TOP ACTIVATIONS
MAX = 3.066

time there was a little av ac ado . It was
, there was a loud av ac ado . It was
" I will buy more av oc ados tomorrow . You
Maybe they could grow more av oc ados and share them
still couldn 't find any av oc ados . Finally ,
a poor m itten . The m itten was all alone
was a m itten . The m itten was red and
away . She learned that av oc ados are good for
shy z ig zag . The z ig zag was always
was a modern band . The band made really cool music
And don 't let go of Velvet . She might get
. Did you know that av oc ados are very healthy
right !" He picked up the tw ig and started to
. They forget about the av oc ados . They just
and try to grab the av oc ados . But the
the store to get more av oc ados . Gary looked
the tree if they were av oc ados , and they
girl who didn 't like av oc ados . She always
there was a band . The band was unusual . The
but there were no other av oc ados .

MIN ACTIVATIONS
MIN = -2.733

cows , pigs , chickens and sheep . They liked to
like cows , pigs , and chickens . But their favorite
like monkeys , birds , and elephants . They liked to
like cows , pigs , and chickens . They also saw
tours with her family . One day , they went on
like lions , monkeys , and birds . But Tim wanted
like lions , monkeys , and birds . But Ben and
that day on , Fl uffy learned that sometimes it 's
cows , pigs , chickens and horses . They love to
cows , pigs , chickens and goats . One
! This is none of your business !" He
like bugs , birds , and flowers . They were having
The files had colors like red , blue , and green
like monkeys , lions , and elephants . They liked to
like lions , monkeys , and birds . But Ben and
monkeys , ze br as and gir aff es . But
dreaming about mice or birds or milk . Suddenly
had colors like red , blue , and green . Tim
the animals . He could already hear the lions roaring and
, like birds , dogs and squirrel s . One day

INTERVAL 1.617 - 3.066
CONTAINS 0.060%

on while her mom my finished shopping . In the end
the snow . They made a big snow man with a
in started to carry the tw ig , it was too
ara loved her velvet dress . It was red and soft
wonderful taste of the sweet apples and juicy cher ries .

INTERVAL 0.167 - 1.617
CONTAINS 37.031%

expected , Mac got stuck inside and started me owing to
raft was gone , but he was careful next time he
finish the quiz . They do not look at each other
The beetle thought to itself , " I wonder if
the soft flour was also important too . She was so

INTERVAL -1.283 - 0.167
CONTAINS 62.159%

Don 't worry , Tim my ! We will find your
Her dad smiled . " We are repairing the
cry . Her mom heard her and ran outside to help
was that people should be careful of things that are special
something new on the black board . So the bald man

INTERVAL -2.733 - -1.283
CONTAINS 0.750%

the forest , but he couldn 't climb like they did
and soft . One day , a man comes
strange hurt mark . <|endoftext|> Danny was walking in the park
, waving to each other every day . Scare crow was
. She lived in a cold place with lots of snow
Token time
Token ID640
Feature activation-2.37e-01

Pos logit contributions
Prin+0.000
Once+0.000
+0.000
By+0.000
spe+0.000
Neg logit contributions
ses-0.001
oa-0.001
ittens-0.001
opsy-0.001
burn-0.001
Token there
Token ID612
Feature activation+2.23e-01

Pos logit contributions
ses+0.008
opsy+0.008
ittens+0.008
oa+0.008
uffy+0.008
Neg logit contributions
Prin-0.008
spe-0.008
By-0.007
RO-0.007
 cheered-0.007
Token was
Token ID373
Feature activation+4.88e-01

Pos logit contributions
Prin+0.006
spe+0.006
By+0.005
+0.005
Once+0.005
Neg logit contributions
ses-0.010
ittens-0.009
opsy-0.009
oa-0.009
burn-0.009
Token a
Token ID257
Feature activation+1.31e-01

Pos logit contributions
Prin+0.017
By+0.016
Once+0.015
+0.015
spe+0.015
Neg logit contributions
ses-0.018
oa-0.017
ittens-0.016
opsy-0.016
burn-0.016
Token little
Token ID1310
Feature activation+4.05e-01

Pos logit contributions
Prin+0.004
By+0.004
Once+0.004
+0.004
spe+0.003
Neg logit contributions
ses-0.005
oa-0.005
ittens-0.005
burn-0.005
sed-0.005
Token av
Token ID1196
Feature activation+3.07e+00

Pos logit contributions
Prin+0.010
+0.009
 cheered+0.009
spe+0.008
By+0.008
Neg logit contributions
ses-0.018
oa-0.017
ittens-0.017
sed-0.017
ats-0.016
Tokenac
Token ID330
Feature activation+1.20e+00

Pos logit contributions
Prin+0.104
spe+0.096
By+0.092
CR+0.090
 cheered+0.089
Neg logit contributions
ses-0.113
opsy-0.106
ittens-0.105
oa-0.104
burn-0.101
Tokenado
Token ID4533
Feature activation-5.49e-01

Pos logit contributions
Prin+0.049
spe+0.046
By+0.045
 cheered+0.044
+0.044
Neg logit contributions
ses-0.035
opsy-0.033
ittens-0.033
oa-0.032
burn-0.031
Token.
Token ID13
Feature activation+6.05e-01

Pos logit contributions
ses+0.025
oa+0.021
burn+0.021
sed+0.021
opsy+0.020
Neg logit contributions
Prin-0.016
spe-0.015
Once-0.014
-0.014
By-0.013
Token It
Token ID632
Feature activation-8.60e-02

Pos logit contributions
Prin+0.018
spe+0.016
By+0.015
CR+0.015
 cheered+0.015
Neg logit contributions
ses-0.026
opsy-0.023
oa-0.023
ittens-0.023
burn-0.022
Token was
Token ID373
Feature activation+3.40e-02

Pos logit contributions
ses+0.003
opsy+0.003
oa+0.003
ittens+0.003
uffy+0.003
Neg logit contributions
Prin-0.003
spe-0.003
By-0.003
CR-0.002
Happy-0.002
Token,
Token ID11
Feature activation+5.85e-01

Pos logit contributions
ses+0.009
ittens+0.009
opsy+0.009
uffy+0.008
oa+0.008
Neg logit contributions
Prin-0.010
spe-0.010
By-0.009
RO-0.009
 cheered-0.009
Token there
Token ID612
Feature activation+5.41e-02

Pos logit contributions
Prin+0.019
spe+0.018
By+0.016
 rect+0.016
RO+0.016
Neg logit contributions
ses-0.023
opsy-0.021
uffy-0.021
ittens-0.020
sed-0.020
Token was
Token ID373
Feature activation+5.49e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.001
CR+0.001
RO+0.001
Neg logit contributions
ses-0.002
opsy-0.002
oa-0.002
ittens-0.002
burn-0.002
Token a
Token ID257
Feature activation+3.04e-01

Pos logit contributions
Prin+0.021
spe+0.019
By+0.019
Once+0.018
+0.018
Neg logit contributions
ses-0.018
opsy-0.017
ittens-0.016
oa-0.016
burn-0.016
Token loud
Token ID7812
Feature activation+4.38e-01

Pos logit contributions
Prin+0.010
By+0.009
Once+0.009
spe+0.009
+0.009
Neg logit contributions
ses-0.012
oa-0.011
ittens-0.011
burn-0.010
opsy-0.010
Token av
Token ID1196
Feature activation+3.05e+00

Pos logit contributions
Prin+0.015
 cheered+0.014
By+0.013
spe+0.013
RO+0.013
Neg logit contributions
ses-0.015
opsy-0.015
ittens-0.014
oa-0.014
burn-0.014
Tokenac
Token ID330
Feature activation+1.13e+00

Pos logit contributions
Prin+0.113
spe+0.108
CR+0.102
By+0.101
RO+0.101
Neg logit contributions
ses-0.100
ittens-0.096
opsy-0.095
oa-0.092
burn-0.091
Tokenado
Token ID4533
Feature activation-5.13e-01

Pos logit contributions
Prin+0.041
spe+0.038
By+0.037
+0.037
 cheered+0.037
Neg logit contributions
ses-0.038
ittens-0.037
opsy-0.037
oa-0.036
burn-0.035
Token.
Token ID13
Feature activation+3.19e-01

Pos logit contributions
ses+0.020
oa+0.018
opsy+0.018
burn+0.018
ittens+0.018
Neg logit contributions
Prin-0.017
spe-0.016
By-0.015
Once-0.015
-0.015
Token It
Token ID632
Feature activation+2.11e-01

Pos logit contributions
Prin+0.012
spe+0.011
By+0.010
 cheered+0.010
Uh+0.009
Neg logit contributions
ses-0.011
oa-0.009
ittens-0.009
opsy-0.009
sed-0.009
Token was
Token ID373
Feature activation+2.31e-01

Pos logit contributions
Prin+0.008
spe+0.007
By+0.007
 triumph+0.007
Happy+0.007
Neg logit contributions
ses-0.007
oa-0.006
opsy-0.006
uffy-0.006
sed-0.006
Token "
Token ID366
Feature activation-3.55e-02

Pos logit contributions
ses+0.015
opsy+0.014
ittens+0.014
burn+0.014
oa+0.014
Neg logit contributions
Prin-0.011
spe-0.010
By-0.010
-0.010
Once-0.010
TokenI
Token ID40
Feature activation+7.77e-02

Pos logit contributions
oa+0.001
opsy+0.001
ittens+0.001
burn+0.001
itten+0.001
Neg logit contributions
spe-0.001
Prin-0.001
 rect-0.001
 achieved-0.001
 erupted-0.001
Token will
Token ID481
Feature activation-2.30e-01

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
+0.003
 cheered+0.003
Neg logit contributions
ses-0.003
ittens-0.002
opsy-0.002
oa-0.002
burn-0.002
Token buy
Token ID2822
Feature activation+2.63e-01

Pos logit contributions
ses+0.010
opsy+0.009
uffy+0.009
ittens+0.009
erry+0.009
Neg logit contributions
-0.007
Once-0.007
 cheered-0.006
By-0.006
Prin-0.006
Token more
Token ID517
Feature activation+1.06e+00

Pos logit contributions
Prin+0.007
+0.006
spe+0.006
By+0.006
 cheered+0.006
Neg logit contributions
ses-0.012
opsy-0.011
ittens-0.011
burn-0.011
oa-0.011
Token av
Token ID1196
Feature activation+3.00e+00

Pos logit contributions
Prin+0.045
spe+0.042
By+0.041
CR+0.040
Once+0.040
Neg logit contributions
ses-0.030
ittens-0.027
opsy-0.027
oa-0.027
burn-0.026
Tokenoc
Token ID420
Feature activation-2.08e-01

Pos logit contributions
Prin+0.119
spe+0.113
RO+0.111
By+0.109
 behold+0.107
Neg logit contributions
ittens-0.087
ses-0.081
opsy-0.081
oa-0.081
erry-0.080
Tokenados
Token ID22484
Feature activation+1.99e+00

Pos logit contributions
ses+0.006
opsy+0.005
ittens+0.005
oa+0.005
burn+0.005
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
CR-0.008
-0.008
Token tomorrow
Token ID9439
Feature activation-3.28e-01

Pos logit contributions
Prin+0.073
spe+0.067
By+0.065
RO+0.063
CR+0.063
Neg logit contributions
ses-0.068
oa-0.063
ittens-0.063
opsy-0.063
burn-0.060
Token.
Token ID13
Feature activation-1.50e-01

Pos logit contributions
ses+0.014
opsy+0.013
ittens+0.013
burn+0.012
oa+0.012
Neg logit contributions
-0.009
Prin-0.009
spe-0.009
 achieved-0.008
 cheered-0.008
Token You
Token ID921
Feature activation+3.40e-01

Pos logit contributions
ses+0.006
oa+0.005
opsy+0.005
ittens+0.005
burn+0.005
Neg logit contributions
Prin-0.005
spe-0.005
By-0.004
 cheered-0.004
CR-0.004
Token Maybe
Token ID6674
Feature activation+1.30e-01

Pos logit contributions
Prin+0.038
spe+0.035
By+0.034
Once+0.033
+0.033
Neg logit contributions
ses-0.042
opsy-0.039
ittens-0.038
oa-0.038
burn-0.037
Token they
Token ID484
Feature activation+1.61e-01

Pos logit contributions
Prin+0.005
spe+0.004
RO+0.004
 cheered+0.004
By+0.004
Neg logit contributions
ses-0.004
opsy-0.004
oa-0.004
ittens-0.004
 Cow-0.004
Token could
Token ID714
Feature activation-8.55e-01

Pos logit contributions
Prin+0.005
spe+0.004
By+0.004
+0.004
 cheered+0.004
Neg logit contributions
ses-0.007
ittens-0.007
oa-0.007
opsy-0.006
burn-0.006
Token grow
Token ID1663
Feature activation-4.39e-02

Pos logit contributions
ses+0.031
oa+0.029
ittens+0.029
uffy+0.027
opsy+0.027
Neg logit contributions
Prin-0.030
-0.028
Once-0.028
 behold-0.027
By-0.027
Token more
Token ID517
Feature activation+4.81e-01

Pos logit contributions
ses+0.002
opsy+0.002
ittens+0.002
oa+0.002
burn+0.002
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
Once-0.001
RO-0.001
Token av
Token ID1196
Feature activation+2.90e+00

Pos logit contributions
spe+0.023
Prin+0.023
By+0.022
Uh+0.022
RO+0.022
Neg logit contributions
opsy-0.010
 herb-0.009
erry-0.009
ittens-0.008
 potatoes-0.008
Tokenoc
Token ID420
Feature activation+3.83e-01

Pos logit contributions
Prin+0.110
spe+0.108
RO+0.102
By+0.099
CR+0.098
Neg logit contributions
ses-0.088
ittens-0.087
opsy-0.086
oa-0.083
burn-0.082
Tokenados
Token ID22484
Feature activation+1.70e+00

Pos logit contributions
Prin+0.015
spe+0.014
By+0.014
CR+0.014
 rect+0.013
Neg logit contributions
ses-0.012
opsy-0.011
ittens-0.011
burn-0.011
uffy-0.010
Token and
Token ID290
Feature activation-6.16e-01

Pos logit contributions
Prin+0.059
spe+0.057
RO+0.054
By+0.054
CR+0.053
Neg logit contributions
ses-0.057
opsy-0.055
ittens-0.054
oa-0.054
burn-0.053
Token share
Token ID2648
Feature activation-3.09e-01

Pos logit contributions
ses+0.017
opsy+0.015
oa+0.014
sed+0.014
 cough+0.014
Neg logit contributions
Prin-0.026
spe-0.024
By-0.024
CR-0.023
RO-0.023
Token them
Token ID606
Feature activation+8.68e-01

Pos logit contributions
ses+0.010
oa+0.010
opsy+0.010
ittens+0.010
burn+0.010
Neg logit contributions
Prin-0.011
spe-0.010
By-0.010
Uh-0.010
RO-0.010
Token still
Token ID991
Feature activation-3.07e-01

Pos logit contributions
ses+0.006
opsy+0.006
oa+0.006
ittens+0.005
uffy+0.005
Neg logit contributions
Prin-0.006
spe-0.006
Happy-0.005
RO-0.005
By-0.005
Token couldn
Token ID3521
Feature activation-8.36e-01

Pos logit contributions
ses+0.012
opsy+0.012
ittens+0.012
oa+0.012
burn+0.011
Neg logit contributions
Prin-0.009
spe-0.009
By-0.008
-0.008
 cheered-0.008
Token't
Token ID470
Feature activation-7.31e-01

Pos logit contributions
ses+0.031
opsy+0.029
ittens+0.029
oa+0.029
burn+0.028
Neg logit contributions
Prin-0.028
spe-0.026
By-0.025
-0.024
Once-0.024
Token find
Token ID1064
Feature activation-2.14e-01

Pos logit contributions
ses+0.026
oa+0.024
ittens+0.024
burn+0.023
uffy+0.023
Neg logit contributions
Prin-0.027
-0.025
By-0.025
Once-0.025
 behold-0.024
Token any
Token ID597
Feature activation+3.07e-01

Pos logit contributions
ses+0.011
ittens+0.011
oa+0.010
opsy+0.010
sed+0.010
Neg logit contributions
Prin-0.004
-0.004
 behold-0.004
Once-0.003
CR-0.003
Token av
Token ID1196
Feature activation+2.82e+00

Pos logit contributions
Prin+0.010
spe+0.009
By+0.009
+0.009
 cheered+0.009
Neg logit contributions
ses-0.012
opsy-0.011
oa-0.011
ittens-0.011
burn-0.010
Tokenoc
Token ID420
Feature activation-8.08e-01

Pos logit contributions
Prin+0.111
spe+0.106
By+0.103
RO+0.102
 cheered+0.101
Neg logit contributions
ittens-0.080
ses-0.079
opsy-0.077
erry-0.076
oa-0.075
Tokenados
Token ID22484
Feature activation+1.73e+00

Pos logit contributions
ses+0.023
opsy+0.021
ittens+0.021
oa+0.020
burn+0.020
Neg logit contributions
Prin-0.034
spe-0.032
By-0.031
CR-0.030
-0.030
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
Prin+0.059
spe+0.054
By+0.052
CR+0.050
Once+0.050
Neg logit contributions
ses-0.064
opsy-0.059
ittens-0.059
oa-0.059
burn-0.057
Token Finally
Token ID9461
Feature activation-7.09e-02

Pos logit contributions
ses+0.004
opsy+0.004
ittens+0.004
oa+0.004
uffy+0.004
Neg logit contributions
Prin-0.003
spe-0.003
 rect-0.003
By-0.003
RO-0.003
Token,
Token ID11
Feature activation-2.53e-01

Pos logit contributions
ses+0.002
ittens+0.002
opsy+0.002
oa+0.002
uffy+0.002
Neg logit contributions
Prin-0.003
spe-0.002
By-0.002
RO-0.002
 cheered-0.002
Token a
Token ID257
Feature activation+2.09e-01

Pos logit contributions
Prin+0.021
By+0.019
+0.019
Once+0.019
spe+0.019
Neg logit contributions
ses-0.021
oa-0.019
opsy-0.019
ittens-0.019
burn-0.018
Token poor
Token ID3595
Feature activation+4.78e-01

Pos logit contributions
Prin+0.007
By+0.006
Once+0.006
spe+0.006
+0.006
Neg logit contributions
ses-0.008
oa-0.008
ittens-0.008
burn-0.007
sed-0.007
Token m
Token ID285
Feature activation+4.30e-01

Pos logit contributions
Prin+0.014
spe+0.012
Once+0.011
 cheered+0.011
By+0.010
Neg logit contributions
ses-0.020
oa-0.019
ittens-0.018
burn-0.018
ats-0.018
Tokenitten
Token ID2621
Feature activation-7.40e-01

Pos logit contributions
spe+0.020
Once+0.019
+0.019
By+0.019
Prin+0.019
Neg logit contributions
ses-0.011
sed-0.008
burn-0.007
oa-0.007
 wool-0.006
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
ses+0.033
oa+0.031
opsy+0.030
ittens+0.030
burn+0.028
Neg logit contributions
Prin-0.019
-0.018
spe-0.017
Once-0.017
By-0.017
Token The
Token ID383
Feature activation+2.76e+00

Pos logit contributions
Prin+0.036
spe+0.033
By+0.032
 cheered+0.031
CR+0.030
Neg logit contributions
ses-0.046
oa-0.042
ittens-0.041
opsy-0.041
burn-0.039
Token m
Token ID285
Feature activation+1.00e+00

Pos logit contributions
Once+0.106
By+0.103
+0.098
Uh+0.096
Prin+0.096
Neg logit contributions
ses-0.092
oa-0.077
sed-0.075
uffy-0.075
gy-0.075
Tokenitten
Token ID2621
Feature activation-8.23e-01

Pos logit contributions
+0.046
Once+0.045
By+0.044
spe+0.044
Uh+0.043
Neg logit contributions
ses-0.023
sed-0.016
 crate-0.015
 health-0.015
isk-0.015
Token was
Token ID373
Feature activation+7.40e-01

Pos logit contributions
ses+0.036
oa+0.033
opsy+0.033
ittens+0.033
burn+0.033
Neg logit contributions
Prin-0.023
spe-0.020
-0.020
 cheered-0.019
By-0.019
Token all
Token ID477
Feature activation+1.32e+00

Pos logit contributions
Prin+0.023
spe+0.021
Once+0.020
By+0.020
+0.020
Neg logit contributions
ses-0.029
oa-0.028
opsy-0.028
ittens-0.028
burn-0.027
Token alone
Token ID3436
Feature activation-5.68e-01

Pos logit contributions
Prin+0.043
By+0.039
spe+0.039
CR+0.037
RO+0.037
Neg logit contributions
ses-0.050
opsy-0.045
burn-0.044
ittens-0.044
oa-0.043
Token was
Token ID373
Feature activation+5.48e-01

Pos logit contributions
Prin+0.004
spe+0.004
+0.003
 cheered+0.003
Once+0.003
Neg logit contributions
ses-0.007
ittens-0.007
opsy-0.007
oa-0.007
burn-0.007
Token a
Token ID257
Feature activation+2.57e-01

Pos logit contributions
Prin+0.020
By+0.018
spe+0.018
Once+0.018
+0.018
Neg logit contributions
ses-0.019
oa-0.018
opsy-0.018
ittens-0.018
burn-0.017
Token m
Token ID285
Feature activation+2.22e-01

Pos logit contributions
Prin+0.008
By+0.007
Once+0.007
spe+0.007
+0.007
Neg logit contributions
ses-0.010
oa-0.009
ittens-0.009
burn-0.009
sed-0.009
Tokenitten
Token ID2621
Feature activation-8.95e-01

Pos logit contributions
spe+0.010
+0.009
Once+0.009
 of+0.009
By+0.009
Neg logit contributions
ses-0.006
sed-0.004
oa-0.004
burn-0.004
 potatoes-0.004
Token.
Token ID13
Feature activation+9.17e-01

Pos logit contributions
ses+0.042
oa+0.038
opsy+0.038
ittens+0.037
sed+0.036
Neg logit contributions
Prin-0.021
-0.021
Once-0.019
spe-0.019
By-0.019
Token The
Token ID383
Feature activation+2.75e+00

Pos logit contributions
Prin+0.030
spe+0.027
By+0.025
CR+0.025
 cheered+0.024
Neg logit contributions
ses-0.036
oa-0.033
ittens-0.033
opsy-0.032
burn-0.031
Token m
Token ID285
Feature activation+9.07e-01

Pos logit contributions
Once+0.106
By+0.102
+0.098
Prin+0.097
Uh+0.094
Neg logit contributions
ses-0.091
oa-0.078
sed-0.076
uffy-0.075
opsy-0.073
Tokenitten
Token ID2621
Feature activation-9.21e-01

