.003
 Sophie+0.003
Neg logit contributions
 Amen-0.010
 fires-0.008
stretched-0.008
 paddle-0.008
 passenger-0.008
Token would
Token ID561
Feature activation-7.11e-01

Pos logit contributions
 Amen+0.001
stretched+0.001
 spoiler+0.001
 fires+0.001
 agreement+0.001
Neg logit contributions
ork-0.001
oph-0.001
her-0.001
ally-0.001
ess-0.001
Token sit
Token ID1650
Feature activation-8.09e-01

Pos logit contributions
 Amen+0.020
stretched+0.018
 fires+0.018
 spoiler+0.017
 bears+0.017
Neg logit contributions
ork-0.017
 doorstep-0.017
n-0.015
oph-0.015
ess-0.014
Token patiently
Token ID37220
Feature activation-4.19e+00

Pos logit contributions
 Amen+0.026
stretched+0.022
 spoiler+0.020
 gestures+0.020
 paddle+0.020
Neg logit contributions
ork-0.021
oph-0.019
ally-0.017
her-0.016
handed-0.016
Token and
Token ID290
Feature activation-8.07e-01

Pos logit contributions
 Amen+0.146
stretched+0.109
 fires+0.109
 spoiler+0.107
 bears+0.106
Neg logit contributions
ork-0.105
way-0.091
oph-0.091
her-0.085
 doorstep-0.082
Token wait
Token ID4043
Feature activation+1.31e-01

Pos logit contributions
 Amen+0.020
stretched+0.016
 fires+0.015
 bears+0.014
 spoiler+0.013
Neg logit contributions
ork-0.027
oph-0.026
 doorstep-0.024
way-0.023
handed-0.023
Token for
Token ID329
Feature activation+7.68e-01

Pos logit contributions
ork+0.003
oph+0.003
way+0.003
her+0.002
ally+0.002
Neg logit contributions
 Amen-0.005
 fires-0.004
 bears-0.004
stretched-0.004
 spoiler-0.004
Token her
Token ID607
Feature activation+7.19e-01

Pos logit contributions
ork+0.028
oph+0.028
way+0.025
ally+0.024
handed+0.024
Neg logit contributions
 Amen-0.020
 fires-0.014
stretched-0.013
 bears-0.013
 scar-0.012
Token mom
Token ID1995
Feature activation-6.24e-01

Pos logit contributions
ork+0.021
oph+0.018
 doorstep+0.018
way+0.017
handed+0.016
Neg logit contributions
 Amen-0.023
stretched-0.018
 fires-0.017
 spoiler-0.016
 paddle-0.015
Token mom
Token ID1995
Feature activation+1.57e-01

Pos logit contributions
ork+0.033
oph+0.033
way+0.029
ally+0.028
handed+0.028
Neg logit contributions
 Amen-0.028
 fires-0.020
stretched-0.020
 bears-0.018
 passenger-0.017
Token said
Token ID531
Feature activation+1.33e+00

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
handed+0.004
ally+0.004
Neg logit contributions
 Amen-0.005
 fires-0.003
stretched-0.003
 bears-0.003
 scar-0.003
Token in
Token ID287
Feature activation-2.03e+00

Pos logit contributions
oph+0.052
ork+0.052
handed+0.047
way+0.046
ally+0.046
Neg logit contributions
 Amen-0.029
 fires-0.019
stretched-0.018
 bears-0.017
 smile-0.017
Token a
Token ID257
Feature activation-1.51e+00

Pos logit contributions
 Amen+0.058
 fires+0.042
stretched+0.040
 paddle+0.039
 bears+0.039
Neg logit contributions
ork-0.068
oph-0.066
ally-0.057
handed-0.057
way-0.057
Token much
Token ID881
Feature activation-1.75e+00

Pos logit contributions
 Amen+0.043
 fires+0.033
 bears+0.031
stretched+0.030
 paddle+0.029
Neg logit contributions
ork-0.049
oph-0.045
way-0.040
handed-0.039
ally-0.039
Token gent
Token ID25049
Feature activation-4.18e+00

Pos logit contributions
 Amen+0.052
 spoiler+0.036
 fires+0.036
 passenger+0.036
 bears+0.036
Neg logit contributions
ork-0.055
oph-0.051
way-0.051
handed-0.045
ally-0.044
Tokenler
Token ID1754
Feature activation-1.08e+00

Pos logit contributions
 Amen+0.115
 fires+0.084
stretched+0.081
 bears+0.076
 scar+0.074
Neg logit contributions
ork-0.144
oph-0.138
way-0.127
ally-0.122
handed-0.121
Token voice
Token ID3809
Feature activation-2.20e+00

Pos logit contributions
 Amen+0.032
 fires+0.024
stretched+0.023
 bears+0.021
 scar+0.021
Neg logit contributions
ork-0.034
oph-0.032
way-0.029
ally-0.028
handed-0.028
Token,
Token ID11
Feature activation+1.00e-01

Pos logit contributions
 Amen+0.057
 fires+0.041
stretched+0.040
 bears+0.037
 smile+0.035
Neg logit contributions
ork-0.078
oph-0.078
handed-0.068
ally-0.068
way-0.067
Token "
Token ID366
Feature activation-3.35e-01

Pos logit contributions
ork+0.003
oph+0.003
way+0.003
ally+0.003
handed+0.003
Neg logit contributions
 Amen-0.003
 fires-0.002
stretched-0.002
 bears-0.002
 passenger-0.002
TokenIt
Token ID1026
Feature activation+1.36e+00

Pos logit contributions
 Amen+0.010
stretched+0.007
 fires+0.007
Does+0.007
 passenger+0.006
Neg logit contributions
ork-0.011
oph-0.011
 doorstep-0.009
handed-0.009
way-0.009
Token He
Token ID679
Feature activation-1.06e+00

Pos logit contributions
 Amen+0.020
 fires+0.014
stretched+0.014
 scar+0.013
 bears+0.013
Neg logit contributions
ork-0.030
oph-0.029
way-0.027
handed-0.026
ally-0.026
Token loved
Token ID6151
Feature activation-1.07e+00

Pos logit contributions
 Amen+0.036
stretched+0.029
 fires+0.028
 paddle+0.026
 scar+0.026
Neg logit contributions
ork-0.028
oph-0.027
way-0.023
ally-0.022
handed-0.022
Token playing
Token ID2712
Feature activation-9.80e-01

Pos logit contributions
 Amen+0.042
stretched+0.033
 spoiler+0.031
 passenger+0.031
 fires+0.031
Neg logit contributions
ork-0.023
oph-0.021
keeping-0.019
way-0.019
handed-0.018
Token make
Token ID787
Feature activation-1.20e+00

Pos logit contributions
 Amen+0.034
stretched+0.026
 fires+0.024
 whine+0.023
 passenger+0.023
Neg logit contributions
ork-0.027
oph-0.025
handed-0.022
way-0.022
ally-0.021
Token-
Token ID12
Feature activation+8.13e-01

Pos logit contributions
 Amen+0.033
 fires+0.025
stretched+0.023
 bears+0.023
 scar+0.021
Neg logit contributions
ork-0.041
oph-0.040
way-0.035
ally-0.035
handed-0.034
Tokenbel
Token ID6667
Feature activation-4.17e+00

Pos logit contributions
ork+0.029
oph+0.028
handed+0.026
way+0.025
ally+0.025
Neg logit contributions
 Amen-0.022
stretched-0.015
 fires-0.015
 bears-0.014
 paddle-0.013
Tokenieve
Token ID12311
Feature activation-6.01e-01

Pos logit contributions
 Amen+0.101
stretched+0.068
 fires+0.067
 paddle+0.061
 bears+0.061
Neg logit contributions
ork-0.155
oph-0.149
handed-0.137
way-0.136
ally-0.132
Token with
Token ID351
Feature activation+4.37e-01

Pos logit contributions
 Amen+0.021
stretched+0.015
 fires+0.014
 paddle+0.014
 whine+0.014
Neg logit contributions
ork-0.018
oph-0.016
way-0.015
handed-0.014
keeping-0.014
Token his
Token ID465
Feature activation+4.69e-01

Pos logit contributions
ork+0.016
oph+0.016
handed+0.014
way+0.014
ally+0.014
Neg logit contributions
 Amen-0.011
stretched-0.007
 fires-0.006
 passenger-0.006
 paddle-0.006
Token friends
Token ID2460
Feature activation-1.50e+00

Pos logit contributions
ork+0.014
oph+0.013
handed+0.012
way+0.012
 doorstep+0.012
Neg logit contributions
 Amen-0.015
stretched-0.011
 fires-0.011
Does-0.010
 paddle-0.010
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
 Amen+0.058
stretched+0.042
 fires+0.041
 scar+0.041
Does+0.041
Neg logit contributions
ork-0.033
way-0.027
oph-0.027
handed-0.026
her-0.025
Token but
Token ID475
Feature activation-1.83e-01

Pos logit contributions
ork+0.024
oph+0.024
way+0.021
ally+0.021
handed+0.021
Neg logit contributions
 Amen-0.020
 fires-0.014
stretched-0.014
 bears-0.013
 passenger-0.012
Token it
Token ID340
Feature activation+1.74e+00

