INDEX
Explanations
mentions of the word "Brow" or its variations, possibly related to a specific location or context
New Auto-Interp
Negative Logits
s
-0.21
iom
-0.19
nos
-0.16
enade
-0.15
aison
-0.15
ianne
-0.15
zh
-0.14
ueil
-0.14
tongues
-0.14
nop
-0.14
POSITIVE LOGITS
ning
0.22
icz
0.21
NING
0.19
beat
0.19
ns
0.19
ccoli
0.18
der
0.17
æ¯Ľ
0.17
nton
0.17
intree
0.16
Activations Density 0.004%