INDEX
Explanations
words related to legal sentences or judgments
repeated mentions of the word "sentence."
New Auto-Interp
Negative Logits
BLIC
-0.84
cler
-0.79
RIS
-0.76
ichita
-0.70
atinum
-0.69
Prin
-0.69
OPS
-0.69
rists
-0.68
sie
-0.67
Blooming
-0.66
POSITIVE LOGITS
sentences
1.23
sentence
1.16
uttered
0.90
boat
0.80
forestation
0.78
ishment
0.77
©¶æ
0.74
summ
0.72
paragraphs
0.72
poon
0.72
Activations Density 0.008%