Pos logit contributions
+0.041
Once+0.040
spe+0.039
By+0.039
Uh+0.039
Neg logit contributions
ses-0.021
sed-0.015
 crate-0.014
isk-0.014
 health-0.014
Token was
Token ID373
Feature activation+7.54e-01

Pos logit contributions
ses+0.044
burn+0.041
opsy+0.041
oa+0.041
ittens+0.040
Neg logit contributions
Prin-0.021
-0.020
 cheered-0.019
spe-0.019
Once-0.018
Token red
Token ID2266
Feature activation-6.59e-01

Pos logit contributions
Prin+0.022
Once+0.020
spe+0.019
+0.019
By+0.019
Neg logit contributions
ses-0.031
oa-0.030
opsy-0.029
ittens-0.028
uffy-0.028
Token and
Token ID290
Feature activation+2.27e-01

Pos logit contributions
ses+0.032
opsy+0.032
oa+0.031
ittens+0.031
uffy+0.030
Neg logit contributions
-0.012
 of-0.012
Prin-0.011
 by-0.011
Once-0.010
Token away
Token ID1497
Feature activation+3.86e-01

Pos logit contributions
ses+0.001
burn+0.001
ittens+0.001
opsy+0.001
oa+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
RO-0.001
 behold-0.001
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
Prin+0.013
spe+0.012
By+0.011
Once+0.011
 cheered+0.011
Neg logit contributions
ses-0.015
opsy-0.013
ittens-0.013
oa-0.013
burn-0.013
Token She
Token ID1375
Feature activation+4.49e-01

Pos logit contributions
Prin+0.012
Once+0.010
By+0.010
+0.010
spe+0.010
Neg logit contributions
ses-0.024
ittens-0.023
opsy-0.023
burn-0.023
oa-0.023
Token learned
Token ID4499
Feature activation+8.41e-01

Pos logit contributions
Prin+0.014
spe+0.012
By+0.012
 cheered+0.011
+0.011
Neg logit contributions
ses-0.019
opsy-0.017
ittens-0.017
oa-0.017
burn-0.017
Token that
Token ID326
Feature activation+5.82e-01

Pos logit contributions
Prin+0.031
spe+0.028
By+0.028
+0.027
Once+0.027
Neg logit contributions
ses-0.030
opsy-0.027
ittens-0.027
oa-0.026
burn-0.026
Token av
Token ID1196
Feature activation+2.73e+00

Pos logit contributions
Prin+0.018
spe+0.016
By+0.016
RO+0.015
 cheered+0.015
Neg logit contributions
ses-0.023
opsy-0.022
ittens-0.022
oa-0.021
burn-0.021
Tokenoc
Token ID420
Feature activation+3.18e-02

Pos logit contributions
Prin+0.091
spe+0.083
By+0.080
CR+0.077
Once+0.077
Neg logit contributions
ses-0.103
opsy-0.096
ittens-0.095
oa-0.095
burn-0.092
Tokenados
Token ID22484
Feature activation+1.25e+00

Pos logit contributions
Prin+0.001
spe+0.001
By+0.001
CR+0.001
 achieved+0.001
Neg logit contributions
ses-0.001
opsy-0.001
ittens-0.001
burn-0.001
uffy-0.001
Token are
Token ID389
Feature activation-1.95e-01

Pos logit contributions
Prin+0.040
spe+0.036
By+0.035
+0.035
 cheered+0.034
Neg logit contributions
ses-0.049
opsy-0.046
ittens-0.046
oa-0.045
burn-0.044
Token good
Token ID922
Feature activation+1.90e-01

Pos logit contributions
ses+0.007
opsy+0.006
ittens+0.006
oa+0.006
burn+0.006
Neg logit contributions
Prin-0.007
spe-0.007
By-0.006
 cheered-0.006
RO-0.006
Token for
Token ID329
Feature activation+5.81e-01

Pos logit contributions
Prin+0.005
 achieved+0.004
+0.004
spe+0.004
 cheered+0.004
Neg logit contributions
ses-0.008
opsy-0.008
oa-0.008
ittens-0.008
burn-0.008
Token shy
Token ID15800
Feature activation+1.67e-01

Pos logit contributions
Prin+0.013
By+0.011
Once+0.011
spe+0.011
+0.011
Neg logit contributions
ses-0.015
oa-0.014
ittens-0.014
burn-0.013
opsy-0.013
Token z
Token ID1976
Feature activation+1.48e-02

Pos logit contributions
Prin+0.005
spe+0.004
RO+0.004
By+0.004
 cheered+0.004
Neg logit contributions
ses-0.007
oa-0.007
ittens-0.006
burn-0.006
opsy-0.006
Tokenig
Token ID328
Feature activation-3.89e-01

Pos logit contributions
Prin+0.001
spe+0.001
By+0.001
CR+0.001
RO+0.001
Neg logit contributions
ses-0.000
oa-0.000
opsy-0.000
ittens-0.000
burn-0.000
Tokenzag
Token ID50183
Feature activation+1.02e-01

Pos logit contributions
ses+0.014
oa+0.013
opsy+0.012
ittens+0.012
burn+0.012
Neg logit contributions
Prin-0.014
spe-0.013
Once-0.012
By-0.012
-0.012
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
 cheered+0.003
Once+0.003
Neg logit contributions
ses-0.004
opsy-0.004
oa-0.004
ittens-0.004
burn-0.004
Token The
Token ID383
Feature activation+2.72e+00

Pos logit contributions
Prin+0.036
spe+0.033
By+0.031
 cheered+0.031
CR+0.030
Neg logit contributions
ses-0.042
oa-0.038
ittens-0.038
opsy-0.037
sed-0.035
Token z
Token ID1976
Feature activation+1.19e+00

Pos logit contributions
Prin+0.099
spe+0.091
By+0.088
CR+0.085
 cheered+0.085
Neg logit contributions
ses-0.096
opsy-0.088
ittens-0.087
oa-0.087
burn-0.084
Tokenig
Token ID328
Feature activation+2.27e-01

Pos logit contributions
Prin+0.055
By+0.052
spe+0.051
CR+0.051
RO+0.050
Neg logit contributions
ses-0.028
opsy-0.025
oa-0.025
burn-0.024
ittens-0.024
Tokenzag
Token ID50183
Feature activation+4.30e-01

Pos logit contributions
Prin+0.010
spe+0.009
By+0.009
 cheered+0.009
CR+0.009
Neg logit contributions
ses-0.006
opsy-0.005
ittens-0.005
oa-0.005
burn-0.005
Token was
Token ID373
Feature activation+7.58e-01

Pos logit contributions
Prin+0.014
spe+0.012
By+0.012
 cheered+0.012
Once+0.012
Neg logit contributions
ses-0.017
opsy-0.016
ittens-0.016
oa-0.016
burn-0.015
Token always
Token ID1464
Feature activation+2.07e-01

Pos logit contributions
Prin+0.027
spe+0.025
By+0.024
 cheered+0.023
Once+0.023
Neg logit contributions
ses-0.027
opsy-0.025
ittens-0.025
oa-0.025
burn-0.024
Token was
Token ID373
Feature activation+3.90e-01

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
CR+0.005
Once+0.005
Neg logit contributions
ses-0.008
opsy-0.007
ittens-0.007
oa-0.007
burn-0.007
Token a
Token ID257
Feature activation+1.08e-01

Pos logit contributions
Prin+0.015
spe+0.014
By+0.013
 cheered+0.013
Once+0.013
Neg logit contributions
ses-0.013
opsy-0.012
ittens-0.012
oa-0.012
burn-0.011
Token modern
Token ID3660
Feature activation+5.35e-01

Pos logit contributions
Prin+0.004
By+0.003
Once+0.003
spe+0.003
+0.003
Neg logit contributions
ses-0.004
oa-0.004
ittens-0.004
burn-0.004
opsy-0.004
Token band
Token ID4097
Feature activation+1.04e-01

Pos logit contributions
Prin+0.019
spe+0.017
Once+0.016
+0.016
By+0.015
Neg logit contributions
ses-0.019
oa-0.018
ittens-0.018
opsy-0.017
burn-0.017
Token.
Token ID13
Feature activation+9.48e-01

Pos logit contributions
Prin+0.004
spe+0.003
By+0.003
 cheered+0.003
Once+0.003
Neg logit contributions
ses-0.004
opsy-0.004
oa-0.004
ittens-0.003
sed-0.003
Token The
Token ID383
Feature activation+2.72e+00

Pos logit contributions
Prin+0.030
spe+0.028
By+0.026
CR+0.025
 cheered+0.025
Neg logit contributions
ses-0.037
ittens-0.034
oa-0.034
opsy-0.034
burn-0.033
Token band
Token ID4097
Feature activation+4.25e-01

Pos logit contributions
Prin+0.101
By+0.093
spe+0.091
Once+0.090
 cheered+0.088
Neg logit contributions
ses-0.095
oa-0.087
opsy-0.086
ittens-0.083
sed-0.081
Token made
Token ID925
Feature activation+1.38e+00

Pos logit contributions
Prin+0.013
spe+0.012
By+0.011
 cheered+0.011
Once+0.011
Neg logit contributions
ses-0.018
opsy-0.017
oa-0.016
ittens-0.016
burn-0.016
Token really
Token ID1107
Feature activation+5.17e-01

Pos logit contributions
Prin+0.054
spe+0.051
By+0.048
+0.048
Once+0.047
Neg logit contributions
ses-0.044
ittens-0.040
opsy-0.039
oa-0.038
burn-0.038
Token cool
Token ID3608
Feature activation+2.02e-01

Pos logit contributions
Prin+0.018
Once+0.016
By+0.016
spe+0.016
CR+0.016
Neg logit contributions
ses-0.019
opsy-0.017
ittens-0.017
sed-0.016
oa-0.016
Token music
Token ID2647
Feature activation-3.29e-01

Pos logit contributions
Prin+0.008
spe+0.007
By+0.007
Once+0.007
CR+0.007
Neg logit contributions
ses-0.007
opsy-0.006
ittens-0.006
oa-0.006
burn-0.006
Token And
Token ID843
Feature activation+9.28e-01

Pos logit contributions
Prin+0.026
spe+0.023
By+0.023
+0.022
Once+0.022
Neg logit contributions
ses-0.032
opsy-0.030
ittens-0.029
oa-0.029
burn-0.029
Token don
Token ID836
Feature activation-3.26e-01

Pos logit contributions
Prin+0.024
+0.024
Once+0.022
By+0.022
 behold+0.021
Neg logit contributions
ses-0.040
opsy-0.038
ittens-0.038
burn-0.038
oa-0.037
Token't
Token ID470
Feature activation+4.28e-01

Pos logit contributions
ses+0.013
opsy+0.012
oa+0.012
ittens+0.012
sed+0.012
Neg logit contributions
Prin-0.010
-0.009
By-0.009
spe-0.009
Once-0.009
Token let
Token ID1309
Feature activation+1.36e+00

Pos logit contributions
Prin+0.016
spe+0.015
By+0.014
+0.014
Once+0.014
Neg logit contributions
ses-0.015
opsy-0.013
ittens-0.013
oa-0.013
burn-0.012
Token go
Token ID467
Feature activation+2.56e-01

Pos logit contributions
Prin+0.041
+0.038
Once+0.036
By+0.035
CR+0.034
Neg logit contributions
ses-0.059
opsy-0.053
sed-0.052
ittens-0.052
oa-0.050
Token of
Token ID286
Feature activation+2.70e+00

Pos logit contributions
+0.006
Prin+0.006
Once+0.006
CR+0.006
 cheered+0.006
Neg logit contributions
ses-0.012
opsy-0.011
oa-0.011
sed-0.011
uf-0.011
Token Velvet
Token ID36271
Feature activation+1.68e-01

Pos logit contributions
+0.051
Prin+0.051
Once+0.050
 again+0.038
By+0.038
Neg logit contributions
ses-0.135
opsy-0.127
sed-0.126
gy-0.125
ower-0.124
Token.
Token ID13
Feature activation+5.29e-01

Pos logit contributions
Prin+0.005
+0.004
spe+0.004
Once+0.004
CR+0.004
Neg logit contributions
ses-0.008
opsy-0.007
sed-0.007
oa-0.007
ittens-0.007
Token She
Token ID1375
Feature activation-2.17e-03

Pos logit contributions
Prin+0.017
spe+0.015
By+0.015
+0.014
Once+0.014
Neg logit contributions
ses-0.021
opsy-0.020
ittens-0.019
oa-0.019
burn-0.019
Token might
Token ID1244
Feature activation-7.37e-01

Pos logit contributions
ses+0.000
ittens+0.000
opsy+0.000
oa+0.000
burn+0.000
Neg logit contributions
-0.000
Prin-0.000
 cheered-0.000
 achieved-0.000
 scored-0.000
Token get
Token ID651
Feature activation+2.47e-01

Pos logit contributions
ses+0.027
oa+0.026
ittens+0.026
opsy+0.025
uffy+0.024
Neg logit contributions
Prin-0.025
-0.024
Once-0.023
By-0.022
spe-0.022
Token.
Token ID13
Feature activation+4.61e-01

Pos logit contributions
ses+0.018
ittens+0.017
opsy+0.016
oa+0.016
sed+0.016
Neg logit contributions
Prin-0.014
-0.013
spe-0.013
 cheered-0.013
 achieved-0.012
Token Did
Token ID7731
Feature activation-2.69e-01

Pos logit contributions
Prin+0.015
spe+0.013
By+0.013
+0.013
Once+0.013
Neg logit contributions
ses-0.018
opsy-0.017
ittens-0.017
oa-0.016
burn-0.016
Token you
Token ID345
Feature activation+4.54e-02

Pos logit contributions
ses+0.013
opsy+0.012
burn+0.012
ittens+0.011
oa+0.011
Neg logit contributions
Prin-0.006
-0.006
spe-0.006
Once-0.005
 behold-0.005
Token know
Token ID760
Feature activation-2.85e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
CR+0.002
RO+0.002
Neg logit contributions
ses-0.001
opsy-0.001
ittens-0.001
oa-0.001
burn-0.001
Token that
Token ID326
Feature activation+7.90e-02

Pos logit contributions
ses+0.011
opsy+0.010
ittens+0.010
oa+0.010
sed+0.009
Neg logit contributions
Prin-0.010
-0.009
spe-0.009
Once-0.009
By-0.008
Token av
Token ID1196
Feature activation+2.69e+00

Pos logit contributions
Prin+0.003
By+0.003
spe+0.003
Once+0.002
CR+0.002
Neg logit contributions
ses-0.003
burn-0.002
opsy-0.002
oa-0.002
ittens-0.002
Tokenoc
Token ID420
Feature activation-6.20e-01

Pos logit contributions
Prin+0.104
spe+0.100
By+0.097
RO+0.096
CR+0.096
Neg logit contributions
ses-0.078
ittens-0.076
opsy-0.074
oa-0.072
burn-0.072
Tokenados
Token ID22484
Feature activation+9.68e-01

Pos logit contributions
ses+0.018
opsy+0.017
ittens+0.016
oa+0.016
burn+0.016
Neg logit contributions
Prin-0.026
spe-0.024
By-0.023
CR-0.023
-0.023
Token are
Token ID389
Feature activation-1.05e+00

Pos logit contributions
Prin+0.030
spe+0.028
+0.026
By+0.026
 cheered+0.026
Neg logit contributions
ses-0.039
opsy-0.036
ittens-0.036
oa-0.035
burn-0.035
Token very
Token ID845
Feature activation-8.22e-01

Pos logit contributions
ses+0.032
opsy+0.030
ittens+0.029
oa+0.029
burn+0.028
Neg logit contributions
Prin-0.042
spe-0.039
By-0.038
 cheered-0.037
RO-0.037
Token healthy
Token ID5448
Feature activation-4.23e-02

Pos logit contributions
ses+0.027
opsy+0.025
ittens+0.025
oa+0.025
burn+0.024
Neg logit contributions
Prin-0.031
spe-0.028
By-0.028
 cheered-0.027
Once-0.027
Token right
Token ID826
Feature activation+9.01e-01

Pos logit contributions
ses+0.022
opsy+0.021
ittens+0.021
oa+0.021
burn+0.020
Neg logit contributions
Prin-0.019
spe-0.017
By-0.017
Once-0.016
 cheered-0.016
Token!"
Token ID2474
Feature activation+2.09e-01

Pos logit contributions
Prin+0.028
spe+0.025
By+0.025
Once+0.025
CR+0.025
Neg logit contributions
ses-0.036
ittens-0.033
opsy-0.033
oa-0.032
burn-0.032
Token He
Token ID679
Feature activation+3.16e-01

Pos logit contributions
Prin+0.005
Once+0.004
By+0.004
spe+0.004
 cheered+0.004
Neg logit contributions
ses-0.010
opsy-0.009
burn-0.009
oa-0.009
ittens-0.009
Token picked
Token ID6497
Feature activation+6.74e-01

Pos logit contributions
Prin+0.010
spe+0.009
By+0.009
CR+0.008
Once+0.008
Neg logit contributions
ses-0.013
opsy-0.012
oa-0.012
ittens-0.012
burn-0.011
Token up
Token ID510
Feature activation+5.03e-01

Pos logit contributions
Prin+0.018
+0.016
 cheered+0.016
By+0.015
 triumph+0.015
Neg logit contributions
ses-0.030
ittens-0.029
opsy-0.028
oa-0.028
uffy-0.028
Token the
Token ID262
Feature activation+2.67e+00

Pos logit contributions
Prin+0.012
spe+0.010
By+0.010
Once+0.009
 cheered+0.009
Neg logit contributions
ses-0.024
opsy-0.023
ittens-0.023
oa-0.023
burn-0.022
Token tw
Token ID665
Feature activation+2.79e+00

Pos logit contributions
Prin+0.094
spe+0.087
By+0.084
 cheered+0.081
CR+0.081
Neg logit contributions
ses-0.096
opsy-0.089
ittens-0.088
oa-0.087
burn-0.085
Tokenig
Token ID328
Feature activation-3.42e-01

Pos logit contributions
Prin+0.127
spe+0.118
By+0.116
CR+0.115
Once+0.113
Neg logit contributions
ses-0.072
oa-0.064
opsy-0.061
ittens-0.060
burn-0.059
Token and
Token ID290
Feature activation+3.38e-01

Pos logit contributions
ses+0.013
opsy+0.012
oa+0.012
ittens+0.012
burn+0.012
Neg logit contributions
Prin-0.011
spe-0.010
By-0.009
-0.009
Once-0.009
Token started
Token ID2067
Feature activation+8.49e-02

Pos logit contributions
Prin+0.011
spe+0.010
By+0.010
Once+0.009
CR+0.009
Neg logit contributions
ses-0.013
opsy-0.012
oa-0.012
ittens-0.012
burn-0.012
Token to
Token ID284
Feature activation+5.87e-01

Pos logit contributions
Prin+0.003
spe+0.002
By+0.002
Once+0.002
+0.002
Neg logit contributions
ses-0.004
opsy-0.003
ittens-0.003
oa-0.003
burn-0.003
Token.
Token ID13
Feature activation+8.99e-01

Pos logit contributions
Prin+0.015
RO+0.014
By+0.013
spe+0.013
Happy+0.013
Neg logit contributions
ses-0.010
burn-0.009
ittens-0.009
oa-0.009
uffy-0.008
Token They
Token ID1119
Feature activation+7.26e-02

Pos logit contributions
Prin+0.032
spe+0.030
By+0.029
Once+0.028
 cheered+0.028
Neg logit contributions
ses-0.032
opsy-0.030
oa-0.029
ittens-0.029
burn-0.028
Token forget
Token ID6044
Feature activation+1.38e+00

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
CR+0.003
Happy+0.003
Neg logit contributions
ses-0.002
opsy-0.002
oa-0.002
ittens-0.002
burn-0.002
Token about
Token ID546
Feature activation+8.94e-01

Pos logit contributions
Prin+0.044
spe+0.040
Uh+0.038
By+0.038
RO+0.037
Neg logit contributions
ses-0.054
oa-0.050
opsy-0.049
ittens-0.049
burn-0.048
Token the
Token ID262
Feature activation+8.70e-02

Pos logit contributions
spe+0.010
 behold+0.009
 triumph+0.009
Once+0.008
 cheered+0.008
Neg logit contributions
ittens-0.051
itten-0.049
ses-0.049
uffy-0.048
erry-0.048
Token av
Token ID1196
Feature activation+2.66e+00

Pos logit contributions
Prin+0.004
spe+0.003
By+0.003
Once+0.003
 cheered+0.003
Neg logit contributions
ses-0.003
opsy-0.002
ittens-0.002
oa-0.002
burn-0.002
Tokenoc
Token ID420
Feature activation-6.99e-01

Pos logit contributions
Prin+0.098
spe+0.092
RO+0.087
By+0.087
CR+0.086
Neg logit contributions
ses-0.089
ittens-0.086
opsy-0.085
oa-0.083
burn-0.081
Tokenados
Token ID22484
Feature activation+1.90e+00

Pos logit contributions
ses+0.022
opsy+0.020
ittens+0.020
burn+0.019
uffy+0.019
Neg logit contributions
Prin-0.027
spe-0.026
By-0.024
CR-0.024
 rect-0.024
Token.
Token ID13
Feature activation+7.36e-01

Pos logit contributions
Prin+0.065
spe+0.060
By+0.058
+0.057
 cheered+0.057
Neg logit contributions
ses-0.070
opsy-0.064
ittens-0.064
oa-0.064
burn-0.062
Token They
Token ID1119
Feature activation-2.41e-01

Pos logit contributions
Prin+0.028
spe+0.026
By+0.024
 cheered+0.024
 achieved+0.024
Neg logit contributions
ses-0.025
oa-0.023
opsy-0.023
ittens-0.022
sed-0.021
Token just
Token ID655
Feature activation-7.89e-02

Pos logit contributions
ses+0.008
opsy+0.007
oa+0.007
ittens+0.007
burn+0.007
Neg logit contributions
Prin-0.009
spe-0.009
By-0.008
CR-0.008
Happy-0.008
Token and
Token ID290
Feature activation+4.20e-01

Pos logit contributions
Prin+0.012
spe+0.011
By+0.011
RO+0.010
CR+0.010
Neg logit contributions
ses-0.009
opsy-0.008
ittens-0.008
oa-0.008
burn-0.008
Token try
Token ID1949
Feature activation+9.33e-02

Pos logit contributions
Prin+0.018
spe+0.017
By+0.016
CR+0.016
Once+0.015
Neg logit contributions
ses-0.013
opsy-0.011
oa-0.011
ittens-0.011
burn-0.011
Token to
Token ID284
Feature activation+3.01e-03

Pos logit contributions
Prin+0.002
+0.001
 rect+0.001
Once+0.001
 scored+0.001
Neg logit contributions
ses-0.005
ittens-0.005
opsy-0.005
oa-0.005
uffy-0.005
Token grab
Token ID5552
Feature activation-1.62e-01