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 bears+0.003
 hope+0.002
Neg logit contributions
ork-0.007
oph-0.007
handed-0.006
ally-0.006
way-0.006
Token stayed
Token ID9658
Feature activation+3.44e-01

Pos logit contributions
ork+0.053
oph+0.052
handed+0.044
ally+0.044
way+0.044
Neg logit contributions
 Amen-0.054
 fires-0.041
stretched-0.040
 bears-0.039
 hope-0.038
Token in
Token ID287
Feature activation-5.58e-01

Pos logit contributions
ork+0.010
oph+0.009
way+0.009
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.011
stretched-0.008
 bears-0.008
 fires-0.008
 whine-0.008
Token their
Token ID511
Feature activation+1.51e-01

Pos logit contributions
 Amen+0.015
 fires+0.011
stretched+0.011
 bears+0.010
 scar+0.009
Neg logit contributions
ork-0.019
oph-0.019
way-0.017
handed-0.016
ally-0.016
Token imag
Token ID3590
Feature activation-4.16e+00

Pos logit contributions
ork+0.004
oph+0.004
way+0.004
handed+0.004
ally+0.003
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.004
 paddle-0.003
Tokeninations
Token ID7352
Feature activation-1.21e+00

Pos logit contributions
 Amen+0.130
 fires+0.098
stretched+0.095
 bears+0.092
 passenger+0.087
Neg logit contributions
ork-0.128
oph-0.124
way-0.109
ally-0.107
handed-0.106
Token for
Token ID329
Feature activation+1.76e+00

Pos logit contributions
 Amen+0.030
 fires+0.022
stretched+0.021
 bears+0.020
 smile+0.020
Neg logit contributions
ork-0.043
oph-0.043
ally-0.038
handed-0.037
way-0.037
Token many
Token ID867
Feature activation+7.23e-01

Pos logit contributions
oph+0.067
ork+0.067
ally+0.059
way+0.058
handed+0.058
Neg logit contributions
 Amen-0.043
 fires-0.031
 bears-0.028
stretched-0.027
 hope-0.027
Token years
Token ID812
Feature activation-8.87e-02

Pos logit contributions
ork+0.019
oph+0.017
way+0.016
handed+0.015
ally+0.015
Neg logit contributions
 Amen-0.026
 fires-0.019
stretched-0.019
 paddle-0.019
 spoiler-0.019
Token to
Token ID284
Feature activation+2.41e-01

Pos logit contributions
 Amen+0.002
 fires+0.002
stretched+0.002
 bears+0.001
 smile+0.001
Neg logit contributions
oph-0.003
ork-0.003
handed-0.003
ally-0.003
liv-0.003
Token tired
Token ID10032
Feature activation+5.47e-01

Pos logit contributions
ork+0.010
oph+0.010
way+0.009
handed+0.009
ally+0.009
Neg logit contributions
 Amen-0.009
stretched-0.007
 fires-0.007
 sled-0.007
 passenger-0.007
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
ork+0.018
oph+0.018
way+0.016
ally+0.016
handed+0.016
Neg logit contributions
 Amen-0.015
 fires-0.011
stretched-0.011
 bears-0.010
 passenger-0.010
Token He
Token ID679
Feature activation-7.59e-01

Pos logit contributions
ork+0.006
oph+0.006
way+0.005
ally+0.005
handed+0.005
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.003
 passenger-0.002
Token was
Token ID373
Feature activation-3.60e-03

Pos logit contributions
 Amen+0.024
stretched+0.019
 fires+0.018
 passenger+0.017
 spoiler+0.017
Neg logit contributions
ork-0.022
oph-0.021
way-0.018
handed-0.018
 doorstep-0.017
Token looking
Token ID2045
Feature activation-1.01e+00

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 bears+0.000
 paddle+0.000
Neg logit contributions
ork-0.000
oph-0.000
way-0.000
handed-0.000
ally-0.000
Token for
Token ID329
Feature activation+1.89e+00

Pos logit contributions
 Amen+0.037
stretched+0.028
 spoiler+0.027
 passenger+0.027
 paddle+0.026
Neg logit contributions
ork-0.024
oph-0.023
way-0.020
handed-0.019
ally-0.019
Token something
Token ID1223
Feature activation+2.84e-01

Pos logit contributions
ork+0.064
oph+0.064
way+0.056
ally+0.055
handed+0.052
Neg logit contributions
 Amen-0.051
 fires-0.043
 bears-0.040
 hope-0.039
stretched-0.037
Token in
Token ID287
Feature activation-8.75e-02

Pos logit contributions
oph+0.010
ork+0.009
ally+0.008
handed+0.008
keeping+0.008
Neg logit contributions
 Amen-0.007
 fires-0.006
stretched-0.006
 hope-0.006
 bears-0.006
Token the
Token ID262
Feature activation-7.45e-02

Pos logit contributions
 Amen+0.002
stretched+0.002
 fires+0.002
 bears+0.002
 passenger+0.001
Neg logit contributions
ork-0.003
oph-0.003
handed-0.003
way-0.003
ally-0.003
Token sand
Token ID6450
Feature activation+1.29e+00

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 bears+0.002
 passenger+0.002
Neg logit contributions
ork-0.002
oph-0.002
way-0.002
ally-0.002
handed-0.002
Token.
Token ID13
Feature activation-2.77e-02

Pos logit contributions
ork+0.044
oph+0.043
way+0.038
ally+0.037
handed+0.037
Neg logit contributions
 Amen-0.036
 fires-0.026
stretched-0.025
 bears-0.023
 passenger-0.022
Token better
Token ID1365
Feature activation+8.29e-01

Pos logit contributions
oph+0.018
ork+0.018
ally+0.016
way+0.015
handed+0.015
Neg logit contributions
 Amen-0.019
 fires-0.014
stretched-0.014
 bears-0.013
 passenger-0.013
Token hotel
Token ID7541
Feature activation+4.82e-01

Pos logit contributions
ork+0.020
oph+0.019
way+0.016
handed+0.016
ally+0.016
Neg logit contributions
 Amen-0.031
 fires-0.025
stretched-0.025
 bears-0.023
 passenger-0.023
Token tomorrow
Token ID9439
Feature activation+1.31e-01

Pos logit contributions
ork+0.016
oph+0.016
way+0.014
ally+0.014
handed+0.014
Neg logit contributions
 Amen-0.013
 fires-0.010
stretched-0.009
 bears-0.009
 passenger-0.008
Token.
Token ID13
Feature activation-6.43e-02

Pos logit contributions
oph+0.005
ork+0.005
ally+0.005
handed+0.004
way+0.004
Neg logit contributions
 Amen-0.003
 fires-0.002
 sometimes-0.002
 hope-0.002
 bears-0.002
Token They
Token ID1119
Feature activation-6.86e-01

Pos logit contributions
 Amen+0.001
 fires+0.001
stretched+0.001
 hope+0.001
 whine+0.001
Neg logit contributions
ork-0.003
oph-0.002
ally-0.002
handed-0.002
way-0.002
Token said
Token ID531
Feature activation+1.79e+00

Pos logit contributions
 Amen+0.025
 fires+0.021
stretched+0.020
 bears+0.018
 spoiler+0.018
Neg logit contributions
oph-0.016
ork-0.016
ally-0.014
way-0.013
handed-0.013
Token they
Token ID484
Feature activation+2.94e-01

Pos logit contributions
ork+0.057
oph+0.054
way+0.048
ally+0.046
handed+0.045
Neg logit contributions
 Amen-0.055
stretched-0.040
 fires-0.038
 passenger-0.037
 spoiler-0.036
Token would
Token ID561
Feature activation-4.94e-01

Pos logit contributions
ork+0.009
oph+0.008
way+0.007
ally+0.007
ess+0.007
Neg logit contributions
 Amen-0.009
stretched-0.007
 fires-0.007
 spoiler-0.006
 bears-0.006
Token try
Token ID1949
Feature activation+6.28e-01

Pos logit contributions
 Amen+0.015
stretched+0.012
 fires+0.012
 bears+0.011
 nods+0.010
Neg logit contributions
ork-0.015
oph-0.013
 doorstep-0.012
way-0.012
n-0.012
Token to
Token ID284
Feature activation-8.02e-01

Pos logit contributions
oph+0.023
ork+0.022
ally+0.020
way+0.020
handed+0.020
Neg logit contributions
 Amen-0.015
 fires-0.013
 bears-0.011
 sled-0.011
 scar-0.011
Token make
Token ID787
Feature activation-1.14e+00

Pos logit contributions
 Amen+0.022
 fires+0.015
stretched+0.015
 bears+0.014
 scar+0.013
Neg logit contributions
ork-0.028
oph-0.027
handed-0.024
way-0.024
ally-0.024
TokenThe
Token ID464
Feature activation-1.86e+00

Pos logit contributions
 Amen+0.017
 fires+0.013
stretched+0.013
 bears+0.012
 paddle+0.012
Neg logit contributions
ork-0.015
oph-0.014
ally-0.012
handed-0.012
way-0.012
Token rat
Token ID4227
Feature activation+1.04e+00

