INDEX
Explanations
references to cartoons
instances of the word "cartoon" in relation to various topics
New Auto-Interp
Negative Logits
acia
-0.71
opio
-0.71
atches
-0.67
statement
-0.65
CI
-0.65
Sov
-0.64
iott
-0.64
pta
-0.63
Availability
-0.63
ĪĴ
-0.62
POSITIVE LOGITS
ishly
1.25
ists
1.10
ist
1.06
ish
0.99
depicting
0.99
cartoons
0.98
istic
0.98
drawings
0.96
istically
0.95
eer
0.95
Activations Density 0.036%