Pos logit contributions
Prin+0.000
 behold+0.000
Once+0.000
+0.000
By+0.000
Neg logit contributions
ses-0.000
ittens-0.000
oa-0.000
uffy-0.000
opsy-0.000
Token the
Token ID262
Feature activation-4.74e-01

Pos logit contributions
ses+0.008
ittens+0.007
opsy+0.007
oa+0.007
uffy+0.007
Neg logit contributions
Prin-0.004
-0.003
spe-0.003
 cheered-0.003
By-0.003
Token av
Token ID1196
Feature activation+2.66e+00

Pos logit contributions
ses+0.014
opsy+0.013
oa+0.013
ittens+0.012
burn+0.012
Neg logit contributions
Prin-0.020
spe-0.019
By-0.018
-0.018
Once-0.018
Tokenoc
Token ID420
Feature activation-8.81e-01

Pos logit contributions
Prin+0.101
spe+0.098
RO+0.094
By+0.093
 cheered+0.092
Neg logit contributions
ses-0.079
ittens-0.079
opsy-0.079
oa-0.077
burn-0.075
Tokenados
Token ID22484
Feature activation+1.90e+00

Pos logit contributions
ses+0.027
opsy+0.025
ittens+0.024
burn+0.024
oa+0.023
Neg logit contributions
Prin-0.034
spe-0.033
By-0.031
CR-0.031
 rect-0.030
Token.
Token ID13
Feature activation+6.34e-01

Pos logit contributions
Prin+0.070
spe+0.065
RO+0.063
By+0.063
 behold+0.061
Neg logit contributions
ses-0.064
opsy-0.060
oa-0.059
ittens-0.058
burn-0.057
Token But
Token ID887
Feature activation+7.82e-02

Pos logit contributions
Prin+0.021
spe+0.019
By+0.019
Once+0.018
+0.018
Neg logit contributions
ses-0.024
opsy-0.023
ittens-0.022
oa-0.022
burn-0.022
Token the
Token ID262
Feature activation-8.09e-01

Pos logit contributions
Prin+0.003
spe+0.003
Happy+0.003
RO+0.003
By+0.002
Neg logit contributions
ses-0.003
opsy-0.003
oa-0.003
sed-0.002
ittens-0.002
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
Prin+0.019
+0.018
Once+0.017
spe+0.017
 behold+0.017
Neg logit contributions
ses-0.028
ittens-0.027
oa-0.026
opsy-0.026
uffy-0.025
Token store
Token ID3650
Feature activation+3.62e-01

Pos logit contributions
ses+0.005
opsy+0.005
oa+0.005
ittens+0.004
burn+0.004
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
RO-0.008
CR-0.008
Token to
Token ID284
Feature activation-6.12e-02

Pos logit contributions
Prin+0.011
spe+0.011
 cheered+0.010
Once+0.010
By+0.010
Neg logit contributions
ses-0.014
opsy-0.014
ittens-0.013
oa-0.013
burn-0.013
Token get
Token ID651
Feature activation-3.15e-01

Pos logit contributions
ses+0.002
ittens+0.002
oa+0.002
sed+0.002
uffy+0.002
Neg logit contributions
Prin-0.002
-0.002
Once-0.002
 behold-0.002
spe-0.002
Token more
Token ID517
Feature activation+2.17e-01

Pos logit contributions
ses+0.009
opsy+0.009
burn+0.009
ittens+0.009
oa+0.009
Neg logit contributions
Prin-0.012
spe-0.011
RO-0.011
By-0.011
CR-0.011
Token av
Token ID1196
Feature activation+2.63e+00

Pos logit contributions
Prin+0.010
By+0.009
spe+0.009
RO+0.009
CR+0.009
Neg logit contributions
ittens-0.005
opsy-0.005
erry-0.005
ses-0.005
 potato-0.004
Tokenoc
Token ID420
Feature activation+1.30e-01

Pos logit contributions
Prin+0.100
spe+0.094
RO+0.091
By+0.089
CR+0.089
Neg logit contributions
ittens-0.081
ses-0.080
opsy-0.079
oa-0.077
burn-0.076
Tokenados
Token ID22484
Feature activation+1.74e+00

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
CR+0.005
+0.005
Neg logit contributions
ses-0.004
opsy-0.004
ittens-0.004
burn-0.003
oa-0.003
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
Prin+0.065
spe+0.059
RO+0.058
By+0.057
CR+0.057
Neg logit contributions
ses-0.058
ittens-0.054
opsy-0.054
oa-0.053
burn-0.052
Token Gary
Token ID10936
Feature activation-4.93e-01

Pos logit contributions
ses+0.041
opsy+0.038
oa+0.038
ittens+0.038
burn+0.036
Neg logit contributions
Prin-0.036
spe-0.033
By-0.032
CR-0.031
 cheered-0.031
Token looked
Token ID3114
Feature activation-1.73e-01

Pos logit contributions
ses+0.021
opsy+0.019
oa+0.019
ittens+0.019
burn+0.019
Neg logit contributions
Prin-0.014
spe-0.013
By-0.012
CR-0.012
Once-0.012
Token the
Token ID262
Feature activation-7.37e-01

Pos logit contributions
Prin+0.004
+0.003
Once+0.003
 cheered+0.003
 behold+0.003
Neg logit contributions
ses-0.007
ittens-0.007
opsy-0.006
burn-0.006
oa-0.006
Token tree
Token ID5509
Feature activation+5.37e-01

Pos logit contributions
ses+0.025
opsy+0.023
ittens+0.023
oa+0.022
burn+0.022
Neg logit contributions
Prin-0.028
spe-0.026
By-0.025
Once-0.024
-0.024
Token if
Token ID611
Feature activation-4.02e-01

Pos logit contributions
Prin+0.019
By+0.018
spe+0.017
RO+0.017
CR+0.017
Neg logit contributions
ses-0.019
opsy-0.017
ittens-0.017
oa-0.017
uffy-0.016
Token they
Token ID484
Feature activation+4.70e-01

Pos logit contributions
ses+0.013
opsy+0.013
oa+0.013
 Cow+0.012
uffy+0.012
Neg logit contributions
Prin-0.014
spe-0.014
RO-0.013
By-0.013
 cheered-0.013
Token were
Token ID547
Feature activation-5.94e-01

Pos logit contributions
Prin+0.011
spe+0.010
By+0.009
+0.009
 cheered+0.009
Neg logit contributions
ses-0.023
ittens-0.021
oa-0.021
opsy-0.021
burn-0.021
Token av
Token ID1196
Feature activation+2.60e+00

Pos logit contributions
ses+0.022
oa+0.020
opsy+0.020
ittens+0.020
burn+0.020
Neg logit contributions
Prin-0.020
spe-0.018
By-0.018
Once-0.018
-0.018
Tokenoc
Token ID420
Feature activation-2.71e-01

Pos logit contributions
Prin+0.100
spe+0.092
RO+0.089
By+0.089
CR+0.088
Neg logit contributions
ses-0.081
ittens-0.080
opsy-0.077
oa-0.076
burn-0.074
Tokenados
Token ID22484
Feature activation+1.49e+00

Pos logit contributions
ses+0.008
opsy+0.007
ittens+0.007
oa+0.007
burn+0.007
Neg logit contributions
Prin-0.011
spe-0.011
By-0.010
CR-0.010
-0.010
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
Prin+0.046
spe+0.042
+0.041
By+0.040
Once+0.040
Neg logit contributions
ses-0.060
opsy-0.056
ittens-0.055
oa-0.055
burn-0.053
Token and
Token ID290
Feature activation-4.24e-01

Pos logit contributions
ses+0.007
opsy+0.006
oa+0.006
ittens+0.006
burn+0.006
Neg logit contributions
Prin-0.007
spe-0.006
-0.006
Once-0.006
By-0.006
Token they
Token ID484
Feature activation+3.25e-01

Pos logit contributions
ses+0.016
opsy+0.015
oa+0.015
ittens+0.014
burn+0.014
Neg logit contributions
Prin-0.014
By-0.013
spe-0.013
CR-0.012
RO-0.012
Token girl
Token ID2576
Feature activation+5.08e-01

Pos logit contributions
Prin+0.012
+0.010
 cheered+0.010
spe+0.010
By+0.010
Neg logit contributions
ses-0.021
oa-0.020
ittens-0.020
sed-0.019
ats-0.019
Token who
Token ID508
Feature activation-2.31e-01

Pos logit contributions
Prin+0.016
+0.015
Once+0.015
spe+0.014
 cheered+0.014
Neg logit contributions
ses-0.021
oa-0.019
ittens-0.018
sed-0.018
opsy-0.018
Token didn
Token ID1422
Feature activation-1.23e+00

Pos logit contributions
ses+0.010
ittens+0.010
oa+0.010
burn+0.009
opsy+0.009
Neg logit contributions
Prin-0.007
-0.007
 cheered-0.006
By-0.006
Once-0.006
Token't
Token ID470
Feature activation-5.90e-02

Pos logit contributions
ses+0.053
opsy+0.048
oa+0.048
ittens+0.047
sed+0.047
Neg logit contributions
Prin-0.037
-0.034
spe-0.033
By-0.032
CR-0.032
Token like
Token ID588
Feature activation-3.27e-01

Pos logit contributions
ses+0.003
oa+0.003
sed+0.002
opsy+0.002
uffy+0.002
Neg logit contributions
Prin-0.002
Once-0.002
-0.002
 cheered-0.001
By-0.001
Token av
Token ID1196
Feature activation+2.59e+00

Pos logit contributions
ses+0.015
opsy+0.014
ittens+0.014
oa+0.014
uffy+0.013
Neg logit contributions
Prin-0.008
spe-0.007
Once-0.007
-0.007
By-0.007
Tokenoc
Token ID420
Feature activation-2.22e-01

Pos logit contributions
Prin+0.090
spe+0.083
By+0.080
CR+0.078
 cheered+0.078
Neg logit contributions
ses-0.093
ittens-0.087
opsy-0.087
oa-0.086
burn-0.083
Tokenados
Token ID22484
Feature activation+1.60e+00

Pos logit contributions
ses+0.007
opsy+0.006
ittens+0.006
burn+0.006
oa+0.006
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
CR-0.008
Once-0.008
Token.
Token ID13
Feature activation+5.30e-01

Pos logit contributions
Prin+0.044
+0.041
Once+0.040
 achieved+0.038
spe+0.038
Neg logit contributions
ses-0.071
opsy-0.065
oa-0.063
sed-0.063
ittens-0.062
Token She
Token ID1375
Feature activation+6.98e-01

Pos logit contributions
Prin+0.016
spe+0.014
Once+0.014
+0.013
By+0.013
Neg logit contributions
ses-0.022
opsy-0.021
ittens-0.021
oa-0.020
burn-0.020
Token always
Token ID1464
Feature activation-2.46e-01

Pos logit contributions
Prin+0.023
spe+0.021
By+0.020
+0.019
 cheered+0.019
Neg logit contributions
ses-0.027
opsy-0.025
ittens-0.025
oa-0.025
burn-0.025
Token there
Token ID612
Feature activation+8.43e-02

Pos logit contributions
Prin+0.015
spe+0.014
By+0.013
RO+0.012
 achieved+0.012
Neg logit contributions
ses-0.021
opsy-0.020
uffy-0.019
ittens-0.019
oa-0.018
Token was
Token ID373
Feature activation+2.64e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
Once+0.002
+0.002
Neg logit contributions
ses-0.004
opsy-0.003
ittens-0.003
oa-0.003
burn-0.003
Token a
Token ID257
Feature activation+1.28e-01

Pos logit contributions
Prin+0.010
spe+0.010
By+0.009
 cheered+0.009
CR+0.009
Neg logit contributions
ses-0.008
opsy-0.008
ittens-0.008
oa-0.007
burn-0.007
Token band
Token ID4097
Feature activation+2.61e-01

Pos logit contributions
Prin+0.004
By+0.004
Once+0.004
spe+0.004
+0.004
Neg logit contributions
ses-0.005
oa-0.005
ittens-0.005
burn-0.004
opsy-0.004
Token.
Token ID13
Feature activation+9.07e-01

Pos logit contributions
Prin+0.009
spe+0.009
By+0.008
 cheered+0.008
Once+0.008
Neg logit contributions
ses-0.010
oa-0.009
opsy-0.009
ittens-0.009
sed-0.008
Token The
Token ID383
Feature activation+2.58e+00

Pos logit contributions
Prin+0.030
spe+0.027
By+0.026
CR+0.025
 cheered+0.025
Neg logit contributions
ses-0.035
oa-0.032
ittens-0.032
opsy-0.031
burn-0.030
Token band
Token ID4097
Feature activation+6.29e-01

Pos logit contributions
Prin+0.094
By+0.087
Once+0.084
spe+0.082
+0.081
Neg logit contributions
ses-0.093
oa-0.085
opsy-0.084
ittens-0.080
sed-0.079
Token was
Token ID373
Feature activation+1.15e+00

Pos logit contributions
Prin+0.019
spe+0.018
By+0.017
 cheered+0.017
Once+0.016
Neg logit contributions
ses-0.026
opsy-0.024
oa-0.024
ittens-0.024
burn-0.023
Token unusual
Token ID8468
Feature activation+5.58e-01

Pos logit contributions
Prin+0.035
Once+0.032
By+0.031
spe+0.031
+0.030
Neg logit contributions
ses-0.045
oa-0.044
opsy-0.043
ittens-0.042
uffy-0.041
Token.
Token ID13
Feature activation+8.43e-01

Pos logit contributions
Prin+0.014
spe+0.013
+0.013
 rect+0.012
Once+0.012
Neg logit contributions
ses-0.025
opsy-0.024
oa-0.024
ittens-0.023
sed-0.022
Token The
Token ID383
Feature activation+2.16e+00

Pos logit contributions
Prin+0.025
spe+0.022
By+0.021
 cheered+0.020
CR+0.020
Neg logit contributions
ses-0.036
opsy-0.033
ittens-0.033
oa-0.033
burn-0.032
Token but
Token ID475
Feature activation-1.53e-01

Pos logit contributions
ses+0.029
oa+0.026
ittens+0.025
opsy+0.025
sed+0.025
Neg logit contributions
Prin-0.037
By-0.035
spe-0.035
CR-0.034
Happy-0.033
Token there
Token ID612
Feature activation+5.81e-02

Pos logit contributions
ses+0.005
sed+0.005
oa+0.004
opsy+0.004
 Cow+0.004
Neg logit contributions
Prin-0.006
Happy-0.005
RO-0.005
By-0.005
spe-0.005
Token were
Token ID547
Feature activation-1.49e-01

Pos logit contributions
Prin+0.002
By+0.002
spe+0.002
CR+0.002
Happy+0.002
Neg logit contributions
ses-0.002
opsy-0.002
oa-0.002
ittens-0.002
uffy-0.002
Token no
Token ID645
Feature activation-9.95e-02

Pos logit contributions
ses+0.006
opsy+0.005
ittens+0.005
oa+0.005
burn+0.005
Neg logit contributions
Prin-0.005
spe-0.005
By-0.005
CR-0.004
 cheered-0.004
Token other
Token ID584
Feature activation-1.10e-01

Pos logit contributions
ses+0.003
opsy+0.003
ittens+0.003
oa+0.003
burn+0.003
Neg logit contributions
Prin-0.004
spe-0.004
By-0.003
CR-0.003
Once-0.003
Token av
Token ID1196
Feature activation+2.57e+00

Pos logit contributions
ses+0.004
opsy+0.003
ittens+0.003
oa+0.003
burn+0.003
Neg logit contributions
Prin-0.004
spe-0.004
By-0.004
CR-0.004
Once-0.004
Tokenoc
Token ID420
Feature activation+3.04e-02

Pos logit contributions
Prin+0.095
spe+0.088
By+0.084
RO+0.083
 behold+0.083
Neg logit contributions
ses-0.087
ittens-0.082
opsy-0.081
oa-0.079
burn-0.078
Tokenados
Token ID22484
Feature activation+1.13e+00

Pos logit contributions
Prin+0.001
spe+0.001
By+0.001
CR+0.001
RO+0.001
Neg logit contributions
ses-0.001
opsy-0.001
ittens-0.001
burn-0.001
oa-0.001
Token.
Token ID13
Feature activation-1.95e-01

Pos logit contributions
Prin+0.036
spe+0.033
+0.032
By+0.032
Once+0.032
Neg logit contributions
ses-0.044
opsy-0.041
oa-0.040
ittens-0.040
burn-0.039
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
ses+0.006
oa+0.005
uffy+0.005
ittens+0.005
sed+0.005
Neg logit contributions
Prin-0.007
spe-0.007
By-0.007
Happy-0.007
 achieved-0.007
Token
Token ID198
Feature activation+2.87e-01

Pos logit contributions
ses+0.007
opsy+0.007
ittens+0.007
oa+0.007
uffy+0.006
Neg logit contributions
Prin-0.005
spe-0.004
By-0.004
CR-0.004
RO-0.004
Token cows
Token ID22575
Feature activation-1.20e+00

Pos logit contributions
ses+0.066
opsy+0.063
ittens+0.062
uffy+0.059
oa+0.058
Neg logit contributions
Prin-0.063
-0.058
spe-0.057
 cheered-0.056
Once-0.055
Token,
Token ID11
Feature activation-2.14e+00

Pos logit contributions
ses+0.056
opsy+0.053
ittens+0.051
burn+0.050
oa+0.050
Neg logit contributions
Prin-0.027
-0.026
 cheered-0.025
Once-0.025
spe-0.023
Token pigs
Token ID22333
Feature activation-1.07e+00

Pos logit contributions
ses+0.072
opsy+0.065
oa+0.062
ittens+0.062
uffy+0.061
Neg logit contributions
Prin-0.084
Once-0.077
-0.076
 rect-0.074
RO-0.073
Token,
Token ID11
Feature activation-2.08e+00

Pos logit contributions
ses+0.052
opsy+0.048
burn+0.046
ittens+0.046
sed+0.046
Neg logit contributions
Prin-0.023
-0.023
Once-0.022
 cheered-0.021
spe-0.020
Token chickens
Token ID25972
Feature activation-1.18e+00

Pos logit contributions
ses+0.080
opsy+0.074
oa+0.072
ittens+0.071
uffy+0.070
Neg logit contributions
Prin-0.070
Once-0.064
-0.063
 rect-0.061
By-0.060
Token and
Token ID290
Feature activation-2.70e+00

Pos logit contributions
ses+0.049
opsy+0.045
ittens+0.044
oa+0.044
burn+0.044
Neg logit contributions
Prin-0.035
spe-0.031
-0.031
Once-0.030
 cheered-0.030
Token sheep
Token ID15900
Feature activation-1.47e+00

Pos logit contributions
ses+0.081
opsy+0.077
ittens+0.074
oa+0.074
uffy+0.074
Neg logit contributions
Prin-0.114
-0.106
RO-0.101
By-0.101
Once-0.101
Token.
Token ID13
Feature activation+2.43e-02

Pos logit contributions
ses+0.056
opsy+0.052
ittens+0.051
oa+0.050
burn+0.049
Neg logit contributions
Prin-0.049
spe-0.044
-0.043
By-0.042
 cheered-0.042
Token They
Token ID1119
Feature activation-1.26e+00

Pos logit contributions
Prin+0.001
spe+0.001
 achieved+0.001
By+0.001
RO+0.001
Neg logit contributions
ses-0.001
ittens-0.001
oa-0.001
opsy-0.001
uffy-0.001
Token liked
Token ID8288
Feature activation-1.09e+00

Pos logit contributions
ses+0.060
ittens+0.057
oa+0.056
burn+0.056
opsy+0.054
Neg logit contributions
Prin-0.031
 cheered-0.028
Once-0.027
-0.027
spe-0.027
Token to
Token ID284
Feature activation-1.69e+00

Pos logit contributions
ses+0.052
opsy+0.048
ittens+0.048
uffy+0.047
oa+0.046
Neg logit contributions
Prin-0.026
spe-0.023
Once-0.022
 rect-0.022
-0.021
Token like
Token ID588
Feature activation-1.67e+00

Pos logit contributions
ses+0.059
opsy+0.055
oa+0.055
ittens+0.055
burn+0.053
Neg logit contributions
Prin-0.047
spe-0.042
By-0.040
Once-0.040
 cheered-0.040
Token cows
Token ID22575
Feature activation-1.26e+00

Pos logit contributions
ses+0.060
opsy+0.058
ittens+0.057
uffy+0.055
oa+0.053
Neg logit contributions
Prin-0.060
-0.056
spe-0.054
 cheered-0.053
Once-0.053
Token,
Token ID11
Feature activation-2.05e+00

Pos logit contributions
ses+0.060
opsy+0.057
ittens+0.055
burn+0.055
sed+0.053
Neg logit contributions
-0.027
Prin-0.027
 cheered-0.024
Once-0.024
spe-0.023
Token pigs
Token ID22333
Feature activation-1.11e+00

Pos logit contributions
ses+0.067
opsy+0.061
oa+0.057
ittens+0.057
uffy+0.056
Neg logit contributions
Prin-0.081
Once-0.075
-0.075
 rect-0.072
By-0.071
Token,
Token ID11
Feature activation-1.96e+00

Pos logit contributions
ses+0.055
opsy+0.051
burn+0.049
ittens+0.049
sed+0.049
Neg logit contributions
-0.024
Prin-0.023
Once-0.022
 cheered-0.021
spe-0.020
Token and
Token ID290
Feature activation-2.69e+00

Pos logit contributions
ses+0.078
opsy+0.073
oa+0.070
ittens+0.069
uffy+0.068
Neg logit contributions
Prin-0.064
Once-0.059
-0.058
 rect-0.055
By-0.055
Token chickens
Token ID25972
Feature activation-1.07e+00

Pos logit contributions
ses+0.079
opsy+0.075
ittens+0.073
uffy+0.072
oa+0.071
Neg logit contributions
Prin-0.114
-0.106
Once-0.102
By-0.102
 rect-0.102
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
ses+0.040
opsy+0.037
ittens+0.036
oa+0.036
burn+0.035
Neg logit contributions
Prin-0.036
spe-0.033
By-0.032
-0.032
 cheered-0.031
Token But
Token ID887
Feature activation-7.23e-02

Pos logit contributions
Prin+0.008
spe+0.007
 achieved+0.007
By+0.007
Happy+0.007
Neg logit contributions
ses-0.006
opsy-0.005
oa-0.005
ittens-0.005
uffy-0.005
Token their
Token ID511
Feature activation-1.02e+00

Pos logit contributions
ses+0.003
opsy+0.003
oa+0.003
ittens+0.003
burn+0.002
Neg logit contributions
Prin-0.002
spe-0.002
By-0.002
RO-0.002
 cheered-0.002
Token favorite
Token ID4004
Feature activation-2.15e+00