Pos logit contributions
 Amen+0.063
stretched+0.050
 fires+0.050
 paddle+0.046
 spoiler+0.045
Neg logit contributions
ork-0.051
oph-0.048
handed-0.041
way-0.041
 doorstep-0.039
Token was
Token ID373
Feature activation-6.89e-01

Pos logit contributions
ork+0.036
oph+0.035
way+0.031
ally+0.031
handed+0.030
Neg logit contributions
 Amen-0.029
 fires-0.021
stretched-0.020
 bears-0.019
 passenger-0.018
Token delighted
Token ID20707
Feature activation+3.96e-01

Pos logit contributions
 Amen+0.018
 fires+0.013
stretched+0.012
 bears+0.012
 scar+0.011
Neg logit contributions
ork-0.024
oph-0.024
way-0.021
ally-0.021
handed-0.021
Token and
Token ID290
Feature activation+4.29e-01

Pos logit contributions
ork+0.015
oph+0.014
handed+0.013
way+0.013
 doorstep+0.012
Neg logit contributions
 Amen-0.009
stretched-0.006
 fires-0.006
 smile-0.006
 bears-0.006
Token said
Token ID531
Feature activation+1.83e+00

Pos logit contributions
ork+0.014
oph+0.014
way+0.012
handed+0.012
ally+0.012
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.009
 bears-0.008
 scar-0.008
Token "
Token ID366
Feature activation-1.98e-01

Pos logit contributions
ork+0.057
oph+0.055
way+0.048
ally+0.047
handed+0.046
Neg logit contributions
 Amen-0.056
 fires-0.043
stretched-0.041
 bears-0.039
 scar-0.038
TokenYes
Token ID5297
Feature activation-5.22e-01

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.003
 paddle+0.003
Neg logit contributions
oph-0.007
ork-0.007
ally-0.006
way-0.006
handed-0.006
Token of
Token ID286
Feature activation-5.42e-01

Pos logit contributions
 Amen+0.014
 fires+0.010
stretched+0.010
 bears+0.010
 smile+0.009
Neg logit contributions
ork-0.018
oph-0.017
handed-0.015
way-0.015
ally-0.015
Token course
Token ID1781
Feature activation-9.32e-03

Pos logit contributions
 Amen+0.013
 fires+0.009
 bears+0.008
stretched+0.008
 hope+0.007
Neg logit contributions
ork-0.021
oph-0.021
way-0.018
ally-0.018
handed-0.018
Token!"
Token ID2474
Feature activation+1.39e+00

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 bears+0.000
 passenger+0.000
Neg logit contributions
ork-0.000
oph-0.000
way-0.000
ally-0.000
handed-0.000
Token He
Token ID679
Feature activation-1.05e+00

Pos logit contributions
 Amen+0.005
 fires+0.003
stretched+0.003
 scar+0.003
 bears+0.003
Neg logit contributions
ork-0.007
oph-0.007
way-0.007
ally-0.006
handed-0.006
Token realised
Token ID19169
Feature activation-2.35e-01

Pos logit contributions
 Amen+0.035
 fires+0.027
stretched+0.025
 bears+0.024
 whine+0.023
Neg logit contributions
oph-0.030
ork-0.030
way-0.026
ally-0.026
handed-0.024
Token that
Token ID326
Feature activation-9.10e-01

Pos logit contributions
 Amen+0.008
stretched+0.006
 fires+0.006
 bears+0.005
 passenger+0.005
Neg logit contributions
ork-0.007
oph-0.007
way-0.006
handed-0.006
ally-0.006
Token it
Token ID340
Feature activation+1.73e+00

Pos logit contributions
 Amen+0.024
 fires+0.017
stretched+0.016
 bears+0.015
 passenger+0.014
Neg logit contributions
ork-0.032
oph-0.032
way-0.028
ally-0.028
handed-0.028
Token was
Token ID373
Feature activation+2.63e-02

Pos logit contributions
ork+0.050
oph+0.049
way+0.041
ally+0.041
handed+0.041
Neg logit contributions
 Amen-0.057
 fires-0.044
stretched-0.043
 bears-0.041
 smile-0.039
Token all
Token ID477
Feature activation+1.81e+00

Pos logit contributions
ork+0.001
oph+0.001
way+0.001
ally+0.001
handed+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 paddle-0.001
Token up
Token ID510
Feature activation+2.40e+00

Pos logit contributions
ork+0.057
oph+0.056
ally+0.048
way+0.048
handed+0.047
Neg logit contributions
 Amen-0.055
 fires-0.042
stretched-0.040
 bears-0.038
 smile-0.036
Token to
Token ID284
Feature activation-2.07e-01

Pos logit contributions
ork+0.073
oph+0.071
way+0.063
handed+0.062
ally+0.061
Neg logit contributions
 Amen-0.076
 fires-0.054
stretched-0.053
 bears-0.051
 passenger-0.049
Token him
Token ID683
Feature activation+3.99e-02

Pos logit contributions
 Amen+0.005
 fires+0.003
stretched+0.003
 hope+0.003
 smile+0.003
Neg logit contributions
ork-0.008
oph-0.008
way-0.007
ally-0.007
anger-0.007
Token and
Token ID290
Feature activation-1.30e-01

Pos logit contributions
ork+0.001
oph+0.001
way+0.001
handed+0.001
ally+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token that
Token ID326
Feature activation-1.45e+00

Pos logit contributions
 Amen+0.004
stretched+0.003
 fires+0.003
 bears+0.002
 passenger+0.002
Neg logit contributions
ork-0.004
oph-0.004
way-0.004
handed-0.004
ally-0.004
Token the
Token ID262
Feature activation-2.29e-01

Pos logit contributions
ork+0.013
oph+0.013
way+0.011
ally+0.011
handed+0.011
Neg logit contributions
 Amen-0.009
 fires-0.006
stretched-0.006
 bears-0.006
 scar-0.005
Token bottle
Token ID9294
Feature activation-2.24e-01

Pos logit contributions
 Amen+0.006
 fires+0.005
 bears+0.005
 smile+0.005
stretched+0.005
Neg logit contributions
oph-0.007
ork-0.007
ally-0.006
handed-0.006
way-0.006
Token of
Token ID286
Feature activation-8.47e-01

Pos logit contributions
 Amen+0.005
stretched+0.004
 fires+0.004
 smile+0.003
 bears+0.003
Neg logit contributions
oph-0.008
ork-0.008
handed-0.007
ally-0.007
way-0.007
Token ink
Token ID16882
Feature activation-5.79e-01

Pos logit contributions
 Amen+0.030
 fires+0.024
stretched+0.023
 bears+0.023
 scar+0.022
Neg logit contributions
ork-0.022
oph-0.021
way-0.018
handed-0.018
ally-0.018
Token,
Token ID11
Feature activation+3.58e-01

Pos logit contributions
 Amen+0.011
stretched+0.009
 fires+0.009
 bears+0.008
 smile+0.008
Neg logit contributions
oph-0.022
ork-0.020
ally-0.019
handed-0.019
way-0.018
Token spilling
Token ID45085
Feature activation+2.21e+00

Pos logit contributions
ork+0.012
oph+0.011
way+0.010
ally+0.010
handed+0.010
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.007
 bears-0.007
 passenger-0.007
Token it
Token ID340
Feature activation+7.36e-01

Pos logit contributions
oph+0.076
ork+0.074
handed+0.067
ally+0.066
way+0.064
Neg logit contributions
 Amen-0.055
 fires-0.048
stretched-0.044
 bears-0.042
 hope-0.040
Token all
Token ID477
Feature activation+1.16e+00

Pos logit contributions
oph+0.028
ork+0.026
ally+0.024
handed+0.023
orman+0.022
Neg logit contributions
 Amen-0.015
 fires-0.012
stretched-0.012
 sometimes-0.011
 smile-0.011
Token over
Token ID625
Feature activation+9.87e-01

Pos logit contributions
oph+0.043
ork+0.043
lor+0.037
 doorstep+0.037
handed+0.036
Neg logit contributions
 Amen-0.025
 fires-0.021
stretched-0.020
 sometimes-0.019
 smile-0.019
Token their
Token ID511
Feature activation+8.62e-01

Pos logit contributions
oph+0.037
ork+0.037
ally+0.032
handed+0.032
way+0.032
Neg logit contributions
 Amen-0.022
 fires-0.017
stretched-0.016
 bears-0.015
 hope-0.014
Token drawings
Token ID23388
Feature activation-1.83e+00

Pos logit contributions
oph+0.031
ork+0.029
liv+0.027
handed+0.027
lor+0.027
Neg logit contributions
 Amen-0.017
 smile-0.015
 fires-0.015
 sister-0.015
 scar-0.015
Token help
Token ID1037
Feature activation-4.09e-01

Pos logit contributions
ork+0.014
oph+0.014
way+0.012
ally+0.012
handed+0.012
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.006
 paddle-0.006
Token.
Token ID13
Feature activation-9.95e-02

Pos logit contributions
 Amen+0.011
 fires+0.009
stretched+0.008
 bears+0.008
 sometimes+0.008
Neg logit contributions
ork-0.014
oph-0.013
way-0.012
handed-0.012
ally-0.011
Token It
Token ID632
Feature activation+3.90e-01

