INDEX
Explanations
specific phonetic patterns in words, particularly those containing "iph," "aim," and "app."
New Auto-Interp
Negative Logits
çµ
-0.15
ABS
-0.15
Ub
-0.15
alc
-0.15
urette
-0.14
aton
-0.14
ieber
-0.14
év
-0.14
deniz
-0.14
concent
-0.14
POSITIVE LOGITS
atchewan
0.22
.amazonaws
0.17
-serif
0.16
Vectorizer
0.15
oÄŁ
0.15
Mask
0.15
çŃĭ
0.15
ãĥ«ãĥĪ
0.14
Scenes
0.14
imus
0.14
Activations Density 0.099%