Pos logit contributions
ittens+0.031
opsy+0.030
ses+0.030
burn+0.029
oa+0.029
Neg logit contributions
spe-0.037
Prin-0.035
By-0.033
Once-0.033
-0.032
Token like
Token ID588
Feature activation-1.62e+00

Pos logit contributions
ses+0.067
opsy+0.062
ittens+0.061
oa+0.061
burn+0.060
Neg logit contributions
Prin-0.055
spe-0.050
By-0.048
Once-0.047
 cheered-0.046
Token monkeys
Token ID26697
Feature activation-8.77e-01

Pos logit contributions
ses+0.064
opsy+0.062
ittens+0.061
oa+0.059
burn+0.058
Neg logit contributions
Prin-0.051
spe-0.046
-0.045
By-0.044
 cheered-0.044
Token,
Token ID11
Feature activation-2.11e+00

Pos logit contributions
ses+0.038
opsy+0.036
burn+0.034
oa+0.034
ittens+0.034
Neg logit contributions
Prin-0.024
-0.022
Once-0.021
spe-0.021
 cheered-0.021
Token birds
Token ID10087
Feature activation-1.09e+00

Pos logit contributions
ses+0.087
opsy+0.084
ittens+0.081
oa+0.080
uffy+0.078
Neg logit contributions
Prin-0.063
spe-0.056
Once-0.056
-0.055
By-0.054
Token,
Token ID11
Feature activation-1.98e+00

Pos logit contributions
ses+0.046
opsy+0.042
oa+0.042
ittens+0.041
burn+0.040
Neg logit contributions
Prin-0.031
-0.028
Once-0.028
By-0.027
spe-0.027
Token and
Token ID290
Feature activation-2.68e+00

Pos logit contributions
ses+0.076
opsy+0.072
ittens+0.071
oa+0.070
burn+0.068
Neg logit contributions
Prin-0.065
spe-0.058
By-0.058
Once-0.057
 cheered-0.056
Token elephants
Token ID25368
Feature activation-7.21e-01

Pos logit contributions
ses+0.093
opsy+0.085
ittens+0.085
oa+0.085
burn+0.082
Neg logit contributions
Prin-0.097
spe-0.089
By-0.087
CR-0.084
Once-0.084
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
ses+0.023
ittens+0.021
oa+0.021
opsy+0.021
burn+0.020
Neg logit contributions
Prin-0.028
spe-0.026
By-0.025
CR-0.025
RO-0.024
Token They
Token ID1119
Feature activation-9.28e-01

Pos logit contributions
ses+0.011
ittens+0.011
oa+0.010
opsy+0.010
uffy+0.010
Neg logit contributions
spe-0.013
Prin-0.013
 achieved-0.012
RO-0.011
 cheered-0.011
Token liked
Token ID8288
Feature activation-8.65e-01

Pos logit contributions
ses+0.040
opsy+0.037
ittens+0.037
oa+0.037
burn+0.036
Neg logit contributions
Prin-0.026
spe-0.024
By-0.023
 cheered-0.022
Once-0.022
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
ses+0.039
opsy+0.036
ittens+0.036
oa+0.036
burn+0.035
Neg logit contributions
Prin-0.023
spe-0.021
By-0.020
Once-0.019
 cheered-0.019
Token like
Token ID588
Feature activation-1.85e+00

Pos logit contributions
ses+0.062
opsy+0.059
oa+0.058
ittens+0.058
burn+0.056
Neg logit contributions
Prin-0.043
spe-0.038
By-0.037
Once-0.036
 cheered-0.036
Token cows
Token ID22575
Feature activation-1.16e+00

Pos logit contributions
ses+0.069
opsy+0.066
ittens+0.065
uffy+0.062
oa+0.062
Neg logit contributions
Prin-0.063
spe-0.057
-0.057
 cheered-0.055
By-0.055
Token,
Token ID11
Feature activation-2.08e+00

Pos logit contributions
ses+0.057
opsy+0.054
ittens+0.052
burn+0.052
oa+0.050
Neg logit contributions
-0.024
Prin-0.023
 cheered-0.021
Once-0.021
spe-0.019
Token pigs
Token ID22333
Feature activation-9.70e-01

Pos logit contributions
ses+0.071
opsy+0.066
oa+0.062
ittens+0.062
uffy+0.061
Neg logit contributions
Prin-0.079
Once-0.073
-0.072
RO-0.069
 cheered-0.069
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
ses+0.049
opsy+0.045
burn+0.044
ittens+0.043
 elbow+0.043
Neg logit contributions
-0.019
Prin-0.019
Once-0.018
 cheered-0.017
spe-0.016
Token and
Token ID290
Feature activation-2.65e+00

Pos logit contributions
ses+0.083
opsy+0.079
oa+0.076
ittens+0.076
uffy+0.074
Neg logit contributions
Prin-0.060
Once-0.055
-0.054
 cheered-0.051
By-0.051
Token chickens
Token ID25972
Feature activation-9.30e-01

Pos logit contributions
ses+0.077
opsy+0.073
ittens+0.071
oa+0.069
uffy+0.069
Neg logit contributions
Prin-0.113
-0.104
spe-0.102
By-0.102
Once-0.101
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
ses+0.036
opsy+0.033
ittens+0.033
oa+0.033
burn+0.032
Neg logit contributions
Prin-0.030
spe-0.027
-0.026
 cheered-0.026
By-0.026
Token They
Token ID1119
Feature activation-1.00e+00

Pos logit contributions
Prin+0.009
spe+0.008
By+0.008
 achieved+0.008
 cheered+0.008
Neg logit contributions
ses-0.010
oa-0.009
ittens-0.009
opsy-0.009
burn-0.008
Token also
Token ID635
Feature activation-1.46e+00

Pos logit contributions
ses+0.048
ittens+0.045
oa+0.045
burn+0.044
opsy+0.044
Neg logit contributions
Prin-0.024
 cheered-0.022
spe-0.021
Once-0.021
By-0.021
Token saw
Token ID2497
Feature activation-1.38e+00

Pos logit contributions
ses+0.065
ittens+0.062
oa+0.061
opsy+0.061
burn+0.060
Neg logit contributions
Prin-0.040
spe-0.035
 cheered-0.034
By-0.034
Once-0.033
Token tours
Token ID21284
Feature activation-1.45e-01

Pos logit contributions
Prin+0.007
Once+0.007
+0.006
By+0.006
spe+0.006
Neg logit contributions
ses-0.009
opsy-0.008
ittens-0.008
oa-0.008
sed-0.008
Token with
Token ID351
Feature activation+1.69e-01

Pos logit contributions
ses+0.007
opsy+0.006
ittens+0.006
oa+0.006
burn+0.006
Neg logit contributions
Prin-0.004
spe-0.003
By-0.003
Once-0.003
 cheered-0.003
Token her
Token ID607
Feature activation-1.59e+00

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
Once+0.005
+0.005
Neg logit contributions
ses-0.007
opsy-0.006
oa-0.006
ittens-0.006
burn-0.006
Token family
Token ID1641
Feature activation+2.37e-01

Pos logit contributions
ses+0.058
burn+0.055
oa+0.054
opsy+0.054
uf+0.053
Neg logit contributions
spe-0.048
Once-0.047
By-0.045
Prin-0.045
 cheered-0.042
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
spe+0.005
Once+0.005
+0.005
Prin+0.005
 cheered+0.004
Neg logit contributions
ses-0.012
sed-0.011
opsy-0.011
oa-0.011
ittens-0.010
Token One
Token ID1881
Feature activation-2.62e+00

Pos logit contributions
Prin+0.007
Once+0.007
By+0.006
+0.006
spe+0.006
Neg logit contributions
ses-0.013
opsy-0.013
oa-0.012
ittens-0.012
burn-0.012
Token day
Token ID1110
Feature activation-1.15e+00

Pos logit contributions
ses+0.141
oa+0.129
 elbow+0.129
sed+0.129
ittens+0.123
Neg logit contributions
Once-0.050
By-0.048
Prin-0.048
-0.046
Happy-0.045
Token,
Token ID11
Feature activation-5.57e-01

Pos logit contributions
ses+0.050
opsy+0.046
oa+0.045
ittens+0.044
burn+0.044
Neg logit contributions
Prin-0.032
By-0.029
Once-0.028
CR-0.028
-0.028
Token they
Token ID484
Feature activation-2.30e-01

Pos logit contributions
ses+0.024
opsy+0.022
oa+0.022
ittens+0.022
burn+0.022
Neg logit contributions
Prin-0.016
By-0.014
Once-0.013
spe-0.013
CR-0.013
Token went
Token ID1816
Feature activation-5.72e-01

Pos logit contributions
ses+0.009
opsy+0.009
oa+0.009
ittens+0.009
burn+0.009
Neg logit contributions
Prin-0.007
spe-0.006
By-0.006
RO-0.006
CR-0.006
Token on
Token ID319
Feature activation-4.73e-01

Pos logit contributions
ses+0.027
opsy+0.025
oa+0.025
ittens+0.025
burn+0.024
Neg logit contributions
Prin-0.014
By-0.012
Once-0.012
CR-0.012
spe-0.012
Token like
Token ID588
Feature activation-1.74e+00

Pos logit contributions
ses+0.077
opsy+0.072
oa+0.071
ittens+0.071
burn+0.069
Neg logit contributions
Prin-0.059
spe-0.053
By-0.052
Once-0.050
 cheered-0.050
Token lions
Token ID31420
Feature activation-1.03e+00

Pos logit contributions
ses+0.072
opsy+0.069
ittens+0.068
oa+0.065
burn+0.065
Neg logit contributions
Prin-0.053
spe-0.048
-0.046
 cheered-0.045
By-0.045
Token,
Token ID11
Feature activation-2.21e+00

Pos logit contributions
ses+0.045
opsy+0.043
burn+0.042
ittens+0.041
oa+0.041
Neg logit contributions
Prin-0.028
 cheered-0.025
-0.024
Once-0.024
spe-0.024
Token monkeys
Token ID26697
Feature activation-9.42e-01

Pos logit contributions
ses+0.091
opsy+0.087
ittens+0.084
oa+0.084
burn+0.082
Neg logit contributions
Prin-0.067
spe-0.060
By-0.058
Once-0.058
-0.057
Token,
Token ID11
Feature activation-2.10e+00

Pos logit contributions
ses+0.039
opsy+0.037
oa+0.035
ittens+0.035
burn+0.035
Neg logit contributions
Prin-0.028
spe-0.025
Once-0.024
-0.024
By-0.024
Token and
Token ID290
Feature activation-2.61e+00

Pos logit contributions
ses+0.082
opsy+0.079
ittens+0.077
oa+0.076
burn+0.074
Neg logit contributions
Prin-0.067
Once-0.059
By-0.059
spe-0.059
-0.058
Token birds
Token ID10087
Feature activation-8.11e-01

Pos logit contributions
ses+0.093
opsy+0.086
ittens+0.085
oa+0.085
burn+0.082
Neg logit contributions
Prin-0.092
spe-0.085
By-0.082
-0.080
Once-0.080
Token.
Token ID13
Feature activation-7.31e-01

Pos logit contributions
ses+0.026
opsy+0.024
ittens+0.024
oa+0.024
burn+0.023
Neg logit contributions
Prin-0.031
spe-0.029
By-0.028
CR-0.028
RO-0.027
Token But
Token ID887
Feature activation-6.85e-01

Pos logit contributions
ses+0.025
ittens+0.023
opsy+0.023
oa+0.023
uffy+0.022
Neg logit contributions
Prin-0.027
spe-0.025
By-0.024
 achieved-0.024
 cheered-0.023
Token Tim
Token ID5045
Feature activation-6.47e-01

Pos logit contributions
ses+0.024
opsy+0.022
oa+0.022
ittens+0.022
burn+0.021
Neg logit contributions
Prin-0.025
spe-0.023
By-0.022
 cheered-0.022
RO-0.021
Token wanted
Token ID2227
Feature activation-1.70e+00

Pos logit contributions
ses+0.027
ittens+0.026
burn+0.026
opsy+0.026
oa+0.025
Neg logit contributions
Prin-0.017
-0.017
 cheered-0.016
 achieved-0.016
 scored-0.016
Token like
Token ID588
Feature activation-1.74e+00

Pos logit contributions
ses+0.077
opsy+0.072
oa+0.071
ittens+0.071
burn+0.069
Neg logit contributions
Prin-0.058
spe-0.053
By-0.051
 cheered-0.050
Once-0.050
Token lions
Token ID31420
Feature activation-1.05e+00

Pos logit contributions
ses+0.071
opsy+0.069
ittens+0.067
oa+0.065
burn+0.064
Neg logit contributions
Prin-0.054
spe-0.049
-0.047
 cheered-0.046
By-0.046
Token,
Token ID11
Feature activation-2.20e+00

Pos logit contributions
ses+0.046
opsy+0.044
burn+0.042
ittens+0.042
oa+0.041
Neg logit contributions
Prin-0.028
 cheered-0.025
-0.025
Once-0.025
spe-0.024
Token monkeys
Token ID26697
Feature activation-9.68e-01

Pos logit contributions
ses+0.092
opsy+0.088
ittens+0.085
oa+0.085
burn+0.083
Neg logit contributions
Prin-0.065
spe-0.058
-0.056
Once-0.056
By-0.056
Token,
Token ID11
Feature activation-2.17e+00

Pos logit contributions
ses+0.040
opsy+0.038
oa+0.036
ittens+0.036
burn+0.036
Neg logit contributions
Prin-0.028
spe-0.026
-0.025
Once-0.025
By-0.025
Token and
Token ID290
Feature activation-2.60e+00

Pos logit contributions
ses+0.087
opsy+0.084
ittens+0.082
oa+0.081
uffy+0.078
Neg logit contributions
Prin-0.067
Once-0.060
-0.059
spe-0.059
By-0.059
Token birds
Token ID10087
Feature activation-8.77e-01

Pos logit contributions
ses+0.094
opsy+0.088
ittens+0.086
oa+0.086
burn+0.083
Neg logit contributions
Prin-0.091
spe-0.083
By-0.081
-0.079
 cheered-0.079
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
ses+0.029
opsy+0.027
ittens+0.027
oa+0.026
burn+0.026
Neg logit contributions
Prin-0.033
spe-0.031
By-0.030
CR-0.030
RO-0.029
Token But
Token ID887
Feature activation-2.37e-01

Pos logit contributions
ses+0.009
opsy+0.008
oa+0.008
ittens+0.008
uffy+0.007
Neg logit contributions
Prin-0.011
spe-0.010
By-0.010
 achieved-0.009
 cheered-0.009
Token Ben
Token ID3932
Feature activation-9.45e-01

Pos logit contributions
ses+0.008
opsy+0.008
oa+0.008
ittens+0.007
burn+0.007
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
RO-0.008
Happy-0.008
Token and
Token ID290
Feature activation-2.10e-01

Pos logit contributions
ses+0.037
opsy+0.034
ittens+0.034
oa+0.034
burn+0.034
Neg logit contributions
Prin-0.030
spe-0.027
By-0.026
-0.026
 cheered-0.026
Token that
Token ID326
Feature activation-8.73e-01

Pos logit contributions
Prin+0.000
By+0.000
 behold+0.000
Once+0.000
spe+0.000
Neg logit contributions
ses-0.000
ittens-0.000
burn-0.000
opsy-0.000
oa-0.000
Token day
Token ID1110
Feature activation-1.48e+00

Pos logit contributions
ses+0.035
opsy+0.033
ittens+0.032
oa+0.032
burn+0.031
Neg logit contributions
Prin-0.027
spe-0.025
By-0.024
Once-0.023
-0.023
Token on
Token ID319
Feature activation+2.96e-01

Pos logit contributions
ses+0.064
opsy+0.060
oa+0.059
ittens+0.059
burn+0.057
Neg logit contributions
Prin-0.041
By-0.037
spe-0.036
Once-0.035
CR-0.035
Token,
Token ID11
Feature activation-3.60e-01

Pos logit contributions
Prin+0.006
+0.006
Once+0.006
By+0.005
CR+0.005
Neg logit contributions
ses-0.015
burn-0.014
opsy-0.014
sed-0.013
oa-0.013
Token Fl
Token ID1610
Feature activation-1.29e+00

Pos logit contributions
ses+0.009
opsy+0.008
oa+0.008
ittens+0.008
uffy+0.008
Neg logit contributions
Prin-0.017
spe-0.016
CR-0.015
By-0.015
 cheered-0.015
Tokenuffy
Token ID15352
Feature activation-2.60e+00

Pos logit contributions
 medicines+0.023
 coat+0.023
burn+0.022
 downs+0.022
 crate+0.021
Neg logit contributions
By-0.061
CR-0.057
Prin-0.057
Once-0.055
-0.054
Token learned
Token ID4499
Feature activation+8.09e-02

Pos logit contributions
ses+0.108
ittens+0.101
opsy+0.100
burn+0.097
oa+0.097
Neg logit contributions
Prin-0.078
spe-0.070
-0.070
 achieved-0.069
By-0.069
Token that
Token ID326
Feature activation-3.06e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
Once+0.002
+0.002
Neg logit contributions
ses-0.003
opsy-0.003
ittens-0.003
oa-0.003
burn-0.003
Token sometimes
Token ID3360
Feature activation-9.65e-02

Pos logit contributions
ses+0.010
opsy+0.009
oa+0.009
ittens+0.009
burn+0.009
Neg logit contributions
Prin-0.011
spe-0.010
RO-0.010
By-0.010
 cheered-0.010
Token it
Token ID340
Feature activation-1.19e-01

Pos logit contributions
ses+0.004
opsy+0.004
ittens+0.003
oa+0.003
burn+0.003
Neg logit contributions
Prin-0.003
spe-0.003
-0.003
Once-0.003
CR-0.003
Token's
Token ID338
Feature activation-9.24e-01

Pos logit contributions
ses+0.006
opsy+0.005
ittens+0.005
oa+0.005
burn+0.005
Neg logit contributions
Prin-0.003
spe-0.003
By-0.002
Once-0.002
 cheered-0.002
Token cows
Token ID22575
Feature activation-1.16e+00

Pos logit contributions
ses+0.040
opsy+0.039
ittens+0.038
uffy+0.036
oa+0.035
Neg logit contributions
Prin-0.043
-0.040
By-0.039
spe-0.039
Once-0.039
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
ses+0.054
opsy+0.052
ittens+0.050
burn+0.049
oa+0.048
Neg logit contributions
Prin-0.027
-0.026
Once-0.024
 cheered-0.024
spe-0.023
Token pigs
Token ID22333
Feature activation-9.96e-01

Pos logit contributions
ses+0.065
opsy+0.059
ittens+0.055
uffy+0.055
oa+0.055
Neg logit contributions
Prin-0.084
Once-0.079
-0.078
By-0.075
 rect-0.075
Token,
Token ID11
Feature activation-2.09e+00

Pos logit contributions
ses+0.047
opsy+0.044
ittens+0.043
burn+0.042
oa+0.042
Neg logit contributions
Prin-0.023
-0.022
Once-0.021
spe-0.020
 cheered-0.020
Token chickens
Token ID25972
Feature activation-1.13e+00

Pos logit contributions
ses+0.074
opsy+0.069
ittens+0.066
oa+0.066
uffy+0.064
Neg logit contributions
Prin-0.076
Once-0.071
-0.070
By-0.067
 rect-0.066
Token and
Token ID290
Feature activation-2.59e+00

Pos logit contributions
ses+0.047
opsy+0.044
ittens+0.043
oa+0.042
burn+0.042
Neg logit contributions
Prin-0.033
spe-0.029
-0.029
Once-0.029
 cheered-0.028
Token horses
Token ID14260
Feature activation-1.39e+00

Pos logit contributions
ses+0.073
opsy+0.070
ittens+0.068
uffy+0.067
oa+0.066
Neg logit contributions
Prin-0.113
-0.105
By-0.102
RO-0.101
Once-0.101
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
ses+0.050
opsy+0.046
ittens+0.046
oa+0.046
burn+0.044
Neg logit contributions
Prin-0.049
spe-0.045
By-0.043
-0.042
 cheered-0.042
Token They
Token ID1119
Feature activation-1.23e+00

Pos logit contributions
ses+0.011
opsy+0.011
ittens+0.010
uffy+0.010
oa+0.010
Neg logit contributions
spe-0.011
Prin-0.011
 achieved-0.010
By-0.010
RO-0.010
Token love
Token ID1842
Feature activation-9.14e-01

Pos logit contributions
ses+0.050
ittens+0.049
oa+0.048
opsy+0.047
burn+0.046
Neg logit contributions
Prin-0.037
-0.034
 cheered-0.034
spe-0.033
By-0.033
Token to
Token ID284
Feature activation-9.47e-01

Pos logit contributions
ses+0.041
ittens+0.039
opsy+0.038
uffy+0.037
itten+0.036
Neg logit contributions
Prin-0.023
spe-0.020
Once-0.020
By-0.019
RO-0.019
Token cows
Token ID22575
Feature activation-6.69e-01

Pos logit contributions
ittens+0.058
ses+0.058
opsy+0.057
burn+0.056
uffy+0.055
Neg logit contributions
Prin-0.042
 cheered-0.037
-0.036
spe-0.035
By-0.034
Token,
Token ID11
Feature activation-2.24e+00

Pos logit contributions
ses+0.033
opsy+0.030
ittens+0.030
burn+0.029
sed+0.029
Neg logit contributions
-0.014
Prin-0.013
Once-0.013
 cheered-0.013
spe-0.012
Token pigs
Token ID22333
Feature activation-7.17e-01

Pos logit contributions
ses+0.068
opsy+0.057
oa+0.055
sed+0.055
ittens+0.053
Neg logit contributions
Prin-0.098
Once-0.091
-0.089
RO-0.087
By-0.087
Token,
Token ID11
Feature activation-2.14e+00

Pos logit contributions
ses+0.035
opsy+0.032
ittens+0.032
burn+0.031
sed+0.031
Neg logit contributions
-0.015
Prin-0.015
Once-0.014
 cheered-0.014
spe-0.013
Token chickens
Token ID25972
Feature activation-9.16e-01

Pos logit contributions
ses+0.063
opsy+0.056
oa+0.053
ittens+0.052
uffy+0.051
Neg logit contributions
Prin-0.093
Once-0.086
-0.086
By-0.083
 cheered-0.083
Token and
Token ID290
Feature activation-2.59e+00

Pos logit contributions
ses+0.039
opsy+0.036
ittens+0.035
oa+0.035
burn+0.034
Neg logit contributions
Prin-0.026
-0.024
spe-0.024
Once-0.023
 cheered-0.023
Token goats
Token ID35199
Feature activation-9.01e-01

Pos logit contributions
ses+0.073
opsy+0.070
ittens+0.067
uffy+0.066
oa+0.066
Neg logit contributions
Prin-0.113
-0.107
By-0.102
 cheered-0.101
RO-0.101
Token.
Token ID13
Feature activation+7.53e-02