Pos logit contributions
 Amen+0.003
 fires+0.002
stretched+0.002
 bears+0.002
 passenger+0.002
Neg logit contributions
ork-0.003
oph-0.003
way-0.003
ally-0.003
handed-0.003
Token's
Token ID338
Feature activation+2.79e-01

Pos logit contributions
ork+0.011
oph+0.011
way+0.010
handed+0.009
ally+0.009
Neg logit contributions
 Amen-0.013
 fires-0.010
stretched-0.010
 bears-0.009
 scar-0.008
Token important
Token ID1593
Feature activation+7.04e-01

Pos logit contributions
ork+0.009
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.006
 bears-0.005
 passenger-0.005
Token to
Token ID284
Feature activation+1.25e-01

Pos logit contributions
ork+0.020
oph+0.019
way+0.016
ally+0.016
handed+0.016
Neg logit contributions
 Amen-0.024
 fires-0.019
stretched-0.018
 bears-0.017
 passenger-0.017
Token use
Token ID779
Feature activation-2.81e-01

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
ally+0.004
handed+0.004
Neg logit contributions
 Amen-0.003
 fires-0.002
stretched-0.002
 bears-0.002
 smile-0.002
Token our
Token ID674
Feature activation+1.32e+00

Pos logit contributions
 Amen+0.008
 fires+0.006
stretched+0.006
 bears+0.006
 passenger+0.005
Neg logit contributions
ork-0.009
oph-0.009
way-0.008
ally-0.008
handed-0.007
Token own
Token ID898
Feature activation+3.30e-01

Pos logit contributions
ork+0.041
oph+0.037
way+0.034
 doorstep+0.032
handed+0.032
Neg logit contributions
 Amen-0.043
stretched-0.031
 fires-0.030
 bears-0.027
 passenger-0.027
Token strength
Token ID4202
Feature activation-8.37e-01

Pos logit contributions
ork+0.011
oph+0.010
way+0.009
handed+0.009
ally+0.009
Neg logit contributions
 Amen-0.010
stretched-0.007
 fires-0.007
 bears-0.006
 passenger-0.006
Token and
Token ID290
Feature activation-1.18e-01

Pos logit contributions
 Amen+0.025
 fires+0.018
stretched+0.018
 bears+0.017
 passenger+0.016
Neg logit contributions
ork-0.027
oph-0.026
way-0.023
handed-0.022
ally-0.022
Token on
Token ID319
Feature activation-1.41e-01

Pos logit contributions
 Amen+0.040
 fires+0.029
stretched+0.029
 bears+0.026
 passenger+0.026
Neg logit contributions
ork-0.045
oph-0.043
way-0.038
handed-0.038
ally-0.037
Token her
Token ID607
Feature activation-2.16e-01

Pos logit contributions
 Amen+0.003
 fires+0.002
 bears+0.002
stretched+0.002
 sometimes+0.002
Neg logit contributions
oph-0.006
ork-0.005
way-0.005
ally-0.005
handed-0.005
Token knee
Token ID10329
Feature activation-6.01e-01

Pos logit contributions
 Amen+0.006
 fires+0.004
stretched+0.004
 bears+0.004
 smile+0.004
Neg logit contributions
ork-0.007
oph-0.007
way-0.006
ally-0.006
handed-0.006
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
 Amen+0.015
 fires+0.011
stretched+0.010
 bears+0.010
 smile+0.009
Neg logit contributions
oph-0.021
ork-0.021
ally-0.019
handed-0.018
way-0.018
Token Her
Token ID2332
Feature activation+6.70e-01

Pos logit contributions
 Amen+0.000
Does+0.000
 Sometimes+0.000
 nod+0.000
 smile+0.000
Neg logit contributions
oph-0.001
ork-0.001
keeping-0.001
handed-0.001
ilt-0.001
Token mom
Token ID1995
Feature activation-3.00e-01

Pos logit contributions
ork+0.021
oph+0.021
ally+0.018
way+0.018
handed+0.018
Neg logit contributions
 Amen-0.020
 fires-0.015
stretched-0.015
 bears-0.013
 passenger-0.013
Token took
Token ID1718
Feature activation-6.67e-01

Pos logit contributions
 Amen+0.010
 fires+0.007
stretched+0.007
 paddle+0.007
 spoiler+0.006
Neg logit contributions
oph-0.009
ork-0.009
ally-0.008
way-0.008
handed-0.007
Token out
Token ID503
Feature activation-2.13e+00

Pos logit contributions
 Amen+0.012
 fires+0.009
 hope+0.008
 bears+0.008
 scar+0.007
Neg logit contributions
ork-0.029
oph-0.028
way-0.027
ally-0.025
 doorstep-0.025
Token a
Token ID257
Feature activation-3.28e-03

Pos logit contributions
 Amen+0.068
stretched+0.047
 fires+0.046
 spoiler+0.044
 paddle+0.044
Neg logit contributions
ork-0.067
oph-0.064
ally-0.055
way-0.055
handed-0.054
Token bottle
Token ID9294
Feature activation-5.52e-01

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 bears+0.000
 passenger+0.000
Neg logit contributions
ork-0.000
oph-0.000
way-0.000
ally-0.000
handed-0.000
Token of
Token ID286
Feature activation-4.19e-01

Pos logit contributions
 Amen+0.014
 fires+0.010
stretched+0.010
 bears+0.009
 smile+0.009
Neg logit contributions
ork-0.020
oph-0.019
handed-0.017
way-0.017
ally-0.017
Token.
Token ID13
Feature activation-4.46e-01

Pos logit contributions
ork+0.009
oph+0.009
way+0.008
handed+0.008
ally+0.008
Neg logit contributions
 Amen-0.009
stretched-0.006
 fires-0.006
 passenger-0.006
 whine-0.005
Token One
Token ID1881
Feature activation-8.05e-01

Pos logit contributions
 Amen+0.011
 fires+0.008
stretched+0.008
 bears+0.007
 scar+0.007
Neg logit contributions
ork-0.016
oph-0.016
way-0.014
ally-0.014
handed-0.014
Token day
Token ID1110
Feature activation-4.25e-02

Pos logit contributions
 Amen+0.027
 fires+0.021
stretched+0.021
 bears+0.020
 passenger+0.019
Neg logit contributions
ork-0.023
oph-0.022
way-0.019
ally-0.019
handed-0.018
Token M
Token ID337
Feature activation+1.06e+00

Pos logit contributions
 Amen+0.001
 fires+0.001
stretched+0.001
 bears+0.001
 smile+0.001
Neg logit contributions
ork-0.002
oph-0.002
handed-0.001
way-0.001
ally-0.001
Tokenimi
Token ID25236
Feature activation+1.31e+00

Pos logit contributions
ork+0.025
oph+0.022
handed+0.021
way+0.021
keeping+0.020
Neg logit contributions
 Amen-0.038
 bears-0.029
 fires-0.029
stretched-0.029
 sister-0.028
Token decided
Token ID3066
Feature activation+1.42e+00

Pos logit contributions
ork+0.046
oph+0.045
handed+0.040
way+0.040
ally+0.039
Neg logit contributions
 Amen-0.032
 fires-0.023
 bears-0.022
stretched-0.022
 hope-0.021
Token to
Token ID284
Feature activation+2.92e-01

Pos logit contributions
oph+0.046
ork+0.046
handed+0.040
ally+0.040
way+0.038
Neg logit contributions
 Amen-0.038
 fires-0.028
stretched-0.027
 yes-0.027
 sometimes-0.027
Token take
Token ID1011
Feature activation-1.88e-02

Pos logit contributions
ork+0.011
oph+0.011
way+0.010
ally+0.010
handed+0.010
Neg logit contributions
 Amen-0.007
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token a
Token ID257
Feature activation+6.60e-02

Pos logit contributions
 Amen+0.000
 fires+0.000
 bears+0.000
 scar+0.000
 hope+0.000
Neg logit contributions
oph-0.001
ork-0.001
way-0.001
ally-0.001
handed-0.001
Token walk
Token ID2513
Feature activation-1.37e+00

Pos logit contributions
ork+0.002
oph+0.002
way+0.002
ally+0.002
handed+0.002
Neg logit contributions
 Amen-0.002
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token in
Token ID287
Feature activation-4.61e-01

Pos logit contributions
 Amen+0.048
stretched+0.035
 fires+0.035
 spoiler+0.034
 bears+0.034
Neg logit contributions
ork-0.037
oph-0.034
way-0.032
handed-0.030
ally-0.030
Token and
Token ID290
Feature activation-6.15e-01

Pos logit contributions
 Amen+0.025
 fires+0.017
stretched+0.017
 bears+0.016
 smile+0.016
Neg logit contributions
ork-0.036
oph-0.034
way-0.031
handed-0.031
ally-0.030
Token said
Token ID531
Feature activation+1.59e+00

Pos logit contributions
 Amen+0.018
 fires+0.013
 bears+0.013
stretched+0.013
 scar+0.012
Neg logit contributions
ork-0.020
oph-0.019
way-0.017
handed-0.017
ally-0.016
Token she
Token ID673
Feature activation+1.68e-01

Pos logit contributions
ork+0.054
oph+0.052
way+0.045
ally+0.045
handed+0.043
Neg logit contributions
 Amen-0.045
 fires-0.034
stretched-0.032
 passenger-0.030
 bears-0.029
Token liked
Token ID8288
Feature activation-1.24e+00

Pos logit contributions
ork+0.005
oph+0.005
ally+0.005
way+0.004
handed+0.004
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.003
 paddle-0.003
Token to
Token ID284
Feature activation-5.74e-01

Pos logit contributions
 Amen+0.045
 fires+0.034
stretched+0.033
 passenger+0.032
 paddle+0.031
Neg logit contributions
ork-0.032
oph-0.032
ally-0.027
way-0.026
handed-0.025
Token pretend
Token ID16614
Feature activation+2.52e-02

Pos logit contributions
 Amen+0.017
 fires+0.013
stretched+0.012
 bears+0.012
 weaker+0.011
Neg logit contributions
ork-0.019
oph-0.018
ally-0.016
n-0.016
 doorstep-0.015
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ork+0.001
oph+0.001
way+0.001
ally+0.001
handed+0.001
Neg logit contributions
 Amen-0.001
 fires-0.001
stretched-0.001
 bears-0.001
 passenger-0.001
Token She
Token ID1375
Feature activation-1.40e+00

Pos logit contributions
 Amen+0.006
 fires+0.005
stretched+0.004
 bears+0.004
 paddle+0.004
Neg logit contributions
ork-0.005
oph-0.005
way-0.004
ally-0.004
handed-0.004
Token told
Token ID1297
Feature activation+8.25e-01

Pos logit contributions
 Amen+0.043
 fires+0.033
stretched+0.032
 bears+0.029
 passenger+0.028
Neg logit contributions
ork-0.043
oph-0.043
ally-0.037
way-0.037
handed-0.035
Token Max
Token ID5436
Feature activation+8.75e-01

Pos logit contributions
ork+0.025
oph+0.025
way+0.021
handed+0.021
ally+0.021
Neg logit contributions
 Amen-0.026
 fires-0.020
stretched-0.019
 bears-0.019
 scar-0.018
Token he
Token ID339
Feature activation+5.02e-01

Pos logit contributions
ork+0.024
oph+0.023
ally+0.019
way+0.019
handed+0.019
Neg logit contributions
 Amen-0.031
stretched-0.024
 fires-0.024
 passenger-0.022
 spoiler-0.022
Token inside
Token ID2641
Feature activation-6.23e-01

Pos logit contributions
 Amen+0.036
 fires+0.028
stretched+0.028
 bears+0.027
 spoiler+0.027
Neg logit contributions
ork-0.024
oph-0.021
way-0.019
ally-0.019
handed-0.019
Token the
Token ID262
Feature activation-5.18e-01

Pos logit contributions
 Amen+0.017
 fires+0.012
stretched+0.012
 bears+0.011
 passenger+0.011
Neg logit contributions
ork-0.021
oph-0.021
way-0.019
handed-0.018
ally-0.018
Token door
Token ID3420
Feature activation-1.16e+00

Pos logit contributions
 Amen+0.018
 fires+0.014
stretched+0.013
 bears+0.013
 passenger+0.012
Neg logit contributions
ork-0.014
oph-0.014
way-0.012
ally-0.012
handed-0.012
Token.
Token ID13
Feature activation+6.94e-03

Pos logit contributions
 Amen+0.035
 fires+0.025
stretched+0.023
 bears+0.023
 scar+0.022
Neg logit contributions
ork-0.038
oph-0.037
way-0.033
ally-0.032
handed-0.032
Token It
Token ID632
Feature activation+6.76e-01

Pos logit contributions
oph+0.000
ork+0.000
ally+0.000
handed+0.000
ige+0.000
Neg logit contributions
 Amen-0.000
 fires-0.000
stretched-0.000
 smile-0.000
 nod-0.000
Token was
Token ID373
Feature activation+6.47e-01

Pos logit contributions
ork+0.022
oph+0.022
handed+0.020
keeping+0.019
way+0.019
Neg logit contributions
 Amen-0.019
 fires-0.014
stretched-0.014
 bears-0.013
 smile-0.013
Token dark
Token ID3223
Feature activation+1.40e+00

Pos logit contributions
ork+0.023
oph+0.022
way+0.020
ally+0.019
handed+0.019
Neg logit contributions
 Amen-0.017
 fires-0.012
stretched-0.012
 bears-0.011
 passenger-0.010
Token and
Token ID290
Feature activation+4.64e-01

Pos logit contributions
ork+0.048
oph+0.047
way+0.042
ally+0.041
handed+0.041
Neg logit contributions
 Amen-0.038
 fires-0.027
stretched-0.027
 bears-0.025
 passenger-0.024
Token he
Token ID339
Feature activation+7.18e-01

Pos logit contributions
ork+0.016
oph+0.015
way+0.014
handed+0.014
ally+0.013
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.008
 bears-0.008
 passenger-0.008
Token couldn
Token ID3521
Feature activation-3.95e-01

Pos logit contributions
ork+0.023
oph+0.022
way+0.019
ally+0.019
handed+0.019
Neg logit contributions
 Amen-0.021
 fires-0.016
stretched-0.016
 bears-0.015
 passenger-0.014
Token't
Token ID470
Feature activation+1.10e+00

Pos logit contributions
 Amen+0.011
 fires+0.007
stretched+0.007
 sometimes+0.007
 exc+0.007
Neg logit contributions
oph-0.014
ork-0.012
ally-0.012
keeping-0.011
handed-0.011
Token.
Token ID13
Feature activation-2.00e-02

Pos logit contributions
 Amen+0.044
 fires+0.034
stretched+0.033
 paddle+0.033
 passenger+0.033
Neg logit contributions
ork-0.029
oph-0.028
way-0.022
handed-0.022
her-0.021
Token It
Token ID632
Feature activation+2.30e-01

Pos logit contributions
 Amen+0.000
stretched+0.000
 fires+0.000
 nods+0.000
 smile+0.000
Neg logit contributions
oph-0.001
ork-0.001
handed-0.001
way-0.001
ally-0.001
Token is
Token ID318
Feature activation+1.13e-01

Pos logit contributions
ork+0.006
oph+0.006
way+0.005
ally+0.005
her+0.005
Neg logit contributions
 Amen-0.008
stretched-0.006
 fires-0.006
 passenger-0.006
 paddle-0.005
Token delicious
Token ID12625
Feature activation+1.34e+00

Pos logit contributions
ork+0.004
oph+0.003
ally+0.003
way+0.003
handed+0.003
Neg logit contributions
 Amen-0.003
 fires-0.003
stretched-0.003
 passenger-0.002
 paddle-0.002
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
ork+0.049
oph+0.047
way+0.042
handed+0.042
ally+0.041
Neg logit contributions
 Amen-0.033
 fires-0.024
 bears-0.023
stretched-0.022
 smile-0.021
Token She
Token ID1375
Feature activation-1.27e+00

Pos logit contributions
 Amen+0.004
stretched+0.003
 nods+0.003
Does+0.003
 exc+0.003
Neg logit contributions
oph-0.007
ork-0.007
way-0.006
handed-0.006
 doorstep-0.006
Token says
Token ID1139
Feature activation+2.24e+00

Pos logit contributions
 Amen+0.039
stretched+0.030
 fires+0.029
 passenger+0.028
 sled+0.025
Neg logit contributions
oph-0.038
ork-0.037
her-0.030
ally-0.030
ige-0.030
Token thank
Token ID5875
Feature activation-7.30e-01

Pos logit contributions
ork+0.072
oph+0.068
ally+0.055
way+0.055
orman+0.052
Neg logit contributions
 Amen-0.068
 passenger-0.051
 fires-0.051
stretched-0.051
 paddle-0.047
Token you
Token ID345
Feature activation-7.96e-01

Pos logit contributions
 Amen+0.024
 fires+0.018
stretched+0.017
 bears+0.017
 smile+0.017
Neg logit contributions
ork-0.021
oph-0.021
way-0.018
handed-0.018
ally-0.017
Token to
Token ID284
Feature activation-7.80e-02

Pos logit contributions
 Amen+0.024
 fires+0.018
stretched+0.018
 bears+0.016
 passenger+0.016
Neg logit contributions
ork-0.025
oph-0.024
way-0.021
ally-0.021
handed-0.021
Token her
Token ID607
Feature activation-1.35e+00

Pos logit contributions
 Amen+0.002
 fires+0.002
stretched+0.002
 bears+0.002
 passenger+0.001
Neg logit contributions
ork-0.003
oph-0.002
ally-0.002
way-0.002
handed-0.002
Token and
Token ID290
Feature activation+3.70e-01

Pos logit contributions
 Amen+0.019
 fires+0.014
stretched+0.014
 bears+0.013
 smile+0.012
Neg logit contributions
ork-0.029
oph-0.028
ally-0.024
way-0.024
handed-0.024
Token faces
Token ID6698
Feature activation+1.71e-01

Pos logit contributions
ork+0.011
oph+0.011
way+0.010
handed+0.010
ally+0.010
Neg logit contributions
 Amen-0.011
 fires-0.008
stretched-0.008
 passenger-0.007
 bears-0.007
Token.
Token ID13
Feature activation+6.41e-01