Pos logit contributions
ses+0.033
opsy+0.030
ittens+0.030
oa+0.030
burn+0.029
Neg logit contributions
Prin-0.031
spe-0.029
By-0.028
-0.027
 cheered-0.027
Token
Token ID198
Feature activation-3.71e-01

Pos logit contributions
Prin+0.003
spe+0.003
 achieved+0.003
By+0.003
Happy+0.003
Neg logit contributions
ses-0.002
ittens-0.002
oa-0.002
uffy-0.002
opsy-0.002
Token
Token ID198
Feature activation+1.50e-02

Pos logit contributions
ittens+0.013
opsy+0.013
ses+0.013
uffy+0.013
oa+0.013
Neg logit contributions
Prin-0.011
spe-0.011
 rect-0.010
RO-0.010
iece-0.010
TokenOne
Token ID3198
Feature activation-2.04e+00

Pos logit contributions
Prin+0.000
spe+0.000
 triumph+0.000
RO+0.000
 cheered+0.000
Neg logit contributions
ittens-0.001
oa-0.001
opsy-0.001
ses-0.001
uffy-0.001
Token!
Token ID0
Feature activation+4.35e-01

Pos logit contributions
ses+0.023
opsy+0.022
ittens+0.021
oa+0.021
sed+0.020
Neg logit contributions
Prin-0.023
spe-0.021
-0.021
 cheered-0.020
By-0.020
Token This
Token ID770
Feature activation-1.80e+00

Pos logit contributions
Prin+0.013
+0.012
CR+0.012
spe+0.011
By+0.011
Neg logit contributions
ses-0.018
opsy-0.017
ittens-0.017
burn-0.016
oa-0.016
Token is
Token ID318
Feature activation-5.39e-01

Pos logit contributions
opsy+0.072
ses+0.071
ittens+0.070
burn+0.069
oa+0.066
Neg logit contributions
Prin-0.053
-0.053
CR-0.050
 achieved-0.050
 scored-0.049
Token none
Token ID4844
Feature activation-1.85e-01

Pos logit contributions
ses+0.017
oa+0.016
opsy+0.015
ittens+0.015
burn+0.015
Neg logit contributions
Prin-0.021
spe-0.020
By-0.019
 cheered-0.019
Happy-0.018
Token of
Token ID286
Feature activation+2.88e-01

Pos logit contributions
ses+0.009
opsy+0.008
oa+0.008
ittens+0.008
burn+0.008
Neg logit contributions
Prin-0.004
spe-0.004
-0.004
 cheered-0.004
CR-0.004
Token your
Token ID534
Feature activation-2.59e+00

Pos logit contributions
Prin+0.007
spe+0.006
Once+0.006
+0.006
CR+0.006
Neg logit contributions
ses-0.013
opsy-0.013
burn-0.012
ittens-0.012
oa-0.012
Token business
Token ID1597
Feature activation-9.91e-01

Pos logit contributions
burn+0.082
opsy+0.079
oa+0.074
ses+0.073
ittens+0.072
Neg logit contributions
Prin-0.092
spe-0.092
 achieved-0.087
CR-0.087
 scored-0.087
Token!"
Token ID2474
Feature activation-1.07e+00

Pos logit contributions
ses+0.036
opsy+0.035
ittens+0.034
oa+0.033
burn+0.032
Neg logit contributions
Prin-0.033
spe-0.032
-0.032
CR-0.030
 cheered-0.030
Token
Token ID198
Feature activation-9.77e-01

Pos logit contributions
ses+0.041
ittens+0.039
opsy+0.037
oa+0.037
 Cow+0.036
Neg logit contributions
Prin-0.034
spe-0.033
By-0.030
 rect-0.029
 achieved-0.029
Token
Token ID198
Feature activation-9.36e-01

Pos logit contributions
ses+0.046
opsy+0.043
ittens+0.043
oa+0.043
burn+0.042
Neg logit contributions
Prin-0.024
spe-0.021
By-0.020
Once-0.019
 cheered-0.019
TokenHe
Token ID1544
Feature activation-5.96e-01

Pos logit contributions
ses+0.040
oa+0.040
ittens+0.040
opsy+0.040
uffy+0.037
Neg logit contributions
Prin-0.023
spe-0.021
 rect-0.019
RO-0.018
By-0.018
Token like
Token ID588
Feature activation-1.40e+00

Pos logit contributions
ses+0.025
opsy+0.023
oa+0.023
ittens+0.023
burn+0.022
Neg logit contributions
Prin-0.024
spe-0.022
By-0.021
CR-0.021
Once-0.020
Token bugs
Token ID11316
Feature activation-7.43e-01

Pos logit contributions
ses+0.047
opsy+0.043
ittens+0.043
oa+0.043
burn+0.041
Neg logit contributions
Prin-0.052
spe-0.048
By-0.047
Once-0.046
 cheered-0.046
Token,
Token ID11
Feature activation-1.83e+00

Pos logit contributions
ses+0.030
opsy+0.028
ittens+0.027
oa+0.027
burn+0.027
Neg logit contributions
Prin-0.023
spe-0.021
-0.021
 cheered-0.020
By-0.020
Token birds
Token ID10087
Feature activation-5.12e-01

Pos logit contributions
ses+0.063
opsy+0.057
ittens+0.057
oa+0.057
burn+0.055
Neg logit contributions
Prin-0.067
spe-0.062
By-0.060
CR-0.058
Once-0.058
Token,
Token ID11
Feature activation-1.92e+00

Pos logit contributions
ses+0.021
opsy+0.020
oa+0.019
ittens+0.019
burn+0.019
Neg logit contributions
Prin-0.015
spe-0.014
-0.013
 cheered-0.013
Once-0.013
Token and
Token ID290
Feature activation-2.58e+00

Pos logit contributions
ses+0.067
opsy+0.062
ittens+0.061
oa+0.061
burn+0.059
Neg logit contributions
Prin-0.070
spe-0.064
By-0.062
Once-0.060
 cheered-0.060
Token flowers
Token ID12734
Feature activation-6.64e-01

Pos logit contributions
ses+0.078
opsy+0.068
oa+0.067
ittens+0.066
burn+0.064
Neg logit contributions
Prin-0.105
spe-0.099
By-0.097
CR-0.094
Once-0.092
Token.
Token ID13
Feature activation-2.97e-01

Pos logit contributions
ses+0.025
opsy+0.023
ittens+0.023
oa+0.023
burn+0.022
Neg logit contributions
Prin-0.022
spe-0.021
By-0.020
-0.020
 cheered-0.020
Token They
Token ID1119
Feature activation-2.94e-01

Pos logit contributions
ses+0.010
opsy+0.009
oa+0.009
ittens+0.009
sed+0.008
Neg logit contributions
Prin-0.011
spe-0.011
By-0.010
 cheered-0.010
 achieved-0.010
Token were
Token ID547
Feature activation-1.83e-01

Pos logit contributions
ses+0.011
opsy+0.011
oa+0.010
ittens+0.010
sed+0.010
Neg logit contributions
Prin-0.010
spe-0.009
CR-0.009
By-0.008
Happy-0.008
Token having
Token ID1719
Feature activation+1.87e-01

Pos logit contributions
ses+0.006
sed+0.005
opsy+0.005
oa+0.005
ittens+0.004
Neg logit contributions
Prin-0.008
spe-0.007
By-0.007
CR-0.007
Happy-0.007
Token The
Token ID383
Feature activation-1.18e+00

Pos logit contributions
ses+0.020
opsy+0.018
ittens+0.018
oa+0.018
burn+0.018
Neg logit contributions
Prin-0.012
spe-0.010
By-0.010
-0.009
 cheered-0.009
Token files
Token ID3696
Feature activation+7.05e-01

Pos logit contributions
ses+0.033
opsy+0.029
ittens+0.029
oa+0.029
burn+0.027
Neg logit contributions
Prin-0.052
spe-0.048
By-0.047
CR-0.046
 cheered-0.046
Token had
Token ID550
Feature activation-1.34e+00

Pos logit contributions
Prin+0.024
spe+0.021
RO+0.021
By+0.021
CR+0.020
Neg logit contributions
ses-0.026
oa-0.023
ittens-0.023
sed-0.023
uffy-0.022
Token colors
Token ID7577
Feature activation-9.42e-01

Pos logit contributions
ses+0.042
oa+0.037
ittens+0.037
opsy+0.035
sed+0.035
Neg logit contributions
Prin-0.053
spe-0.049
By-0.048
RO-0.047
CR-0.047
Token like
Token ID588
Feature activation-2.00e+00

Pos logit contributions
ses+0.037
opsy+0.034
oa+0.034
ittens+0.034
burn+0.032
Neg logit contributions
Prin-0.030
spe-0.028
By-0.027
-0.026
 cheered-0.026
Token red
Token ID2266
Feature activation-2.58e+00

Pos logit contributions
ses+0.072
opsy+0.069
ittens+0.066
oa+0.065
burn+0.065
Neg logit contributions
Prin-0.070
spe-0.066
-0.063
By-0.063
 cheered-0.061
Token,
Token ID11
Feature activation-1.78e+00

Pos logit contributions
ses+0.107
opsy+0.106
burn+0.097
oa+0.097
ittens+0.096
Neg logit contributions
Prin-0.075
spe-0.068
-0.067
 rect-0.066
CR-0.066
Token blue
Token ID4171
Feature activation-2.54e+00

Pos logit contributions
ses+0.055
ittens+0.050
oa+0.050
opsy+0.046
sed+0.046
Neg logit contributions
Prin-0.071
spe-0.065
By-0.065
CR-0.062
RO-0.062
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
ses+0.103
opsy+0.101
oa+0.094
ittens+0.094
burn+0.093
Neg logit contributions
Prin-0.076
spe-0.070
-0.068
 rect-0.067
Once-0.067
Token and
Token ID290
Feature activation-1.67e+00

Pos logit contributions
ses+0.049
oa+0.044
ittens+0.044
opsy+0.041
burn+0.041
Neg logit contributions
Prin-0.063
spe-0.059
By-0.057
RO-0.056
CR-0.055
Token green
Token ID4077
Feature activation-1.83e+00

Pos logit contributions
ses+0.053
oa+0.047
ittens+0.046
burn+0.044
sed+0.044
Neg logit contributions
Prin-0.067
By-0.060
spe-0.060
RO-0.058
CR-0.058
Token like
Token ID588
Feature activation-1.70e+00

Pos logit contributions
ses+0.075
opsy+0.072
oa+0.070
ittens+0.070
burn+0.068
Neg logit contributions
Prin-0.055
spe-0.049
Once-0.047
-0.047
By-0.047
Token monkeys
Token ID26697
Feature activation-8.33e-01

Pos logit contributions
ses+0.068
opsy+0.066
ittens+0.064
oa+0.061
uffy+0.061
Neg logit contributions
Prin-0.054
spe-0.049
-0.048
 cheered-0.047
Once-0.047
Token,
Token ID11
Feature activation-2.22e+00

Pos logit contributions
ses+0.035
opsy+0.033
oa+0.032
ittens+0.032
burn+0.032
Neg logit contributions
Prin-0.024
spe-0.021
-0.021
Once-0.021
 cheered-0.021
Token lions
Token ID31420
Feature activation-1.12e+00

Pos logit contributions
ses+0.090
opsy+0.087
ittens+0.084
oa+0.082
burn+0.081
Neg logit contributions
Prin-0.068
-0.061
Once-0.061
spe-0.059
 cheered-0.058
Token,
Token ID11
Feature activation-2.10e+00

Pos logit contributions
ses+0.050
opsy+0.047
burn+0.046
ittens+0.046
oa+0.045
Neg logit contributions
Prin-0.029
 cheered-0.026
Once-0.026
-0.026
spe-0.025
Token and
Token ID290
Feature activation-2.57e+00

Pos logit contributions
ses+0.086
opsy+0.083
ittens+0.080
oa+0.079
burn+0.078
Neg logit contributions
Prin-0.064
Once-0.057
-0.057
By-0.056
 cheered-0.055
Token elephants
Token ID25368
Feature activation-7.21e-01

Pos logit contributions
ses+0.093
opsy+0.086
ittens+0.085
oa+0.085
burn+0.082
Neg logit contributions
Prin-0.091
spe-0.083
By-0.080
-0.078
 cheered-0.078
Token.
Token ID13
Feature activation-2.82e-01

Pos logit contributions
ses+0.024
ittens+0.022
oa+0.022
opsy+0.022
burn+0.021
Neg logit contributions
Prin-0.027
spe-0.025
By-0.025
CR-0.024
RO-0.024
Token They
Token ID1119
Feature activation-1.14e+00

Pos logit contributions
ses+0.009
opsy+0.008
oa+0.008
ittens+0.008
uffy+0.008
Neg logit contributions
Prin-0.011
spe-0.011
RO-0.010
 achieved-0.010
By-0.010
Token liked
Token ID8288
Feature activation-9.53e-01

Pos logit contributions
ses+0.050
ittens+0.047
opsy+0.047
oa+0.046
burn+0.046
Neg logit contributions
Prin-0.032
spe-0.028
By-0.027
 cheered-0.027
Once-0.027
Token to
Token ID284
Feature activation-1.49e+00

Pos logit contributions
ses+0.042
opsy+0.039
ittens+0.039
oa+0.038
burn+0.037
Neg logit contributions
Prin-0.026
spe-0.024
By-0.022
Once-0.022
 cheered-0.022
Token like
Token ID588
Feature activation-1.63e+00

Pos logit contributions
ses+0.073
opsy+0.069
ittens+0.068
oa+0.068
burn+0.066
Neg logit contributions
Prin-0.057
spe-0.052
By-0.050
Once-0.049
 cheered-0.049
Token lions
Token ID31420
Feature activation-9.55e-01

Pos logit contributions
ses+0.067
opsy+0.064
ittens+0.063
oa+0.061
burn+0.060
Neg logit contributions
Prin-0.050
spe-0.045
-0.044
 cheered-0.043
By-0.043
Token,
Token ID11
Feature activation-2.13e+00

Pos logit contributions
ses+0.042
opsy+0.040
burn+0.039
ittens+0.038
oa+0.038
Neg logit contributions
Prin-0.025
 cheered-0.023
-0.022
Once-0.022
spe-0.022
Token monkeys
Token ID26697
Feature activation-8.60e-01

Pos logit contributions
ses+0.087
opsy+0.083
ittens+0.081
oa+0.080
burn+0.079
Neg logit contributions
Prin-0.065
spe-0.058
By-0.056
Once-0.056
-0.056
Token,
Token ID11
Feature activation-2.03e+00

Pos logit contributions
ses+0.036
opsy+0.034
oa+0.033
ittens+0.032
burn+0.032
Neg logit contributions
Prin-0.025
spe-0.022
Once-0.022
-0.022
By-0.022
Token and
Token ID290
Feature activation-2.56e+00

Pos logit contributions
ses+0.080
opsy+0.077
ittens+0.075
oa+0.074
burn+0.072
Neg logit contributions
Prin-0.065
Once-0.057
By-0.057
spe-0.057
-0.056
Token birds
Token ID10087
Feature activation-7.96e-01

Pos logit contributions
ses+0.092
opsy+0.085
ittens+0.084
oa+0.084
burn+0.081
Neg logit contributions
Prin-0.090
spe-0.083
By-0.080
-0.078
 cheered-0.078
Token.
Token ID13
Feature activation-3.19e-01

Pos logit contributions
ses+0.026
opsy+0.024
ittens+0.024
oa+0.023
burn+0.023
Neg logit contributions
Prin-0.031
spe-0.029
By-0.028
CR-0.027
RO-0.027
Token But
Token ID887
Feature activation-3.66e-01

Pos logit contributions
ses+0.010
opsy+0.009
oa+0.009
ittens+0.009
uffy+0.009
Neg logit contributions
Prin-0.013
spe-0.012
By-0.011
 achieved-0.011
RO-0.011
Token Ben
Token ID3932
Feature activation-9.52e-01

Pos logit contributions
ses+0.013
opsy+0.012
oa+0.012
ittens+0.012
burn+0.011
Neg logit contributions
Prin-0.013
spe-0.012
By-0.012
RO-0.012
Happy-0.012
Token and
Token ID290
Feature activation-4.87e-01

Pos logit contributions
ses+0.039
ittens+0.036
opsy+0.036
burn+0.036
oa+0.035
Neg logit contributions
Prin-0.028
spe-0.025
-0.025
 cheered-0.025
By-0.025
Token monkeys
Token ID26697
Feature activation-7.56e-01

Pos logit contributions
ses+0.061
opsy+0.059
ittens+0.058
oa+0.056
burn+0.055
Neg logit contributions
Prin-0.052
spe-0.048
-0.046
By-0.046
 cheered-0.046
Token,
Token ID11
Feature activation-2.20e+00

Pos logit contributions
ses+0.032
opsy+0.030
oa+0.029
ittens+0.029
burn+0.028
Neg logit contributions
Prin-0.022
spe-0.020
-0.019
Once-0.019
 cheered-0.019
Token ze
Token ID41271
Feature activation-1.20e+00

Pos logit contributions
ses+0.089
opsy+0.086
ittens+0.084
oa+0.082
uffy+0.081
Neg logit contributions
Prin-0.067
Once-0.060
-0.060
spe-0.059
 cheered-0.057
Tokenbr
Token ID1671
Feature activation-4.62e-01

Pos logit contributions
ses+0.068
opsy+0.065
oa+0.063
burn+0.063
ittens+0.063
Neg logit contributions
Prin-0.018
By-0.014
spe-0.013
Once-0.013
-0.012
Tokenas
Token ID292
Feature activation-1.24e+00

Pos logit contributions
ses+0.017
ittens+0.016
opsy+0.016
uffy+0.015
oa+0.015
Neg logit contributions
Prin-0.016
-0.015
spe-0.015
By-0.015
 cheered-0.014
Token and
Token ID290
Feature activation-2.55e+00

Pos logit contributions
ses+0.051
opsy+0.047
ittens+0.046
oa+0.046
burn+0.045
Neg logit contributions
Prin-0.037
spe-0.034
-0.033
By-0.032
Once-0.032
Token gir
Token ID37370
Feature activation-2.84e-01

Pos logit contributions
ses+0.093
opsy+0.088
ittens+0.087
oa+0.086
burn+0.083
Neg logit contributions
Prin-0.089
spe-0.081
By-0.078
-0.078
 cheered-0.077
Tokenaff
Token ID2001
Feature activation-1.30e-01

Pos logit contributions
ses+0.013
opsy+0.013
burn+0.013
oa+0.013
ittens+0.012
Neg logit contributions
Prin-0.006
spe-0.005
By-0.005
RO-0.005
 cheered-0.005
Tokenes
Token ID274
Feature activation-1.24e+00

Pos logit contributions
ses+0.005
opsy+0.004
ittens+0.004
oa+0.004
burn+0.004
Neg logit contributions
Prin-0.005
spe-0.004
By-0.004
 cheered-0.004
Once-0.004
Token.
Token ID13
Feature activation+5.13e-02

Pos logit contributions
ses+0.041
oa+0.038
opsy+0.038
ittens+0.037
burn+0.036
Neg logit contributions
Prin-0.047
spe-0.043
By-0.042
CR-0.041
RO-0.040
Token But
Token ID887
Feature activation-4.02e-02

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
RO+0.002
 cheered+0.002
Neg logit contributions
ses-0.002
opsy-0.002
ittens-0.002
oa-0.002
uffy-0.002
Token dreaming
Token ID28368
Feature activation-1.31e+00

Pos logit contributions
ses+0.031
opsy+0.028
oa+0.027
burn+0.027
ittens+0.026
Neg logit contributions
Prin-0.037
spe-0.035
By-0.034
 cheered-0.033
Once-0.032
Token about
Token ID546
Feature activation-6.20e-01

Pos logit contributions
ses+0.065
ittens+0.061
opsy+0.060
oa+0.060
burn+0.059
Neg logit contributions
Prin-0.028
spe-0.024
By-0.023
RO-0.021
Once-0.021
Token mice
Token ID10693
Feature activation+4.12e-01

Pos logit contributions
ses+0.024
ittens+0.023
opsy+0.023
oa+0.023
burn+0.022
Neg logit contributions
Prin-0.020
spe-0.018
-0.017
By-0.017
 cheered-0.017
Token or
Token ID393
Feature activation-2.05e+00

Pos logit contributions
Prin+0.015
spe+0.014
By+0.014
CR+0.013
RO+0.013
Neg logit contributions
ses-0.014
opsy-0.013
oa-0.013
ittens-0.013
burn-0.012
Token birds
Token ID10087
Feature activation-1.24e-01

Pos logit contributions
ses+0.067
ittens+0.065
opsy+0.064
oa+0.063
burn+0.061
Neg logit contributions
Prin-0.077
spe-0.070
-0.067
By-0.066
Once-0.066
Token or
Token ID393
Feature activation-2.55e+00

Pos logit contributions
ses+0.004
opsy+0.004
ittens+0.004
oa+0.004
burn+0.004
Neg logit contributions
Prin-0.005
spe-0.004
By-0.004
CR-0.004
RO-0.004
Token milk
Token ID7545
Feature activation-1.03e+00

Pos logit contributions
ses+0.083
opsy+0.079
ittens+0.079
oa+0.078
burn+0.075
Neg logit contributions
Prin-0.096
spe-0.087
By-0.085
-0.084
Once-0.083
Token.
Token ID13
Feature activation+8.29e-02

Pos logit contributions
ses+0.042
opsy+0.039
ittens+0.039
oa+0.038
sed+0.037
Neg logit contributions
Prin-0.032
spe-0.028
-0.028
 cheered-0.027
By-0.027
Token
Token ID198
Feature activation-3.46e-01

Pos logit contributions
Prin+0.003
spe+0.003
 achieved+0.003
By+0.003
 rect+0.003
Neg logit contributions
ses-0.003
oa-0.003
opsy-0.002
uffy-0.002
ittens-0.002
Token
Token ID198
Feature activation-5.24e-02

Pos logit contributions
ses+0.016
opsy+0.015
ittens+0.015
oa+0.015
uffy+0.014
Neg logit contributions
Prin-0.009
spe-0.008
By-0.007
 rect-0.007
RO-0.007
TokenSuddenly
Token ID38582
Feature activation-2.62e-01

Pos logit contributions
opsy+0.002
ittens+0.002
oa+0.002
uffy+0.002
 Cow+0.002
Neg logit contributions
 rect-0.002
Prin-0.001
spe-0.001
 scored-0.001
RO-0.001
Token had
Token ID550
Feature activation-1.34e+00

Pos logit contributions
Prin+0.024
spe+0.021
RO+0.021
By+0.021
CR+0.020
Neg logit contributions
ses-0.026
oa-0.023
ittens-0.023
sed-0.023
uffy-0.022
Token colors
Token ID7577
Feature activation-9.42e-01