Pos logit contributions
ork+0.005
oph+0.005
way+0.004
handed+0.004
ally+0.004
Neg logit contributions
 Amen-0.006
 fires-0.004
stretched-0.004
 bears-0.004
 passenger-0.004
Token They
Token ID1119
Feature activation-1.94e-02

Pos logit contributions
oph+0.024
ork+0.024
handed+0.020
 doorstep+0.020
keeping+0.020
Neg logit contributions
 Amen-0.015
 fires-0.010
stretched-0.010
 Sometimes-0.010
 bears-0.010
Token all
Token ID477
Feature activation+1.14e-01

Pos logit contributions
 Amen+0.001
 fires+0.000
stretched+0.000
 passenger+0.000
 spoiler+0.000
Neg logit contributions
oph-0.001
ork-0.001
ally-0.001
way-0.000
handed-0.000
Token laughed
Token ID13818
Feature activation-1.01e+00

Pos logit contributions
oph+0.003
ork+0.003
ally+0.003
way+0.003
handed+0.003
Neg logit contributions
 Amen-0.004
 fires-0.003
stretched-0.003
 bears-0.002
 passenger-0.002
Token and
Token ID290
Feature activation-1.80e-01

Pos logit contributions
 Amen+0.032
 fires+0.023
stretched+0.023
 passenger+0.022
 whine+0.021
Neg logit contributions
ork-0.030
oph-0.030
way-0.026
ally-0.026
handed-0.024
Token had
Token ID550
Feature activation+1.00e+00

Pos logit contributions
 Amen+0.005
 fires+0.003
stretched+0.003
 bears+0.003
 passenger+0.003
Neg logit contributions
ork-0.007
oph-0.006
way-0.006
ally-0.006
handed-0.006
Token fun
Token ID1257
Feature activation+1.16e+00

Pos logit contributions
ork+0.035
oph+0.034
way+0.030
handed+0.030
ally+0.030
Neg logit contributions
 Amen-0.027
 fires-0.020
stretched-0.019
 bears-0.018
 scar-0.018
Token playing
Token ID2712
Feature activation-2.03e-01

Pos logit contributions
ork+0.034
oph+0.032
way+0.030
handed+0.028
ally+0.028
Neg logit contributions
 Amen-0.038
stretched-0.027
 fires-0.027
 passenger-0.026
 scar-0.025
Token in
Token ID287
Feature activation+3.72e-02

Pos logit contributions
 Amen+0.005
 fires+0.004
 bears+0.003
stretched+0.003
 hope+0.003
Neg logit contributions
oph-0.007
ork-0.007
ally-0.006
way-0.006
handed-0.006
Token and
Token ID290
Feature activation-7.27e-01

Pos logit contributions
ork+0.026
oph+0.025
way+0.022
handed+0.022
ally+0.022
Neg logit contributions
 Amen-0.019
 fires-0.014
stretched-0.014
 bears-0.013
 smile-0.013
Token Jack
Token ID3619
Feature activation+1.84e-01

Pos logit contributions
 Amen+0.024
 fires+0.019
stretched+0.018
 bears+0.017
 scar+0.017
Neg logit contributions
ork-0.021
oph-0.020
way-0.017
ally-0.017
handed-0.017
Token were
Token ID547
Feature activation-1.59e-02

Pos logit contributions
oph+0.006
ork+0.006
ally+0.005
way+0.005
handed+0.005
Neg logit contributions
 Amen-0.005
 fires-0.004
stretched-0.004
 bears-0.003
 scar-0.003
Token very
Token ID845
Feature activation+8.66e-01

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 bears+0.000
 scar+0.000
Neg logit contributions
ork-0.001
oph-0.001
handed-0.000
way-0.000
ally-0.000
Token happy
Token ID3772
Feature activation-1.72e-01

Pos logit contributions
ork+0.028
oph+0.027
handed+0.025
way+0.025
ally+0.024
Neg logit contributions
 Amen-0.024
 fires-0.018
 bears-0.017
 scar-0.016
stretched-0.016
Token that
Token ID326
Feature activation-9.17e-01

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.003
 passenger+0.003
Neg logit contributions
ork-0.005
oph-0.005
way-0.005
ally-0.005
handed-0.005
Token they
Token ID484
Feature activation+8.64e-01

Pos logit contributions
 Amen+0.021
 fires+0.014
stretched+0.013
 bears+0.013
 smile+0.012
Neg logit contributions
ork-0.036
oph-0.035
handed-0.031
way-0.031
ally-0.031
Token had
Token ID550
Feature activation+1.52e+00

Pos logit contributions
ork+0.027
oph+0.027
way+0.023
ally+0.023
handed+0.023
Neg logit contributions
 Amen-0.026
 fires-0.020
stretched-0.019
 bears-0.018
 scar-0.017
Token cleaned
Token ID20750
Feature activation+6.26e-01

Pos logit contributions
ork+0.057
anger+0.053
oph+0.053
ess+0.048
way+0.047
Neg logit contributions
 hope-0.028
 smile-0.026
 Amen-0.026
 yes-0.025
 ne-0.024
Token up
Token ID510
Feature activation-1.94e-01

Pos logit contributions
ork+0.022
oph+0.022
ally+0.019
way+0.019
handed+0.019
Neg logit contributions
 Amen-0.015
 fires-0.013
 bears-0.011
 hope-0.011
stretched-0.010
Token the
Token ID262
Feature activation-2.49e-01

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 bears+0.003
 hope+0.003
Neg logit contributions
ork-0.007
oph-0.007
way-0.007
ally-0.007
handed-0.006
Token three
Token ID1115
Feature activation-6.64e-01

Pos logit contributions
ork+0.000
oph+0.000
way+0.000
ally+0.000
handed+0.000
Neg logit contributions
 Amen-0.000
 fires-0.000
stretched-0.000
 spoiler-0.000
 paddle-0.000
Token and
Token ID290
Feature activation-4.96e-01

Pos logit contributions
 Amen+0.021
 fires+0.014
stretched+0.014
 paddle+0.014
 spoiler+0.014
Neg logit contributions
ork-0.020
oph-0.020
ally-0.018
way-0.018
handed-0.017
Token she
Token ID673
Feature activation+2.52e-01

Pos logit contributions
 Amen+0.014
 fires+0.011
stretched+0.010
 paddle+0.010
 bears+0.010
Neg logit contributions
ork-0.016
oph-0.015
ally-0.014
way-0.013
handed-0.013
Token loved
Token ID6151
Feature activation-1.06e+00

Pos logit contributions
ork+0.009
oph+0.008
way+0.007
ally+0.007
handed+0.007
Neg logit contributions
 Amen-0.007
 fires-0.005
stretched-0.005
 bears-0.005
 scar-0.005
Token to
Token ID284
Feature activation-3.58e-01

Pos logit contributions
 Amen+0.042
stretched+0.033
 fires+0.032
 spoiler+0.032
 passenger+0.031
Neg logit contributions
ork-0.023
oph-0.021
keeping-0.018
way-0.018
ally-0.017
Token imagine
Token ID5967
Feature activation-9.86e-01

Pos logit contributions
 Amen+0.011
stretched+0.009
 fires+0.009
 weaker+0.008
 ang+0.008
Neg logit contributions
ork-0.010
oph-0.009
n-0.009
 doorstep-0.009
ally-0.008
Token.
Token ID13
Feature activation-3.56e-01

Pos logit contributions
 Amen+0.035
 paddle+0.025
stretched+0.025
 passenger+0.024
 spoiler+0.024
Neg logit contributions
ork-0.028
oph-0.024
way-0.022
ally-0.020
handed-0.020
Token One
Token ID1881
Feature activation-9.21e-01

Pos logit contributions
 Amen+0.010
stretched+0.007
 fires+0.006
 smile+0.006
 wonder+0.006
Neg logit contributions
ork-0.013
oph-0.012
handed-0.011
way-0.011
keeping-0.011
Token of
Token ID286
Feature activation-5.64e-01

Pos logit contributions
 Amen+0.030
 fires+0.023
stretched+0.022
 bears+0.021
 passenger+0.021
Neg logit contributions
ork-0.027
oph-0.026
way-0.023
ally-0.022
handed-0.022
Token her
Token ID607
Feature activation+1.73e+00

Pos logit contributions
 Amen+0.010
 fires+0.008
stretched+0.007
 bears+0.007
 smile+0.006
Neg logit contributions
ork-0.024
oph-0.022
way-0.021
handed-0.021
 doorstep-0.021
Token favorite
Token ID4004
Feature activation+1.24e+00

Pos logit contributions
ork+0.058
oph+0.057
way+0.050
ally+0.049
handed+0.049
Neg logit contributions
 Amen-0.049
 fires-0.036
stretched-0.035
 bears-0.032
 paddle-0.031
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
 Amen+0.031
 fires+0.022
 hope+0.021
 sometimes+0.020
 smile+0.020
Neg logit contributions
ork-0.058
oph-0.057
handed-0.049
ally-0.049
way-0.049
Token It
Token ID632
Feature activation+8.03e-01

Pos logit contributions
ork+0.010
oph+0.010
way+0.009
handed+0.008
ally+0.008
Neg logit contributions
 Amen-0.008
stretched-0.005
 fires-0.005
 bears-0.005
 smile-0.005
Token was
Token ID373
Feature activation+5.72e-01

Pos logit contributions
ork+0.023
oph+0.023
way+0.020
handed+0.019
ally+0.019
Neg logit contributions
 Amen-0.026
 fires-0.020
stretched-0.020
 bears-0.019
 smile-0.018
Token a
Token ID257
Feature activation+1.09e+00

Pos logit contributions
ork+0.019
oph+0.019
way+0.017
ally+0.017
handed+0.016
Neg logit contributions
 Amen-0.016
 fires-0.011
stretched-0.011
 bears-0.010
 paddle-0.010
Token pass
Token ID1208
Feature activation+3.22e-01

Pos logit contributions
ork+0.033
oph+0.031
way+0.027
ally+0.027
handed+0.026
Neg logit contributions
 Amen-0.034
 fires-0.026
stretched-0.026
 bears-0.024
 nods-0.023
Token to
Token ID284
Feature activation-6.40e-01

Pos logit contributions
ork+0.010
oph+0.010
way+0.009
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.010
 fires-0.007
stretched-0.007
 bears-0.007
 passenger-0.006
Token the
Token ID262
Feature activation-1.56e-02

Pos logit contributions
 Amen+0.016
 fires+0.012
 smile+0.011
 bears+0.011
stretched+0.011
Neg logit contributions
ork-0.023
oph-0.023
way-0.021
ally-0.020
handed-0.019
Token swimming
Token ID14899
Feature activation+2.60e-01

Pos logit contributions
 Amen+0.000
 fires+0.000
stretched+0.000
 passenger+0.000
 paddle+0.000
Neg logit contributions
oph-0.001
ork-0.001
ally-0.000
handed-0.000
way-0.000
Token pool
Token ID5933
Feature activation+1.03e+00

Pos logit contributions
oph+0.008
ork+0.008
ally+0.007
handed+0.007
way+0.007
Neg logit contributions
 Amen-0.008
 fires-0.006
stretched-0.005
 bears-0.005
 paddle-0.005
Token!
Token ID0
Feature activation-1.23e-01

Pos logit contributions
ork+0.033
oph+0.032
way+0.029
ally+0.028
handed+0.028
Neg logit contributions
 Amen-0.030
 fires-0.022
stretched-0.022
 bears-0.020
 scar-0.019
Token
Token ID198
Feature activation+5.11e-01

Pos logit contributions
 Amen+0.004
 fires+0.003
stretched+0.003
 bears+0.003
 smile+0.002
Neg logit contributions
ork-0.004
oph-0.004
way-0.003
handed-0.003
ally-0.003
Token so
Token ID523
Feature activation+7.68e-01

Pos logit contributions
 Amen+0.037
 fires+0.030
stretched+0.029
 scar+0.027
 bears+0.027
Neg logit contributions
oph-0.034
ork-0.033
handed-0.030
way-0.029
ally-0.029
Token happy
Token ID3772
Feature activation+5.21e-01

Pos logit contributions
ork+0.029
oph+0.029
way+0.026
ally+0.026
handed+0.026
Neg logit contributions
 Amen-0.018
 fires-0.013
stretched-0.011
 bears-0.011
 scar-0.010
Token and
Token ID290
Feature activation+6.10e-01

Pos logit contributions
ork+0.021
oph+0.020
handed+0.018
ally+0.017
way+0.017
Neg logit contributions
 Amen-0.010
 fires-0.007
 sometimes-0.007
 smile-0.007
 bears-0.007
Token hugged
Token ID41130
Feature activation+8.71e-01

Pos logit contributions
ork+0.024
oph+0.022
way+0.020
handed+0.020
ally+0.020
Neg logit contributions
 Amen-0.014
 smile-0.009
stretched-0.009
 fires-0.009
 exc-0.009
Token her
Token ID607
Feature activation-7.33e-01

Pos logit contributions
ork+0.029
oph+0.029
ally+0.025
way+0.025
handed+0.025
Neg logit contributions
 Amen-0.025
 fires-0.018
stretched-0.018
 bears-0.016
 passenger-0.016
Token daddy
Token ID35822
Feature activation-3.06e+00

Pos logit contributions
 Amen+0.023
stretched+0.021
 fires+0.020
Leave+0.018
ahs+0.018
Neg logit contributions
ork-0.019
oph-0.018
 doorstep-0.016
ally-0.015
ilda-0.014
Token tight
Token ID5381
Feature activation-1.02e+00

Pos logit contributions
 Amen+0.091
 fires+0.069
stretched+0.067
 bears+0.062
 passenger+0.060
Neg logit contributions
ork-0.097
oph-0.095
way-0.083
handed-0.082
ally-0.082
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 Amen+0.029
 fires+0.021
stretched+0.020
 bears+0.019
 passenger+0.018
Neg logit contributions
ork-0.034
oph-0.033
way-0.029
ally-0.029
handed-0.029
Token She
Token ID1375
Feature activation-1.32e+00

Pos logit contributions
ork+0.015
oph+0.014
way+0.013
handed+0.013
ally+0.012
Neg logit contributions
 Amen-0.012
 fires-0.008
stretched-0.008
 smile-0.007
 bears-0.007
Token learned
Token ID4499
Feature activation-1.77e-01

Pos logit contributions
 Amen+0.038
 fires+0.028
stretched+0.027
 bears+0.026
 smile+0.025
Neg logit contributions
ork-0.043
oph-0.042
way-0.037
handed-0.037
ally-0.036
Token that
Token ID326
Feature activation-6.67e-01

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.004
 scar+0.004
Neg logit contributions
ork-0.006
oph-0.006
way-0.005
ally-0.005
handed-0.005
Token excited
Token ID6568
Feature activation+1.37e+00

Pos logit contributions
ork+0.044
oph+0.044
handed+0.040
way+0.039
ally+0.039
Neg logit contributions
 Amen-0.030
 fires-0.022
 bears-0.020
stretched-0.020
 scar-0.019
Token,
Token ID11
Feature activation+8.56e-01

Pos logit contributions
ork+0.056
oph+0.051
handed+0.049
keeping+0.046
 doorstep+0.046
Neg logit contributions
 Amen-0.022
 sometimes-0.019
 smile-0.018
stretched-0.017
 bears-0.016
Token she
Token ID673
Feature activation+1.09e+00

Pos logit contributions
ork+0.029
oph+0.028
way+0.025
ally+0.024
handed+0.024
Neg logit contributions
 Amen-0.024
 fires-0.018
stretched-0.017
 bears-0.016
 passenger-0.015
Token hugged
Token ID41130
Feature activation+8.45e-01

Pos logit contributions
ork+0.035
oph+0.034
way+0.030
ally+0.030
handed+0.029
Neg logit contributions
 Amen-0.032
 fires-0.024
stretched-0.023
 bears-0.022
 passenger-0.021
Token the
Token ID262
Feature activation-5.07e-01

Pos logit contributions
ork+0.030
oph+0.029
handed+0.026
way+0.026
ally+0.026
Neg logit contributions
 Amen-0.022
 fires-0.016
stretched-0.015
 bears-0.014
 hope-0.014
Token fairy
Token ID25607
Feature activation-3.07e+00

Pos logit contributions
 Amen+0.014
 fires+0.010
stretched+0.010
 bears+0.009
 paddle+0.009
Neg logit contributions
ork-0.017
oph-0.017
way-0.015
ally-0.015
handed-0.015
Token and
Token ID290
Feature activation-5.61e-01

Pos logit contributions
 Amen+0.093
 fires+0.071
stretched+0.069
Does+0.062
 bears+0.062
Neg logit contributions
ork-0.095
oph-0.092
way-0.080
ally-0.080
handed-0.079
Token thanked
Token ID26280
Feature activation-3.52e-01

Pos logit contributions
 Amen+0.017
 fires+0.012
stretched+0.012
 bears+0.011
 passenger+0.011
Neg logit contributions
oph-0.018
ork-0.018
ally-0.015
way-0.015
handed-0.015
Token her
Token ID607
Feature activation-1.18e+00

Pos logit contributions
 Amen+0.009
 fires+0.007
stretched+0.006
 bears+0.006
 scar+0.006
Neg logit contributions
ork-0.012
oph-0.012
way-0.011
handed-0.011
ally-0.011
Token!
Token ID0
Feature activation-2.66e-01

Pos logit contributions
 Amen+0.043
stretched+0.033
 spoiler+0.033
 fires+0.033
 whine+0.032
Neg logit contributions
ork-0.029
oph-0.027
 doorstep-0.023
ally-0.023
way-0.023
Token
Token ID220
Feature activation-1.49e+00

Pos logit contributions
 Amen+0.008
stretched+0.006
 fires+0.006
 bears+0.006
 passenger+0.006
Neg logit contributions
ork-0.008
oph-0.008
way-0.007
handed-0.007
ally-0.007
Token hugged
Token ID41130
Feature activation+2.18e-01

Pos logit contributions
 Amen+0.016
 fires+0.012
stretched+0.011
 bears+0.010
 passenger+0.010
Neg logit contributions
ork-0.017
oph-0.017
ally-0.014
way-0.014
handed-0.014
Token Spot
Token ID15899
Feature activation-9.78e-01