Pos logit contributions
ses+0.042
oa+0.037
ittens+0.037
opsy+0.035
sed+0.035
Neg logit contributions
Prin-0.053
spe-0.049
By-0.048
RO-0.047
CR-0.047
Token like
Token ID588
Feature activation-2.00e+00

Pos logit contributions
ses+0.037
opsy+0.034
oa+0.034
ittens+0.034
burn+0.032
Neg logit contributions
Prin-0.030
spe-0.028
By-0.027
-0.026
 cheered-0.026
Token red
Token ID2266
Feature activation-2.58e+00

Pos logit contributions
ses+0.072
opsy+0.069
ittens+0.066
oa+0.065
burn+0.065
Neg logit contributions
Prin-0.070
spe-0.066
-0.063
By-0.063
 cheered-0.061
Token,
Token ID11
Feature activation-1.78e+00

Pos logit contributions
ses+0.107
opsy+0.106
burn+0.097
oa+0.097
ittens+0.096
Neg logit contributions
Prin-0.075
spe-0.068
-0.067
 rect-0.066
CR-0.066
Token blue
Token ID4171
Feature activation-2.54e+00

Pos logit contributions
ses+0.055
ittens+0.050
oa+0.050
opsy+0.046
sed+0.046
Neg logit contributions
Prin-0.071
spe-0.065
By-0.065
CR-0.062
RO-0.062
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
ses+0.103
opsy+0.101
oa+0.094
ittens+0.094
burn+0.093
Neg logit contributions
Prin-0.076
spe-0.070
-0.068
 rect-0.067
Once-0.067
Token and
Token ID290
Feature activation-1.67e+00

Pos logit contributions
ses+0.049
oa+0.044
ittens+0.044
opsy+0.041
burn+0.041
Neg logit contributions
Prin-0.063
spe-0.059
By-0.057
RO-0.056
CR-0.055
Token green
Token ID4077
Feature activation-1.83e+00

Pos logit contributions
ses+0.053
oa+0.047
ittens+0.046
burn+0.044
sed+0.044
Neg logit contributions
Prin-0.067
By-0.060
spe-0.060
RO-0.058
CR-0.058
Token.
Token ID13
Feature activation-4.84e-01

Pos logit contributions
opsy+0.074
ses+0.073
ittens+0.069
oa+0.068
burn+0.068
Neg logit contributions
Prin-0.053
spe-0.051
 rect-0.048
 cheered-0.048
CR-0.047
Token Tim
Token ID5045
Feature activation-2.32e-01

Pos logit contributions
ses+0.020
ittens+0.019
oa+0.018
opsy+0.018
uffy+0.018
Neg logit contributions
Prin-0.015
spe-0.014
By-0.013
CR-0.012
-0.012
Token the
Token ID262
Feature activation+2.89e-01

Pos logit contributions
Prin+0.001
By+0.001
Uh+0.001
CR+0.001
Crash+0.001
Neg logit contributions
burn-0.001
erry-0.001
ittens-0.001
ses-0.001
 breed-0.001
Token animals
Token ID4695
Feature activation+1.03e-01

Pos logit contributions
Prin+0.012
spe+0.011
By+0.011
CR+0.011
 cheered+0.010
Neg logit contributions
ses-0.008
ittens-0.008
opsy-0.008
oa-0.007
burn-0.007
Token.
Token ID13
Feature activation+5.62e-02

Pos logit contributions
Prin+0.003
+0.003
spe+0.003
 cheered+0.003
By+0.003
Neg logit contributions
ses-0.004
ittens-0.004
opsy-0.004
oa-0.004
burn-0.004
Token He
Token ID679
Feature activation-6.51e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
CR+0.002
Happy+0.002
Neg logit contributions
ses-0.002
ittens-0.002
opsy-0.002
oa-0.002
uffy-0.002
Token could
Token ID714
Feature activation-1.03e+00

Pos logit contributions
ses+0.029
ittens+0.027
opsy+0.027
oa+0.027
burn+0.026
Neg logit contributions
Prin-0.018
spe-0.016
By-0.016
-0.015
 cheered-0.015
Token already
Token ID1541
Feature activation-2.53e+00

Pos logit contributions
ses+0.045
ittens+0.043
oa+0.042
opsy+0.042
uffy+0.041
Neg logit contributions
Prin-0.027
Once-0.026
-0.026
By-0.025
 cheered-0.025
Token hear
Token ID3285
Feature activation-4.97e-01

Pos logit contributions
ses+0.098
oa+0.092
ittens+0.091
opsy+0.091
burn+0.087
Neg logit contributions
Prin-0.082
spe-0.076
-0.075
By-0.074
 cheered-0.073
Token the
Token ID262
Feature activation-3.54e-01

Pos logit contributions
ses+0.019
oa+0.018
opsy+0.018
ittens+0.018
burn+0.017
Neg logit contributions
Prin-0.016
spe-0.014
By-0.014
CR-0.013
Once-0.013
Token lions
Token ID31420
Feature activation-2.73e-02

Pos logit contributions
ses+0.012
opsy+0.011
ittens+0.011
oa+0.011
burn+0.010
Neg logit contributions
Prin-0.013
spe-0.012
By-0.012
Once-0.012
CR-0.012
Token roaring
Token ID43170
Feature activation-7.05e-01

Pos logit contributions
ses+0.001
opsy+0.001
ittens+0.001
oa+0.001
burn+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
 cheered-0.001
-0.001
Token and
Token ID290
Feature activation-6.55e-01

Pos logit contributions
ses+0.022
oa+0.021
ittens+0.020
opsy+0.019
burn+0.019
Neg logit contributions
Prin-0.027
By-0.025
spe-0.024
CR-0.024
Once-0.024
Token,
Token ID11
Feature activation-1.40e+00

Pos logit contributions
ses+0.029
burn+0.027
oa+0.027
ittens+0.027
opsy+0.026
Neg logit contributions
Prin-0.016
 cheered-0.016
Once-0.015
-0.015
By-0.015
Token like
Token ID588
Feature activation-1.84e+00

Pos logit contributions
ses+0.050
opsy+0.045
ittens+0.045
oa+0.045
burn+0.043
Neg logit contributions
Prin-0.049
spe-0.045
By-0.044
CR-0.044
RO-0.042
Token birds
Token ID10087
Feature activation-9.01e-01

Pos logit contributions
ses+0.069
opsy+0.066
ittens+0.065
oa+0.063
burn+0.062
Neg logit contributions
Prin-0.062
spe-0.057
By-0.055
-0.055
 cheered-0.054
Token,
Token ID11
Feature activation-2.28e+00

Pos logit contributions
ses+0.038
opsy+0.035
oa+0.035
ittens+0.034
sed+0.034
Neg logit contributions
Prin-0.026
-0.023
Once-0.023
 cheered-0.023
spe-0.022
Token dogs
Token ID6844
Feature activation-1.67e+00

Pos logit contributions
ses+0.078
opsy+0.072
ittens+0.071
oa+0.071
burn+0.068
Neg logit contributions
Prin-0.084
spe-0.078
By-0.075
CR-0.073
 cheered-0.073
Token and
Token ID290
Feature activation-2.53e+00

Pos logit contributions
ses+0.076
opsy+0.071
ittens+0.070
burn+0.069
oa+0.068
Neg logit contributions
Prin-0.043
-0.040
Once-0.039
 cheered-0.038
By-0.036
Token squirrel
Token ID33039
Feature activation-1.38e+00

Pos logit contributions
ses+0.084
opsy+0.077
ittens+0.077
oa+0.076
burn+0.073
Neg logit contributions
Prin-0.096
spe-0.088
By-0.086
-0.083
 cheered-0.083
Tokens
Token ID82
Feature activation-1.45e+00

Pos logit contributions
ses+0.062
opsy+0.057
oa+0.056
ittens+0.056
burn+0.055
Neg logit contributions
Prin-0.037
spe-0.033
By-0.031
-0.031
 cheered-0.031
Token.
Token ID13
Feature activation+8.20e-02

Pos logit contributions
ses+0.056
opsy+0.054
oa+0.053
ittens+0.053
burn+0.051
Neg logit contributions
Prin-0.045
spe-0.041
 cheered-0.040
By-0.040
Once-0.040
Token One
Token ID1881
Feature activation-2.09e+00

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
 cheered+0.002
 achieved+0.002
Neg logit contributions
ses-0.003
opsy-0.003
oa-0.003
ittens-0.003
uffy-0.003
Token day
Token ID1110
Feature activation-7.40e-01

Pos logit contributions
ses+0.103
oa+0.099
ittens+0.095
burn+0.093
 elbow+0.093
Neg logit contributions
Prin-0.045
-0.044
spe-0.043
 behold-0.041
Once-0.041
Token on
Token ID319
Feature activation+1.77e-01

Pos logit contributions
ses+0.019
sed+0.017
oa+0.016
opsy+0.016
ittens+0.016
Neg logit contributions
Prin-0.008
spe-0.007
-0.007
CR-0.007
Once-0.007
Token while
Token ID981
Feature activation-1.10e-01

Pos logit contributions
Prin+0.005
+0.004
Once+0.004
spe+0.004
By+0.004
Neg logit contributions
ses-0.008
opsy-0.008
sed-0.008
ittens-0.008
oa-0.007
Token her
Token ID607
Feature activation+5.22e-02

Pos logit contributions
ses+0.004
opsy+0.004
oa+0.004
ittens+0.004
burn+0.004
Neg logit contributions
Prin-0.004
spe-0.003
By-0.003
-0.003
Once-0.003
Token mom
Token ID1995
Feature activation+5.11e-01

Pos logit contributions
Prin+0.002
spe+0.002
+0.002
Once+0.002
By+0.002
Neg logit contributions
ses-0.002
oa-0.001
opsy-0.001
burn-0.001
ittens-0.001
Tokenmy
Token ID1820
Feature activation+2.71e-01

Pos logit contributions
+0.012
Prin+0.012
 cheered+0.012
Once+0.011
spe+0.011
Neg logit contributions
ses-0.025
opsy-0.022
oa-0.022
sed-0.022
ittens-0.021
Token finished
Token ID5201
Feature activation+1.68e+00

Pos logit contributions
+0.007
 cheered+0.006
Prin+0.006
Once+0.005
By+0.005
Neg logit contributions
ses-0.014
opsy-0.012
oa-0.012
sed-0.012
ich-0.011
Token shopping
Token ID9735
Feature activation+5.83e-01

Pos logit contributions
Prin+0.045
+0.043
spe+0.043
Once+0.041
 cheered+0.041
Neg logit contributions
ses-0.074
opsy-0.066
sed-0.064
oa-0.064
ittens-0.064
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
Prin+0.018
spe+0.017
 cheered+0.016
+0.016
By+0.016
Neg logit contributions
ses-0.024
opsy-0.022
oa-0.022
ittens-0.021
burn-0.021
Token In
Token ID554
Feature activation-1.05e-01

Pos logit contributions
Prin+0.008
spe+0.007
By+0.007
RO+0.006
 achieved+0.006
Neg logit contributions
ses-0.010
opsy-0.010
ittens-0.010
oa-0.010
uffy-0.009
Token the
Token ID262
Feature activation+6.21e-02

Pos logit contributions
ses+0.005
opsy+0.005
ittens+0.005
oa+0.005
burn+0.005
Neg logit contributions
Prin-0.002
spe-0.002
Once-0.002
By-0.002
-0.002
Token end
Token ID886
Feature activation-8.48e-01

Pos logit contributions
Prin+0.002
RO+0.002
spe+0.002
By+0.002
 cheered+0.002
Neg logit contributions
ittens-0.002
ses-0.002
burn-0.002
opsy-0.002
 coat-0.002
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
ses+0.001
opsy+0.001
oa+0.001
ittens+0.001
burn+0.001
Neg logit contributions
Prin-0.000
spe-0.000
By-0.000
CR-0.000
 cheered-0.000
Token snow
Token ID6729
Feature activation-6.77e-01

Pos logit contributions
Prin+0.006
spe+0.006
By+0.006
 cheered+0.006
RO+0.005
Neg logit contributions
ses-0.004
opsy-0.003
oa-0.003
ittens-0.003
burn-0.003
Token.
Token ID13
Feature activation+7.65e-01

Pos logit contributions
ses+0.027
oa+0.025
opsy+0.025
ittens+0.024
sed+0.024
Neg logit contributions
Prin-0.020
spe-0.019
Once-0.018
By-0.017
 cheered-0.017
Token They
Token ID1119
Feature activation+3.57e-01

Pos logit contributions
Prin+0.025
spe+0.023
By+0.022
Once+0.022
+0.022
Neg logit contributions
ses-0.029
opsy-0.027
ittens-0.027
oa-0.027
burn-0.026
Token made
Token ID925
Feature activation+1.17e+00

Pos logit contributions
Prin+0.010
 cheered+0.009
spe+0.009
+0.009
By+0.008
Neg logit contributions
ses-0.016
oa-0.015
ittens-0.015
opsy-0.015
burn-0.015
Token a
Token ID257
Feature activation+1.74e+00

Pos logit contributions
Prin+0.045
spe+0.042
By+0.041
Once+0.039
 cheered+0.039
Neg logit contributions
ses-0.039
opsy-0.035
ittens-0.035
oa-0.035
burn-0.034
Token big
Token ID1263
Feature activation+1.51e+00

Pos logit contributions
Prin+0.076
spe+0.070
CR+0.068
By+0.067
RO+0.067
Neg logit contributions
ses-0.049
opsy-0.046
ittens-0.045
burn-0.042
oa-0.042
Token snow
Token ID6729
Feature activation-2.01e-01

Pos logit contributions
Prin+0.056
spe+0.053
+0.051
 cheered+0.051
By+0.051
Neg logit contributions
ses-0.049
oa-0.045
opsy-0.045
ittens-0.044
burn-0.042
Tokenman
Token ID805
Feature activation+1.15e+00

Pos logit contributions
ses+0.008
opsy+0.007
oa+0.007
uf+0.007
ittens+0.007
Neg logit contributions
spe-0.006
Prin-0.006
By-0.005
 rect-0.005
 cheered-0.005
Token with
Token ID351
Feature activation+5.90e-01

Pos logit contributions
Prin+0.034
spe+0.031
By+0.030
CR+0.028
Once+0.028
Neg logit contributions
ses-0.048
opsy-0.045
ittens-0.044
oa-0.044
burn-0.043
Token a
Token ID257
Feature activation+6.40e-01

Pos logit contributions
Prin+0.021
spe+0.019
By+0.019
+0.018
 cheered+0.018
Neg logit contributions
ses-0.021
opsy-0.020
ittens-0.019
oa-0.019
uffy-0.019
Tokenin
Token ID259
Feature activation+2.24e-02

Pos logit contributions
Prin+0.025
By+0.025
spe+0.024
RO+0.023
 rect+0.023
Neg logit contributions
opsy-0.019
uffy-0.017
ittens-0.017
erry-0.017
oo-0.016
Token started
Token ID2067
Feature activation+2.11e-01

Pos logit contributions
Prin+0.001
spe+0.001
By+0.001
Happy+0.001
CR+0.001
Neg logit contributions
ses-0.001
opsy-0.001
ittens-0.001
oa-0.001
uffy-0.001
Token to
Token ID284
Feature activation+3.35e-01

Pos logit contributions
Prin+0.007
By+0.006
spe+0.006
RO+0.006
Happy+0.006
Neg logit contributions
ses-0.008
ittens-0.007
opsy-0.007
oa-0.007
burn-0.007
Token carry
Token ID3283
Feature activation+4.36e-01

Pos logit contributions
Prin+0.012
+0.011
spe+0.011
Once+0.011
 achieved+0.011
Neg logit contributions
ses-0.012
ittens-0.011
oa-0.011
opsy-0.011
uffy-0.010
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
Prin+0.011
spe+0.010
+0.009
By+0.009
 cheered+0.009
Neg logit contributions
ses-0.020
opsy-0.019
ittens-0.019
oa-0.019
burn-0.019
Token tw
Token ID665
Feature activation+1.86e+00

Pos logit contributions
Prin+0.064
By+0.058
spe+0.058
Once+0.057
+0.057
Neg logit contributions
ses-0.059
oa-0.055
ittens-0.054
opsy-0.053
burn-0.051
Tokenig
Token ID328
Feature activation-5.90e-01

Pos logit contributions
Prin+0.082
spe+0.076
CR+0.075
By+0.074
+0.074
Neg logit contributions
ses-0.052
oa-0.047
burn-0.042
sed-0.042
opsy-0.042
Token,
Token ID11
Feature activation+5.69e-01

Pos logit contributions
ses+0.025
oa+0.023
opsy+0.023
ittens+0.022
burn+0.022
Neg logit contributions
Prin-0.017
spe-0.016
-0.015
Once-0.015
By-0.015
Token it
Token ID340
Feature activation+8.21e-01

Pos logit contributions
Prin+0.017
spe+0.015
By+0.015
Once+0.014
Happy+0.014
Neg logit contributions
ses-0.023
opsy-0.022
oa-0.021
ittens-0.021
burn-0.021
Token was
Token ID373
Feature activation+8.75e-01

Pos logit contributions
Prin+0.030
Happy+0.030
spe+0.028
RO+0.027
By+0.027
Neg logit contributions
ses-0.027
opsy-0.026
sed-0.025
uffy-0.024
 needles-0.023
Token too
Token ID1165
Feature activation+1.04e-01

Pos logit contributions
Prin+0.030
spe+0.028
By+0.026
 cheered+0.026
Happy+0.026
Neg logit contributions
ses-0.033
opsy-0.030
ittens-0.030
oa-0.029
burn-0.029
Tokenara
Token ID3301
Feature activation-1.04e+00

Pos logit contributions
Prin+0.015
spe+0.014
RO+0.013
By+0.013
 cheered+0.013
Neg logit contributions
opsy-0.011
ses-0.010
ittens-0.010
oa-0.010
uffy-0.010
Token loved
Token ID6151
Feature activation+3.67e-01

Pos logit contributions
ittens+0.043
ses+0.042
opsy+0.041
oa+0.040
burn+0.040
Neg logit contributions
Prin-0.030
 cheered-0.028
-0.027
 achieved-0.027
CR-0.027
Token her
Token ID607
Feature activation-3.05e-01

Pos logit contributions
Prin+0.011
spe+0.010
By+0.009
Once+0.009
+0.009
Neg logit contributions
ses-0.015
opsy-0.014
ittens-0.014
oa-0.014
burn-0.013
Token velvet
Token ID47750
Feature activation-1.35e+00

Pos logit contributions
ats+0.012
ses+0.011
oa+0.011
oo+0.011
burn+0.011
Neg logit contributions
Prin-0.008
Once-0.008
-0.008
 triumph-0.007
Happy-0.007
Token dress
Token ID6576
Feature activation-1.13e+00

Pos logit contributions
ses+0.045
uf+0.041
oa+0.041
opsy+0.040
ittens+0.040
Neg logit contributions
Prin-0.045
spe-0.040
-0.040
 cheered-0.038
 again-0.037
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
ses+0.057
opsy+0.051
sed+0.050
oa+0.049
ittens+0.048
Neg logit contributions
Prin-0.027
spe-0.025
-0.025
 cheered-0.022
Once-0.021
Token It
Token ID632
Feature activation-4.86e-01

Pos logit contributions
Prin+0.045
+0.040
Once+0.039
spe+0.038
By+0.038
Neg logit contributions
ses-0.081
opsy-0.075
ittens-0.075
oa-0.075
sed-0.074
Token was
Token ID373
Feature activation-8.93e-02

Pos logit contributions
ses+0.024
ittens+0.023
opsy+0.023
oa+0.023
burn+0.022
Neg logit contributions
Prin-0.011
-0.010
spe-0.009
 cheered-0.009
Once-0.009
Token red
Token ID2266
Feature activation-6.27e-01

Pos logit contributions
ses+0.004
oa+0.003
opsy+0.003
ittens+0.003
uffy+0.003
Neg logit contributions
Prin-0.003
Once-0.003
-0.003
By-0.002
spe-0.002
Token and
Token ID290
Feature activation-1.49e-01

Pos logit contributions
opsy+0.033
ses+0.032
oa+0.031
ittens+0.030
sed+0.029
Neg logit contributions
-0.012
 of-0.012
Prin-0.010
 by-0.009
Once-0.009
Token soft
Token ID2705
Feature activation-1.07e+00

Pos logit contributions
ses+0.006
opsy+0.006
uf+0.006
oa+0.006
burn+0.006
Neg logit contributions
Prin-0.004
-0.004
 cheered-0.004
Once-0.004
By-0.004
Token wonderful
Token ID7932
Feature activation+5.97e-01

Pos logit contributions
Prin+0.024
+0.022
By+0.022
Once+0.021
 behold+0.020
Neg logit contributions
ses-0.029
ittens-0.028
oa-0.028
opsy-0.027
burn-0.027
Token taste
Token ID6938
Feature activation+2.78e-01

Pos logit contributions
Prin+0.018
 behold+0.016
spe+0.016
By+0.016
Once+0.016
Neg logit contributions
ses-0.024
oa-0.023
ittens-0.022
opsy-0.022
uffy-0.021
Token of
Token ID286
Feature activation+4.26e-01

Pos logit contributions
Prin+0.009
spe+0.008
By+0.008
RO+0.008
CR+0.008
Neg logit contributions
ses-0.010
ittens-0.010
opsy-0.010
oa-0.010
burn-0.009
Token the
Token ID262
Feature activation+4.80e-01

Pos logit contributions
Prin+0.009
 behold+0.008
Once+0.008
 triumph+0.008
 cheered+0.008
Neg logit contributions
ses-0.021
uffy-0.020
oa-0.020
ittens-0.020
opsy-0.020
Token sweet
Token ID6029
Feature activation+3.38e-01

Pos logit contributions
Prin+0.015
By+0.013
+0.013
Once+0.013
spe+0.013
Neg logit contributions
ses-0.019
oa-0.018
ittens-0.018
opsy-0.017
burn-0.017
Token apples
Token ID22514
Feature activation+1.70e+00

Pos logit contributions
Prin+0.011
+0.011
Happy+0.010
 behold+0.010
Once+0.010
Neg logit contributions
ses-0.013
oa-0.011
sed-0.011
uffy-0.011
ittens-0.011
Token and
Token ID290
Feature activation-3.68e-01

Pos logit contributions
Prin+0.056
spe+0.052
+0.050
By+0.050
 cheered+0.049
Neg logit contributions
ses-0.065
opsy-0.060
ittens-0.059
oa-0.059
burn-0.057
Token juicy
Token ID35075
Feature activation-1.97e-01

Pos logit contributions
ses+0.011
opsy+0.010
oa+0.010
ittens+0.010
burn+0.010
Neg logit contributions
Prin-0.015
spe-0.014
By-0.013
CR-0.013
Once-0.013
Token cher
Token ID21382
Feature activation+8.96e-01

Pos logit contributions
ses+0.006
opsy+0.005
oa+0.005
ittens+0.005
uffy+0.005
Neg logit contributions
Prin-0.008
spe-0.008
By-0.008
 cheered-0.008
Once-0.008
Tokenries
Token ID1678
Feature activation+1.29e+00

Pos logit contributions
Prin+0.039
spe+0.036
By+0.035
CR+0.035
Once+0.035
Neg logit contributions
ses-0.026
sed-0.021
oa-0.021
opsy-0.021
ittens-0.021
Token.
Token ID13
Feature activation-3.40e-02

Pos logit contributions
Prin+0.052
spe+0.046
By+0.045
RO+0.045
CR+0.045
Neg logit contributions
ses-0.040
opsy-0.037
ittens-0.037
oa-0.037
burn-0.036
Token expected
Token ID2938
Feature activation-3.15e-02

Pos logit contributions
Prin+0.007
spe+0.006
By+0.006
RO+0.006
 cheered+0.005
Neg logit contributions
ses-0.011
opsy-0.010
ittens-0.010
oa-0.010
burn-0.010
Token,
Token ID11
Feature activation+6.70e-01

Pos logit contributions
ses+0.001
oa+0.001
ittens+0.001
opsy+0.001
burn+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
RO-0.001
Happy-0.001
Token Mac
Token ID4100
Feature activation-2.74e-01

Pos logit contributions
Prin+0.023
spe+0.020
By+0.019
Happy+0.019
 cheered+0.019
Neg logit contributions
ses-0.026
oa-0.024
opsy-0.024
ittens-0.023
sed-0.022
Token got
Token ID1392
Feature activation+1.24e-01

Pos logit contributions
ses+0.011
opsy+0.010
ittens+0.010
oa+0.010
burn+0.010
Neg logit contributions
Prin-0.008
spe-0.007
By-0.007
RO-0.007
Once-0.007
Token stuck
Token ID7819
Feature activation-3.17e-01

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
 rect+0.005
RO+0.005
Neg logit contributions
ses-0.003
burn-0.003
 coat-0.003
 fever-0.003
opsy-0.003
Token inside
Token ID2641
Feature activation+7.63e-01

Pos logit contributions
ses+0.013
opsy+0.012
ittens+0.012
oa+0.012
burn+0.012
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
Once-0.008
 cheered-0.008
Token and
Token ID290
Feature activation+1.65e-01

Pos logit contributions
Prin+0.019
spe+0.017
By+0.016
+0.015
Once+0.015
Neg logit contributions
ses-0.036
opsy-0.034
oa-0.033
ittens-0.033
burn-0.032
Token started
Token ID2067
Feature activation+6.21e-02

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
Happy+0.004
Once+0.004
Neg logit contributions
ses-0.007
oa-0.006
opsy-0.006
ittens-0.006
sed-0.006
Token me
Token ID502
Feature activation-3.67e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
Once+0.002
 cheered+0.002
Neg logit contributions
ses-0.002
opsy-0.002
ittens-0.002
oa-0.002
burn-0.002
Tokenowing
Token ID7855
Feature activation-1.74e-01

Pos logit contributions
ses+0.014
oa+0.013
opsy+0.013
sed+0.013
ittens+0.012
Neg logit contributions
-0.013
 cheered-0.011
spe-0.011
 achieved-0.011
Once-0.010
Token to
Token ID284
Feature activation+6.55e-01

Pos logit contributions
ses+0.006
oa+0.006
burn+0.006
ittens+0.005
opsy+0.005
Neg logit contributions
Prin-0.006
By-0.006
spe-0.005
RO-0.005
CR-0.005
Token raft
Token ID31812
Feature activation-7.44e-02

Pos logit contributions
oa+0.019
ses+0.017
ittens+0.017
burn+0.017
opsy+0.016
Neg logit contributions
spe-0.020
-0.019
By-0.018
 triumph-0.018
Prin-0.018
Token was
Token ID373
Feature activation+3.89e-01

Pos logit contributions
ses+0.003
opsy+0.003
ittens+0.003
oa+0.003
burn+0.003
Neg logit contributions
Prin-0.002
spe-0.002
By-0.002
-0.002
 cheered-0.002
Token gone
Token ID3750
Feature activation+9.98e-02

Pos logit contributions
Prin+0.014
spe+0.012
By+0.012
Happy+0.012
RO+0.012
Neg logit contributions
ses-0.014
burn-0.013
opsy-0.013
ittens-0.012
sed-0.012
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
Prin+0.003
spe+0.003
+0.003
By+0.003
Once+0.003
Neg logit contributions
ses-0.004
oa-0.004
opsy-0.004
ittens-0.004
burn-0.004
Token but
Token ID475
Feature activation+2.84e-01

Pos logit contributions
Prin+0.045
spe+0.040
CR+0.039
By+0.039
Happy+0.039
Neg logit contributions
ses-0.034
opsy-0.030
ittens-0.030
oa-0.030
burn-0.030
Token he
Token ID339
Feature activation+1.92e-01

Pos logit contributions
Prin+0.011
RO+0.009
CR+0.009
 rect+0.009
Happy+0.009
Neg logit contributions
ses-0.009
opsy-0.009
oa-0.008
 Cow-0.008
 knees-0.008
Token was
Token ID373
Feature activation-1.12e-01

Pos logit contributions
Prin+0.007
spe+0.006
CR+0.006
RO+0.006
By+0.006
Neg logit contributions
ses-0.007
opsy-0.007
oa-0.006
ittens-0.006
sed-0.006
Token careful
Token ID8161
Feature activation-4.41e-02

Pos logit contributions
opsy+0.003
ses+0.003
burn+0.003
 coat+0.003
ittens+0.003
Neg logit contributions
Prin-0.004
spe-0.004
CR-0.004
 rect-0.004
RO-0.004
Token next
Token ID1306
Feature activation+1.67e-01

Pos logit contributions
ses+0.002
ittens+0.001
opsy+0.001
oa+0.001
burn+0.001
Neg logit contributions
Prin-0.002
spe-0.001
By-0.001
RO-0.001
CR-0.001
Token time
Token ID640
Feature activation+4.98e-03

Pos logit contributions
Prin+0.004
spe+0.004
By+0.004
+0.003
Once+0.003
Neg logit contributions
ses-0.008
opsy-0.007
ittens-0.007
oa-0.007
burn-0.007
Token he
Token ID339
Feature activation+5.88e-01

Pos logit contributions
Prin+0.000
spe+0.000
By+0.000
RO+0.000
Once+0.000
Neg logit contributions
ses-0.000
opsy-0.000
ittens-0.000
oa-0.000
burn-0.000
Token finish
Token ID5461
Feature activation+8.82e-01

Pos logit contributions
Prin+0.004
 behold+0.003
spe+0.003
 cheered+0.003
+0.003
Neg logit contributions
ses-0.009
ittens-0.009
opsy-0.008
oa-0.008
burn-0.008
Token the
Token ID262
Feature activation-7.76e-03

Pos logit contributions
Prin+0.021
spe+0.019
+0.017
 cheered+0.017
Once+0.017
Neg logit contributions
ses-0.042
opsy-0.040
ittens-0.039
oa-0.039
burn-0.038
Token quiz
Token ID38964
Feature activation+1.19e+00

Pos logit contributions
ses+0.000
opsy+0.000
ittens+0.000
oa+0.000
burn+0.000
Neg logit contributions
Prin-0.000
spe-0.000
By-0.000
 cheered-0.000
CR-0.000
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
Prin+0.049
By+0.045
Uh+0.045
spe+0.045
RO+0.045
Neg logit contributions
ses-0.034
oa-0.030
ittens-0.029
uffy-0.027
sed-0.027
Token They
Token ID1119
Feature activation-1.49e-01

Pos logit contributions
Prin+0.010
spe+0.010
By+0.009
 achieved+0.009
 rect+0.009
Neg logit contributions
ses-0.010
oa-0.010
ittens-0.009
opsy-0.009
uffy-0.009
Token do
Token ID466
Feature activation+2.02e-01

Pos logit contributions
ses+0.004
oa+0.004
opsy+0.004
burn+0.004
 coat+0.004
Neg logit contributions
Prin-0.006
spe-0.006
By-0.006
CR-0.006
Happy-0.005
Token not
Token ID407
Feature activation-2.03e-02

Pos logit contributions
Prin+0.008
spe+0.008
By+0.007
+0.007
Once+0.007
Neg logit contributions
ses-0.006
opsy-0.006
ittens-0.006
oa-0.006
burn-0.005
Token look
Token ID804
Feature activation+4.41e-01

Pos logit contributions
ses+0.001
opsy+0.001
burn+0.001
oa+0.001
ittens+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
CR-0.001
RO-0.001
Token at
Token ID379
Feature activation+3.53e-01

Pos logit contributions
Prin+0.016
By+0.015
Uh+0.014
spe+0.014
CR+0.014
Neg logit contributions
ses-0.015
 coat-0.014
burn-0.013
oa-0.013
opsy-0.013
Token each
Token ID1123
Feature activation-4.96e-01

Pos logit contributions
spe+0.006
Prin+0.005
 behold+0.005
 cheered+0.005
 scored+0.005
Neg logit contributions
ittens-0.019
opsy-0.018
ses-0.018
itten-0.018
burn-0.018
Token other
Token ID584
Feature activation+4.51e-01

Pos logit contributions
ses+0.019
ittens+0.018
opsy+0.018
oa+0.018
burn+0.017
Neg logit contributions
Prin-0.016
spe-0.015
By-0.014
 cheered-0.013
RO-0.013
Token
Token ID198
Feature activation+5.53e-01

Pos logit contributions
Prin+0.009
spe+0.009
 rect+0.008
By+0.008
RO+0.008
Neg logit contributions
ses-0.014
opsy-0.013
ittens-0.013
oa-0.013
uffy-0.013
TokenThe
Token ID464
Feature activation+3.53e-01

Pos logit contributions
spe+0.014
 rect+0.013
Prin+0.012
iece+0.011
 cheered+0.011
Neg logit contributions
opsy-0.023
ittens-0.023
oa-0.022
 Cow-0.021
oo-0.021
Token beetle
Token ID45489
Feature activation+5.41e-01

Pos logit contributions
Prin+0.015
spe+0.014
By+0.013
Once+0.013
+0.013
Neg logit contributions
ses-0.011
opsy-0.010
ittens-0.010
oa-0.010
burn-0.009
Token thought
Token ID1807
Feature activation+1.11e-02

Pos logit contributions
Prin+0.019
spe+0.019
Happy+0.018
RO+0.018
CR+0.017
Neg logit contributions
opsy-0.018
ses-0.016
ittens-0.016
sed-0.015
 coat-0.015
Token to
Token ID284
Feature activation+3.33e-02

Pos logit contributions
Prin+0.000
+0.000
spe+0.000
By+0.000
 cheered+0.000
Neg logit contributions
ses-0.000
oa-0.000
opsy-0.000
burn-0.000
ittens-0.000
Token itself
Token ID2346
Feature activation+5.31e-01

Pos logit contributions
Prin+0.001
 behold+0.001
+0.001
Once+0.001
By+0.001
Neg logit contributions
ses-0.001
uffy-0.001
ittens-0.001
burn-0.001
oa-0.001
Token,
Token ID11
Feature activation+6.96e-01

Pos logit contributions
Prin+0.014
+0.014
Once+0.013
spe+0.012
 cheered+0.012
Neg logit contributions
ses-0.024
ittens-0.022
oa-0.022
burn-0.022
opsy-0.022
Token "
Token ID366
Feature activation+4.28e-02

Pos logit contributions
Prin+0.022
spe+0.019
By+0.019
+0.019
Once+0.018
Neg logit contributions
ses-0.028
opsy-0.026
ittens-0.026
oa-0.026
burn-0.026
TokenI
Token ID40
Feature activation+3.26e-01

Pos logit contributions
Prin+0.001
spe+0.001
 cheered+0.001
 rect+0.001
 achieved+0.001
Neg logit contributions
opsy-0.002
burn-0.001
ses-0.001
oa-0.001
ittens-0.001
Token wonder
Token ID4240
Feature activation-2.45e-01

Pos logit contributions
Prin+0.012
spe+0.011
By+0.010
+0.010
Once+0.010
Neg logit contributions
ses-0.012
opsy-0.011
ittens-0.011
oa-0.011
burn-0.010
Token if
Token ID611
Feature activation-7.31e-01

Pos logit contributions
ses+0.010
oa+0.009
ittens+0.009
opsy+0.009
burn+0.009
Neg logit contributions
Prin-0.007
-0.007
Once-0.007
spe-0.007
 achieved-0.006
Token the
Token ID262
Feature activation-3.93e-01

Pos logit contributions
Prin+0.005
spe+0.005
By+0.005
Once+0.004
CR+0.004
Neg logit contributions
ses-0.007
opsy-0.006
oa-0.006
ittens-0.006
burn-0.006
Token soft
Token ID2705
Feature activation-8.73e-01

Pos logit contributions
ses+0.013
oa+0.012
ittens+0.011
opsy+0.011
burn+0.011
Neg logit contributions
Prin-0.015
spe-0.014
-0.014
By-0.014
 cheered-0.014
Token flour
Token ID10601
Feature activation+5.75e-01

Pos logit contributions
ses+0.028
ittens+0.027
oa+0.027
opsy+0.027
burn+0.026
Neg logit contributions
Prin-0.031
spe-0.030
 cheered-0.030
-0.029
 behold-0.029
Token was
Token ID373
Feature activation-1.09e-01

Pos logit contributions
Prin+0.015
spe+0.014
+0.014
 cheered+0.014
By+0.013
Neg logit contributions
ses-0.025
opsy-0.024
ittens-0.023
oa-0.023
burn-0.022
Token also
Token ID635
Feature activation-3.58e-01

Pos logit contributions
ses+0.004
oa+0.004
opsy+0.004
ittens+0.004
uffy+0.004
Neg logit contributions
Prin-0.004
spe-0.003
-0.003
By-0.003
Once-0.003
Token important
Token ID1593
Feature activation+3.25e-01

Pos logit contributions
ses+0.014
opsy+0.013
oa+0.013
ittens+0.013
burn+0.012
Neg logit contributions
Prin-0.011
-0.011
spe-0.011
 cheered-0.010
 achieved-0.010
Token too
Token ID1165
Feature activation-2.81e-01

Pos logit contributions
Prin+0.009
spe+0.009
+0.009
 cheered+0.009
By+0.008
Neg logit contributions
ses-0.013
opsy-0.013
ittens-0.013
burn-0.012
oa-0.012
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
ses+0.013
burn+0.012
opsy+0.012
sed+0.012
ittens+0.012
Neg logit contributions
-0.008
spe-0.007
 achieved-0.006
Prin-0.006
 cheered-0.006
Token She
Token ID1375
Feature activation+4.96e-02

Pos logit contributions
Prin+0.004
spe+0.004
By+0.003
RO+0.003
CR+0.003
Neg logit contributions
ses-0.005
opsy-0.004
ittens-0.004
oa-0.004
uffy-0.004
Token was
Token ID373
Feature activation-1.00e-01

Pos logit contributions
Prin+0.002
spe+0.001
By+0.001
CR+0.001
RO+0.001
Neg logit contributions
ses-0.002
opsy-0.002
oa-0.002
ittens-0.002
burn-0.002
Token so
Token ID523
Feature activation-4.37e-01

Pos logit contributions
ses+0.004
opsy+0.003
ittens+0.003
burn+0.003
oa+0.003
Neg logit contributions
Prin-0.004
spe-0.003
CR-0.003
RO-0.003
By-0.003
TokenDon
Token ID3987
Feature activation-7.12e-01

Pos logit contributions
burn+0.003
opsy+0.003
oa+0.003
ses+0.003
 Cow+0.003
Neg logit contributions
Prin-0.002
 rect-0.002
spe-0.002
 achieved-0.002
 behold-0.002
Token't
Token ID470
Feature activation+7.14e-01

Pos logit contributions
ses+0.019
oa+0.019
ittens+0.019
burn+0.019
uffy+0.018
Neg logit contributions
Prin-0.029
spe-0.028
 rect-0.027
 cheered-0.026
 behold-0.025
Token worry
Token ID5490
Feature activation+7.82e-01

Pos logit contributions
Prin+0.034
spe+0.032
By+0.031
CR+0.030
 cheered+0.030
Neg logit contributions
ses-0.016
opsy-0.015
burn-0.015
ittens-0.015
oa-0.014
Token,
Token ID11
Feature activation+5.01e-01

Pos logit contributions
Prin+0.020
spe+0.019
+0.019
By+0.018
Once+0.018
Neg logit contributions
ses-0.034
opsy-0.032
oa-0.031
ittens-0.031
burn-0.031
Token Tim
Token ID5045
Feature activation+1.11e-01

Pos logit contributions
Prin+0.018
spe+0.016
By+0.015
CR+0.015
 cheered+0.015
Neg logit contributions
ses-0.018
oa-0.017
opsy-0.017
ittens-0.017
burn-0.016
Tokenmy
Token ID1820
Feature activation-5.25e-01

Pos logit contributions
Prin+0.003
spe+0.003
Once+0.003
+0.003
 cheered+0.003
Neg logit contributions
ses-0.005
opsy-0.004
oa-0.004
ittens-0.004
sed-0.004
Token!
Token ID0
Feature activation+6.68e-01

Pos logit contributions
ses+0.023
ittens+0.022
opsy+0.021
oa+0.020
sed+0.020
Neg logit contributions
Prin-0.014
-0.013
spe-0.013
 cheered-0.013
CR-0.013
Token We
Token ID775
Feature activation+3.49e-01

Pos logit contributions
Prin+0.021
spe+0.019
By+0.019
Once+0.018
 cheered+0.018
Neg logit contributions
ses-0.026
opsy-0.024
ittens-0.024
oa-0.024
burn-0.023
Token will
Token ID481
Feature activation-1.22e-01

Pos logit contributions
Prin+0.014
spe+0.013
 rect+0.012
CR+0.012
By+0.012
Neg logit contributions
ses-0.011
opsy-0.010
burn-0.010
uffy-0.010
ittens-0.009
Token find
Token ID1064
Feature activation+3.80e-01

Pos logit contributions
ses+0.005
ittens+0.005
oa+0.005
itten+0.004
opsy+0.004
Neg logit contributions
-0.004
Prin-0.004
Once-0.004
By-0.004
 achieved-0.003
Token your
Token ID534
Feature activation+1.15e+00

Pos logit contributions
+0.009
Prin+0.009
By+0.009
CR+0.009
Happy+0.009
Neg logit contributions
ses-0.018
opsy-0.017
ittens-0.017
oa-0.016
uffy-0.016
Token
Token ID198
Feature activation-5.72e-01

Pos logit contributions
ses+0.005
opsy+0.005
ittens+0.005
oa+0.005
 Cow+0.005
Neg logit contributions
Prin-0.005
By-0.004
spe-0.004
CR-0.004
RO-0.004
Token
Token ID198
Feature activation-3.42e-01

Pos logit contributions
opsy+0.018
oo+0.018
ittens+0.018
 Cow+0.017
oa+0.017
Neg logit contributions
 rect-0.018
spe-0.018
 achieved-0.018
Prin-0.018
 thirteen-0.018
TokenHer
Token ID9360
Feature activation-4.95e-01

Pos logit contributions
opsy+0.010
oo+0.009
oa+0.009
ittens+0.009
 Cow+0.009
Neg logit contributions
 scored-0.012
Goal-0.012
RO-0.012
 achieved-0.012
 thirteen-0.011
Token dad
Token ID9955
Feature activation+1.73e-02

Pos logit contributions
ses+0.017
burn+0.016
ittens+0.015
oa+0.015
opsy+0.015
Neg logit contributions
spe-0.018
-0.017
Prin-0.017
Once-0.016
 cheered-0.016
Token smiled
Token ID13541
Feature activation-2.12e-01

Pos logit contributions
Prin+0.001
spe+0.000
CR+0.000
By+0.000
RO+0.000
Neg logit contributions
ses-0.001
oa-0.001
opsy-0.001
ittens-0.001
sed-0.001
Token.
Token ID13
Feature activation+3.30e-02

Pos logit contributions
ses+0.006
opsy+0.005
burn+0.005
ittens+0.005
oa+0.005
Neg logit contributions
Prin-0.009
CR-0.009
RO-0.008
spe-0.008
 behold-0.008
Token "
Token ID366
Feature activation-6.66e-01

Pos logit contributions
Prin+0.001
By+0.001
 achieved+0.001
spe+0.001
CR+0.001
Neg logit contributions
ses-0.001
oa-0.001
ittens-0.001
 Cow-0.001
opsy-0.001
TokenWe
Token ID1135
Feature activation-5.84e-01

Pos logit contributions
oa+0.021
opsy+0.021
burn+0.021
ittens+0.021
ses+0.020
Neg logit contributions
Prin-0.021
 triumph-0.019
spe-0.019
CR-0.019
RO-0.018
Token are
Token ID389
Feature activation-9.28e-01

Pos logit contributions
ses+0.022
opsy+0.020
oa+0.020
ittens+0.020
burn+0.019
Neg logit contributions
Prin-0.020
-0.019
spe-0.019
By-0.018
 cheered-0.018
Token repairing
Token ID39005
Feature activation-1.36e-01

Pos logit contributions
ses+0.028
opsy+0.025
ittens+0.025
oa+0.025
burn+0.024
Neg logit contributions
Prin-0.038
spe-0.036
By-0.035
-0.034
Once-0.034
Token the
Token ID262
Feature activation-4.81e-01

Pos logit contributions
ses+0.006
opsy+0.006
ittens+0.006
sed+0.006
burn+0.006
Neg logit contributions
Prin-0.004
-0.003
spe-0.003
 cheered-0.003
CR-0.003
Token cry
Token ID3960
Feature activation-2.21e-01

Pos logit contributions
Prin+0.033
+0.031
spe+0.030
Once+0.030
 cheered+0.029
Neg logit contributions
ses-0.032
ittens-0.030
oa-0.029
opsy-0.029
uffy-0.028
Token.
Token ID13
Feature activation+4.95e-02

Pos logit contributions
ses+0.010
opsy+0.009
oa+0.009
ittens+0.009
sed+0.009
Neg logit contributions
Prin-0.006
-0.005
Once-0.005
By-0.005
 cheered-0.005
Token Her
Token ID2332
Feature activation+1.52e-01

Pos logit contributions
Prin+0.002
spe+0.001
By+0.001
Once+0.001
+0.001
Neg logit contributions
ses-0.002
opsy-0.002
ittens-0.002
oa-0.002
burn-0.002
Token mom
Token ID1995
Feature activation+7.56e-01

Pos logit contributions
Prin+0.006
spe+0.005
By+0.005
Once+0.005
+0.005
Neg logit contributions
ses-0.005
oa-0.004
opsy-0.004
ittens-0.004
burn-0.004
Token heard
Token ID2982
Feature activation+2.43e-01