Pos logit contributions
ork+0.007
oph+0.006
ally+0.006
way+0.005
handed+0.005
Neg logit contributions
 Amen-0.007
stretched-0.005
 fires-0.005
 passenger-0.005
 paddle-0.004
Token and
Token ID290
Feature activation-1.10e+00

Pos logit contributions
 Amen+0.034
stretched+0.027
 fires+0.025
 spoiler+0.024
Does+0.024
Neg logit contributions
ork-0.026
oph-0.024
way-0.021
ally-0.021
handed-0.021
Token thanked
Token ID26280
Feature activation-9.60e-01

Pos logit contributions
 Amen+0.033
 fires+0.024
stretched+0.024
 bears+0.022
 passenger+0.021
Neg logit contributions
ork-0.035
oph-0.034
way-0.030
ally-0.030
handed-0.030
Token the
Token ID262
Feature activation-1.65e+00

Pos logit contributions
 Amen+0.028
stretched+0.022
 fires+0.021
 passenger+0.020
 spoiler+0.019
Neg logit contributions
ork-0.030
oph-0.029
ally-0.025
handed-0.025
way-0.024
Token man
Token ID582
Feature activation-3.80e+00

Pos logit contributions
 Amen+0.054
stretched+0.042
 fires+0.041
 bears+0.038
 scar+0.036
Neg logit contributions
ork-0.048
oph-0.044
handed-0.040
way-0.039
ally-0.038
Token.
Token ID13
Feature activation-7.01e-02

Pos logit contributions
 Amen+0.135
stretched+0.108
 fires+0.101
 spoiler+0.101
Does+0.100
Neg logit contributions
ork-0.097
oph-0.086
handed-0.080
way-0.079
ess-0.075
Token They
Token ID1119
Feature activation-1.05e+00

Pos logit contributions
 Amen+0.002
 fires+0.002
stretched+0.002
 bears+0.001
 argue+0.001
Neg logit contributions
ork-0.002
oph-0.002
ally-0.002
way-0.002
handed-0.002
Token went
Token ID1816
Feature activation+3.52e-01

Pos logit contributions
 Amen+0.033
 fires+0.025
stretched+0.024
 bears+0.021
 passenger+0.021
Neg logit contributions
oph-0.033
ork-0.032
ally-0.028
handed-0.027
way-0.027
Token back
Token ID736
Feature activation+1.44e+00

Pos logit contributions
ork+0.010
oph+0.009
way+0.008
ally+0.008
handed+0.008
Neg logit contributions
 Amen-0.012
 fires-0.010
stretched-0.009
 bears-0.009
 passenger-0.009
Token to
Token ID284
Feature activation-5.86e-01

Pos logit contributions
oph+0.054
ork+0.049
ally+0.045
liv+0.043
way+0.043
Neg logit contributions
 Amen-0.035
 fires-0.029
 hope-0.027
 bears-0.026
 sled-0.025
Token them
Token ID606
Feature activation-4.64e-01

Pos logit contributions
ork+0.022
oph+0.021
way+0.021
handed+0.020
keeping+0.020
Neg logit contributions
 Amen-0.014
 bears-0.011
 fires-0.010
 hope-0.010
 g-0.010
Token ride
Token ID6594
Feature activation-1.89e-01

Pos logit contributions
 Amen+0.012
stretched+0.008
 fires+0.008
 bears+0.007
 spoiler+0.007
Neg logit contributions
ork-0.017
oph-0.016
way-0.015
handed-0.015
ally-0.015
Token on
Token ID319
Feature activation+6.45e-03

Pos logit contributions
 Amen+0.005
 fires+0.004
stretched+0.004
 bears+0.004
 passenger+0.004
Neg logit contributions
ork-0.006
oph-0.006
way-0.005
ally-0.005
handed-0.005
Token her
Token ID607
Feature activation-5.93e-01

Pos logit contributions
ork+0.000
oph+0.000
way+0.000
ally+0.000
handed+0.000
Neg logit contributions
 Amen-0.000
 fires-0.000
stretched-0.000
 bears-0.000
 scar-0.000
Token back
Token ID736
Feature activation+3.88e-01

Pos logit contributions
 Amen+0.018
 fires+0.013
stretched+0.013
 bears+0.012
 passenger+0.011
Neg logit contributions
ork-0.019
oph-0.018
way-0.016
handed-0.016
ally-0.016
Token sometimes
Token ID3360
Feature activation-3.25e+00

Pos logit contributions
ork+0.012
oph+0.012
way+0.010
handed+0.010
ally+0.010
Neg logit contributions
 Amen-0.012
 fires-0.009
stretched-0.009
 bears-0.008
 scar-0.008
Token.
Token ID13
Feature activation+2.19e-01

Pos logit contributions
 Amen+0.094
 fires+0.069
stretched+0.067
 bears+0.062
 passenger+0.060
Neg logit contributions
ork-0.108
oph-0.105
way-0.092
ally-0.091
handed-0.091
Token
Token ID198
Feature activation+4.22e-01

Pos logit contributions
ork+0.007
oph+0.006
way+0.006
handed+0.006
ally+0.006
Neg logit contributions
 Amen-0.007
 fires-0.005
stretched-0.005
 bears-0.005
 smile-0.004
Token
Token ID198
Feature activation-7.31e-02

Pos logit contributions
oph+0.013
ork+0.013
keeping+0.012
handed+0.012
 doorstep+0.012
Neg logit contributions
 Amen-0.012
stretched-0.009
 fires-0.008
 exc-0.008
 sled-0.008
TokenOne
Token ID3198
Feature activation-1.02e+00

Pos logit contributions
 Amen+0.002
 fires+0.002
 bears+0.001
stretched+0.001
 smile+0.001
Neg logit contributions
ork-0.002
oph-0.002
way-0.002
ally-0.002
handed-0.002
Token day
Token ID1110
Feature activation-1.97e-01

Pos logit contributions
 Amen+0.037
stretched+0.029
 fires+0.029
 spoiler+0.028
 bears+0.027
Neg logit contributions
ork-0.025
oph-0.024
way-0.021
ally-0.021
handed-0.019
Token?
Token ID30
Feature activation-9.34e-01

Pos logit contributions
 Amen+0.064
stretched+0.046
 fires+0.045
 passenger+0.041
 bears+0.041
Neg logit contributions
ork-0.086
oph-0.083
way-0.074
ally-0.073
handed-0.071
Token How
Token ID1374
Feature activation-3.47e-01

Pos logit contributions
 Amen+0.030
stretched+0.026
 fires+0.025
 scar+0.024
 smile+0.023
Neg logit contributions
ork-0.024
oph-0.022
way-0.019
handed-0.018
anger-0.018
Token do
Token ID466
Feature activation-2.69e-01

Pos logit contributions
 Amen+0.010
 fires+0.008
stretched+0.007
 bears+0.007
 smile+0.007
Neg logit contributions
ork-0.011
oph-0.011
handed-0.009
way-0.009
ally-0.009
Token they
Token ID484
Feature activation-1.34e+00

Pos logit contributions
 Amen+0.010
 fires+0.008
stretched+0.007
 bears+0.007
 passenger+0.007
Neg logit contributions
ork-0.007
oph-0.007
way-0.006
ally-0.006
handed-0.006
Token do
Token ID466
Feature activation-1.11e+00

Pos logit contributions
 Amen+0.034
stretched+0.023
 fires+0.023
 bears+0.021
 passenger+0.019
Neg logit contributions
ork-0.049
oph-0.047
way-0.043
handed-0.042
ally-0.042
Token that
Token ID326
Feature activation-3.06e+00

Pos logit contributions
 Amen+0.037
stretched+0.029
 fires+0.028
 bears+0.027
 passenger+0.026
Neg logit contributions
ork-0.032
oph-0.029
way-0.026
handed-0.025
ally-0.024
Token?"
Token ID1701
Feature activation+1.10e+00

Pos logit contributions
 Amen+0.080
stretched+0.061
 fires+0.057
 bears+0.052
 passenger+0.051
Neg logit contributions
ork-0.105
oph-0.101
way-0.093
ally-0.088
handed-0.087
Token Ben
Token ID3932
Feature activation-1.32e+00

Pos logit contributions
ork+0.029
oph+0.029
way+0.024
handed+0.024
ally+0.024
Neg logit contributions
 Amen-0.038
 fires-0.030
stretched-0.030
 bears-0.027
 passenger-0.027
Token asked
Token ID1965
Feature activation+6.50e-01

Pos logit contributions
 Amen+0.036
 fires+0.024
stretched+0.024
 bears+0.023
 smile+0.022
Neg logit contributions
ork-0.048
oph-0.045
way-0.041
handed-0.041
ally-0.040
Token.
Token ID13
Feature activation-8.57e-01

Pos logit contributions
ork+0.021
oph+0.020
way+0.018
ally+0.017
handed+0.017
Neg logit contributions
 Amen-0.020
 fires-0.015
stretched-0.014
 bears-0.013
 scar-0.013
Token
Token ID198
Feature activation-5.01e-01

Pos logit contributions
 Amen+0.031
 fires+0.025
stretched+0.025
 bears+0.023
 scar+0.023
Neg logit contributions
ork-0.022
oph-0.020
way-0.017
handed-0.017
ally-0.017