Pos logit contributions
Prin+0.020
spe+0.017
By+0.017
 cheered+0.016
Once+0.016
Neg logit contributions
ses-0.035
opsy-0.032
ittens-0.032
oa-0.032
burn-0.031
Token her
Token ID607
Feature activation+3.36e-02

Pos logit contributions
Prin+0.008
spe+0.007
By+0.007
CR+0.007
 cheered+0.007
Neg logit contributions
ses-0.009
opsy-0.009
ittens-0.008
oa-0.008
burn-0.008
Token and
Token ID290
Feature activation-8.66e-02

Pos logit contributions
+0.001
Prin+0.001
 cheered+0.001
Once+0.001
spe+0.001
Neg logit contributions
ses-0.001
opsy-0.001
oa-0.001
ittens-0.001
uffy-0.001
Token ran
Token ID4966
Feature activation-1.12e-01

Pos logit contributions
ses+0.004
opsy+0.004
oa+0.004
ittens+0.004
burn+0.004
Neg logit contributions
Prin-0.002
spe-0.002
By-0.002
CR-0.002
RO-0.002
Token outside
Token ID2354
Feature activation+4.78e-02

Pos logit contributions
ses+0.003
oa+0.003
 coat+0.003
burn+0.003
 crate+0.003
Neg logit contributions
spe-0.004
Prin-0.004
 rect-0.004
By-0.004
 behold-0.004
Token to
Token ID284
Feature activation+8.11e-02

Pos logit contributions
Prin+0.002
By+0.002
spe+0.002
RO+0.002
CR+0.002
Neg logit contributions
ses-0.001
ittens-0.001
opsy-0.001
burn-0.001
oa-0.001
Token help
Token ID1037
Feature activation+3.99e-01

Pos logit contributions
Prin+0.003
 cheered+0.002
 behold+0.002
+0.002
By+0.002
Neg logit contributions
ses-0.003
ittens-0.003
opsy-0.003
oa-0.003
burn-0.003
Token was
Token ID373
Feature activation-2.40e-01

Pos logit contributions
Prin+0.027
spe+0.025
By+0.024
 cheered+0.023
Once+0.023
Neg logit contributions
ses-0.031
opsy-0.029
ittens-0.029
oa-0.029
burn-0.028
Token that
Token ID326
Feature activation+8.46e-01

Pos logit contributions
ses+0.008
opsy+0.007
oa+0.007
ittens+0.007
burn+0.007
Neg logit contributions
Prin-0.009
spe-0.009
By-0.008
RO-0.008
 cheered-0.008
Token people
Token ID661
Feature activation+5.72e-01

Pos logit contributions
Prin+0.028
spe+0.025
By+0.024
RO+0.024
Once+0.023
Neg logit contributions
ses-0.032
opsy-0.030
oa-0.029
ittens-0.029
burn-0.028
Token should
Token ID815
Feature activation-6.78e-01

Pos logit contributions
Prin+0.018
spe+0.017
By+0.016
+0.016
 cheered+0.016
Neg logit contributions
ses-0.022
opsy-0.021
ittens-0.020
oa-0.020
burn-0.020
Token be
Token ID307
Feature activation-1.68e-01

Pos logit contributions
ses+0.025
opsy+0.023
ittens+0.023
oa+0.023
burn+0.022
Neg logit contributions
Prin-0.023
spe-0.021
By-0.021
-0.020
Once-0.020
Token careful
Token ID8161
Feature activation-2.80e-01

Pos logit contributions
ses+0.005
opsy+0.005
ittens+0.005
burn+0.005
oa+0.005
Neg logit contributions
Prin-0.007
spe-0.006
By-0.006
RO-0.006
CR-0.006
Token of
Token ID286
Feature activation+3.87e-01

Pos logit contributions
ses+0.011
opsy+0.010
ittens+0.010
oa+0.010
burn+0.010
Neg logit contributions
Prin-0.009
spe-0.008
By-0.008
RO-0.008
Once-0.008
Token things
Token ID1243
Feature activation+8.43e-01

Pos logit contributions
+0.009
Prin+0.009
spe+0.009
 achieved+0.009
 cheered+0.008
Neg logit contributions
ses-0.018
ittens-0.017
burn-0.017
opsy-0.017
oa-0.016
Token that
Token ID326
Feature activation+6.22e-02

Pos logit contributions
Prin+0.027
spe+0.025
+0.024
 cheered+0.024
By+0.024
Neg logit contributions
ses-0.033
opsy-0.031
ittens-0.031
oa-0.030
burn-0.030
Token are
Token ID389
Feature activation-2.91e-01

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
+0.002
 cheered+0.002
Neg logit contributions
ses-0.002
opsy-0.002
ittens-0.002
oa-0.002
burn-0.002
Token special
Token ID2041
Feature activation+4.10e-01

Pos logit contributions
ses+0.009
opsy+0.009
oa+0.009
ittens+0.008
burn+0.008
Neg logit contributions
Prin-0.011
spe-0.010
By-0.010
CR-0.010
RO-0.010
Token something
Token ID1223
Feature activation+5.07e-01

Pos logit contributions
Prin+0.004
spe+0.004
By+0.004
Uh+0.004
CR+0.004
Neg logit contributions
ses-0.004
oa-0.004
ittens-0.004
opsy-0.004
burn-0.004
Token new
Token ID649
Feature activation+5.88e-01

Pos logit contributions
Prin+0.018
By+0.016
spe+0.016
CR+0.016
RO+0.016
Neg logit contributions
ses-0.017
opsy-0.016
oa-0.016
ittens-0.016
burn-0.015
Token on
Token ID319
Feature activation+3.77e-01

Pos logit contributions
Prin+0.020
spe+0.019
By+0.018
 cheered+0.018
+0.018
Neg logit contributions
ses-0.022
opsy-0.020
ittens-0.020
oa-0.020
burn-0.019
Token the
Token ID262
Feature activation-2.11e-01

Pos logit contributions
Prin+0.009
spe+0.008
By+0.008
Once+0.008
 cheered+0.008
Neg logit contributions
ses-0.017
opsy-0.016
ittens-0.016
oa-0.016
burn-0.016
Token black
Token ID2042
Feature activation-1.23e+00

Pos logit contributions
ses+0.007
opsy+0.006
ittens+0.006
oa+0.006
burn+0.006
Neg logit contributions
Prin-0.008
spe-0.008
By-0.008
-0.007
Once-0.007
Tokenboard
Token ID3526
Feature activation+1.57e-01

Pos logit contributions
ses+0.046
opsy+0.043
oa+0.042
ittens+0.042
burn+0.041
Neg logit contributions
Prin-0.042
spe-0.039
By-0.037
-0.037
CR-0.037
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
Prin+0.006
RO+0.006
By+0.006
Uh+0.006
spe+0.006
Neg logit contributions
ses-0.005
ittens-0.004
oa-0.004
opsy-0.004
 coat-0.004
Token So
Token ID1406
Feature activation+1.67e-01

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
CR+0.003
 cheered+0.003
Neg logit contributions
ses-0.005
opsy-0.005
oa-0.005
ittens-0.005
burn-0.004
Token the
Token ID262
Feature activation+5.33e-01

Pos logit contributions
Prin+0.006
RO+0.005
Uh+0.005
Happy+0.005
CR+0.005
Neg logit contributions
ses-0.006
opsy-0.005
oa-0.005
ittens-0.005
 knees-0.005
Token bald
Token ID28273
Feature activation+4.07e-01

Pos logit contributions
Prin+0.019
spe+0.018
By+0.017
Once+0.017
+0.017
Neg logit contributions
ses-0.019
opsy-0.017
ittens-0.017
oa-0.017
burn-0.017
Token man
Token ID582
Feature activation+7.26e-01

Pos logit contributions
Prin+0.012
spe+0.011
By+0.010
 cheered+0.010
+0.010
Neg logit contributions
ses-0.017
opsy-0.016
burn-0.016
oa-0.016
ittens-0.016
Token the
Token ID262
Feature activation-5.62e-01

Pos logit contributions
ses+0.042
ittens+0.041
opsy+0.040
oa+0.040
burn+0.040
Neg logit contributions
Prin-0.017
spe-0.015
Once-0.015
-0.014
By-0.014
Token forest
Token ID8222
Feature activation-1.72e-01

Pos logit contributions
ses+0.020
ittens+0.018
oa+0.018
opsy+0.018
burn+0.017
Neg logit contributions
Prin-0.021
By-0.019
spe-0.019
Once-0.018
-0.018
Token,
Token ID11
Feature activation-4.92e-01

Pos logit contributions
ses+0.007
opsy+0.006
oa+0.006
ittens+0.006
burn+0.006
Neg logit contributions
Prin-0.005
spe-0.005
 cheered-0.005
By-0.005
 achieved-0.005
Token but
Token ID475
Feature activation-4.56e-01

Pos logit contributions
ses+0.016
opsy+0.015
ittens+0.015
oa+0.015
burn+0.014
Neg logit contributions
Prin-0.019
spe-0.017
By-0.017
 cheered-0.016
Once-0.016
Token he
Token ID339
Feature activation-2.27e-01

Pos logit contributions
ses+0.016
oa+0.015
opsy+0.015
 Cow+0.014
sed+0.014
Neg logit contributions
Prin-0.016
Happy-0.014
By-0.014
RO-0.014
spe-0.014
Token couldn
Token ID3521
Feature activation-1.65e+00

Pos logit contributions
ses+0.009
opsy+0.008
ittens+0.008
oa+0.008
burn+0.008
Neg logit contributions
Prin-0.007
spe-0.006
By-0.006
-0.006
Once-0.006
Token't
Token ID470
Feature activation-1.24e+00

Pos logit contributions
ses+0.064
opsy+0.059
ittens+0.059
oa+0.059
burn+0.057
Neg logit contributions
Prin-0.053
spe-0.048
-0.047
By-0.047
Once-0.046
Token climb
Token ID12080
Feature activation-5.18e-01

Pos logit contributions
ses+0.049
ittens+0.046
oa+0.046
burn+0.044
uffy+0.044
Neg logit contributions
Prin-0.040
-0.037
By-0.036
 behold-0.036
Once-0.035
Token like
Token ID588
Feature activation-1.03e+00

Pos logit contributions
ses+0.022
opsy+0.021
ittens+0.021
oa+0.020
burn+0.020
Neg logit contributions
Prin-0.015
spe-0.013
-0.013
By-0.013
Once-0.013
Token they
Token ID484
Feature activation+2.68e-01

Pos logit contributions
ses+0.045
opsy+0.042
ittens+0.041
oa+0.041
burn+0.040
Neg logit contributions
Prin-0.028
spe-0.026
-0.025
By-0.024
Once-0.024
Token did
Token ID750
Feature activation-6.15e-01

Pos logit contributions
Prin+0.006
spe+0.006
By+0.006
 cheered+0.006
+0.005
Neg logit contributions
ses-0.013
opsy-0.012
ittens-0.012
oa-0.012
burn-0.012
Token and
Token ID290
Feature activation-6.09e-02

Pos logit contributions
ses+0.037
oa+0.034
opsy+0.034
ittens+0.033
sed+0.033
Neg logit contributions
-0.018
Prin-0.018
 cheered-0.017
spe-0.016
Once-0.016
Token soft
Token ID2705
Feature activation-7.67e-01

Pos logit contributions
ses+0.002
uffy+0.002
uf+0.002
opsy+0.002
oa+0.002
Neg logit contributions
-0.002
 cheered-0.002
By-0.002
Prin-0.002
 achieved-0.002
Token.
Token ID13
Feature activation+6.88e-01

Pos logit contributions
ses+0.036
opsy+0.033
oa+0.033
ittens+0.032
uffy+0.032
Neg logit contributions
Prin-0.019
-0.018
 cheered-0.018
Once-0.016
By-0.016
Token
Token ID198
Feature activation-9.57e-04

Pos logit contributions
Prin+0.021
spe+0.018
By+0.018
 cheered+0.017
CR+0.017
Neg logit contributions
ses-0.029
ittens-0.027
oa-0.026
opsy-0.026
burn-0.025
Token
Token ID198
Feature activation+5.98e-01

Pos logit contributions
ittens+0.000
ses+0.000
opsy+0.000
uffy+0.000
oa+0.000
Neg logit contributions
Prin-0.000
spe-0.000
 rect-0.000
RO-0.000
By-0.000
TokenOne
Token ID3198
Feature activation-1.51e+00

Pos logit contributions
Prin+0.022
 cheered+0.021
 rect+0.020
spe+0.020
 triumph+0.019
Neg logit contributions
ittens-0.019
oo-0.017
ido-0.017
burn-0.016
oa-0.016
Token day
Token ID1110
Feature activation-3.83e-01

Pos logit contributions
ses+0.070
oa+0.065
sed+0.063
ittens+0.062
opsy+0.061
Neg logit contributions
Prin-0.039
-0.035
Once-0.035
By-0.035
spe-0.035
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
ittens+0.010
ses+0.009
oa+0.009
uffy+0.009
opsy+0.009
Neg logit contributions
Prin-0.017
spe-0.016
 behold-0.015
RO-0.014
By-0.014
Token a
Token ID257
Feature activation-2.91e-02

Pos logit contributions
Prin+0.007
spe+0.006
By+0.006
+0.006
 cheered+0.006
Neg logit contributions
ses-0.007
ittens-0.007
oa-0.007
opsy-0.007
burn-0.007
Token man
Token ID582
Feature activation+6.68e-01

Pos logit contributions
ses+0.001
oa+0.001
ittens+0.001
opsy+0.001
burn+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
Once-0.001
 cheered-0.001
Token comes
Token ID2058
Feature activation+8.43e-01

Pos logit contributions
Prin+0.020
spe+0.019
By+0.018
Once+0.017
 rect+0.017
Neg logit contributions
ses-0.026
opsy-0.024
oa-0.024
burn-0.024
ittens-0.023
Token strange
Token ID6283
Feature activation+1.51e-02

Pos logit contributions
oa+0.002
opsy+0.002
ses+0.002
burn+0.002
ittens+0.002
Neg logit contributions
-0.002
spe-0.002
By-0.002
Once-0.002
 triumph-0.002
Token hurt
Token ID5938
Feature activation+3.87e-01

Pos logit contributions
spe+0.001
Prin+0.001
 cheered+0.000
+0.000
 triumph+0.000
Neg logit contributions
oa-0.001
opsy-0.001
ses-0.000
ittens-0.000
burn-0.000
Token mark
Token ID1317
Feature activation+4.96e-01

Pos logit contributions
spe+0.014
Prin+0.014
+0.014
 cheered+0.013
 behold+0.013
Neg logit contributions
ses-0.012
oa-0.012
opsy-0.011
ittens-0.011
uffy-0.010
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
Prin+0.015
spe+0.013
By+0.013
+0.012
 cheered+0.012
Neg logit contributions
ses-0.021
opsy-0.019
ittens-0.019
oa-0.019
burn-0.018
Token<|endoftext|>
Token ID50256
Feature activation-3.63e-01

Pos logit contributions
ses+0.006
opsy+0.005
oa+0.005
ittens+0.005
burn+0.005
Neg logit contributions
Prin-0.004
spe-0.003
By-0.003
RO-0.003
CR-0.003
TokenDanny
Token ID45478
Feature activation-1.29e+00

Pos logit contributions
ses+0.014
opsy+0.013
ittens+0.013
oa+0.013
burn+0.012
Neg logit contributions
Prin-0.012
spe-0.011
By-0.011
CR-0.010
 cheered-0.010
Token was
Token ID373
Feature activation-1.69e-01

Pos logit contributions
ses+0.059
ittens+0.056
oa+0.054
burn+0.054
opsy+0.054
Neg logit contributions
Prin-0.033
-0.033
 cheered-0.031
spe-0.029
 achieved-0.029
Token walking
Token ID6155
Feature activation-1.93e-01

Pos logit contributions
ses+0.005
opsy+0.005
ittens+0.005
oa+0.005
burn+0.004
Neg logit contributions
Prin-0.007
spe-0.006
By-0.006
CR-0.006
RO-0.006
Token in
Token ID287
Feature activation-4.71e-01

Pos logit contributions
ses+0.007
opsy+0.006
ittens+0.006
burn+0.006
 coat+0.006
Neg logit contributions
Prin-0.007
spe-0.006
By-0.006
Uh-0.006
RO-0.006
Token the
Token ID262
Feature activation-2.46e-02

Pos logit contributions
ses+0.021
opsy+0.019
ittens+0.019
oa+0.019
burn+0.019
Neg logit contributions
Prin-0.013
spe-0.011
By-0.011
CR-0.010
RO-0.010
Token park
Token ID3952
Feature activation-4.63e-01

Pos logit contributions
ses+0.001
opsy+0.001
oa+0.001
burn+0.001
 coat+0.001
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
 cheered-0.001
RO-0.001
Token,
Token ID11
Feature activation-1.53e-02

Pos logit contributions
ses+0.001
opsy+0.001
sed+0.001
ittens+0.001
oa+0.001
Neg logit contributions
Prin-0.001
Uh-0.001
CR-0.001
RO-0.001
spe-0.001
Token waving
Token ID25849
Feature activation-1.07e+00

Pos logit contributions
ses+0.001
opsy+0.000
oa+0.000
ittens+0.000
burn+0.000
Neg logit contributions
Prin-0.001
spe-0.001
By-0.001
CR-0.001
RO-0.001
Token to
Token ID284
Feature activation-2.28e-01

Pos logit contributions
ses+0.036
opsy+0.034
 coat+0.033
oa+0.033
ittens+0.033
Neg logit contributions
Prin-0.039
spe-0.035
Uh-0.034
CR-0.034
RO-0.034
Token each
Token ID1123
Feature activation-4.87e-01

Pos logit contributions
ses+0.011
ittens+0.011
uffy+0.011
opsy+0.010
oa+0.010
Neg logit contributions
Prin-0.005
spe-0.005
 behold-0.004
 rect-0.004
By-0.004
Token other
Token ID584
Feature activation+1.01e-01

Pos logit contributions
ses+0.024
oa+0.022
ittens+0.022
opsy+0.022
sed+0.022
Neg logit contributions
Prin-0.012
-0.010
Once-0.010
spe-0.010
By-0.010
Token every
Token ID790
Feature activation-1.30e+00

Pos logit contributions
Prin+0.003
spe+0.003
By+0.003
CR+0.003
RO+0.003
Neg logit contributions
ses-0.004
opsy-0.003
oa-0.003
ittens-0.003
burn-0.003
Token day
Token ID1110
Feature activation-4.37e-01

Pos logit contributions
ses+0.054
oa+0.050
opsy+0.050
ittens+0.050
burn+0.048
Neg logit contributions
Prin-0.039
spe-0.035
By-0.034
-0.033
Once-0.033
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
ses+0.013
ittens+0.012
opsy+0.012
oa+0.012
burn+0.011
Neg logit contributions
Prin-0.018
RO-0.016
spe-0.016
Uh-0.016
CR-0.015
Token Scare
Token ID47605
Feature activation-4.58e-01

Pos logit contributions
ses+0.015
opsy+0.014
oa+0.014
ittens+0.014
burn+0.013
Neg logit contributions
Prin-0.009
By-0.008
spe-0.008
-0.008
Once-0.007
Tokencrow
Token ID47114
Feature activation-5.53e-01

Pos logit contributions
ses+0.023
ittens+0.021
opsy+0.021
oa+0.021
burn+0.021
Neg logit contributions
Prin-0.010
spe-0.009
By-0.008
-0.008
CR-0.008
Token was
Token ID373
Feature activation-5.22e-01

Pos logit contributions
ses+0.022
opsy+0.021
oa+0.020
ittens+0.020
burn+0.020
Neg logit contributions
Prin-0.017
spe-0.015
By-0.015
CR-0.014
Once-0.014
Token.
Token ID13
Feature activation+5.18e-01

Pos logit contributions
Prin+0.010
Once+0.009
+0.009
spe+0.009
 cheered+0.008
Neg logit contributions
ses-0.013
oa-0.012
ittens-0.012
opsy-0.012
sed-0.012
Token She
Token ID1375
Feature activation+4.86e-01

Pos logit contributions
Prin+0.017
spe+0.015
By+0.015
CR+0.014
 cheered+0.014
Neg logit contributions
ses-0.020
opsy-0.019
ittens-0.019
oa-0.019
burn-0.018
Token lived
Token ID5615
Feature activation-1.75e-01

Pos logit contributions
Prin+0.015
By+0.014
Once+0.013
+0.013
 cheered+0.013
Neg logit contributions
ses-0.020
opsy-0.018
ittens-0.018
oa-0.018
burn-0.018
Token in
Token ID287
Feature activation-8.84e-01

Pos logit contributions
ses+0.008
opsy+0.007
ittens+0.007
oa+0.007
burn+0.007
Neg logit contributions
Prin-0.005
spe-0.004
By-0.004
-0.004
 cheered-0.004
Token a
Token ID257
Feature activation+5.18e-02

Pos logit contributions
ses+0.034
ittens+0.032
opsy+0.031
oa+0.031
uffy+0.030
Neg logit contributions
Prin-0.030
Once-0.027
By-0.027
-0.026
Happy-0.026
Token cold
Token ID4692
Feature activation-1.68e+00

Pos logit contributions
Prin+0.002
spe+0.002
By+0.002
RO+0.002
 cheered+0.002
Neg logit contributions
ses-0.002
opsy-0.002
ittens-0.001
oa-0.001
uffy-0.001
Token place
Token ID1295
Feature activation-5.89e-01

Pos logit contributions
ses+0.073
oa+0.066
sed+0.064
ittens+0.063
opsy+0.061
Neg logit contributions
Prin-0.052
Once-0.048
spe-0.045
By-0.044
 cheered-0.043
Token with
Token ID351
Feature activation+6.90e-01

Pos logit contributions
ses+0.027
oa+0.025
ittens+0.025
opsy+0.025
burn+0.025
Neg logit contributions
Prin-0.015
spe-0.014
By-0.013
Once-0.013
 cheered-0.012
Token lots
Token ID6041
Feature activation-1.04e-02

Pos logit contributions
Prin+0.022
spe+0.020
By+0.019
Once+0.019
Happy+0.019
Neg logit contributions
ses-0.027
opsy-0.025
oa-0.025
ittens-0.025
uffy-0.024
Token of
Token ID286
Feature activation+6.49e-01

Pos logit contributions
ses+0.001
opsy+0.001
oa+0.001
ittens+0.001
burn+0.001
Neg logit contributions
Prin-0.000
spe-0.000
By-0.000
 cheered-0.000
Once-0.000
Token snow
Token ID6729
Feature activation-1.33e+00

Pos logit contributions
Prin+0.023
 cheered+0.020
RO+0.020
Happy+0.020
Once+0.019
Neg logit contributions
ses-0.024
oa-0.022
opsy-0.022
burn-0.022
ittens-0.021