INDEX
Explanations
terms related to the brain and its functions
New Auto-Interp
Negative Logits
tti
-0.18
gue
-0.16
ypse
-0.15
iband
-0.15
uator
-0.15
mlin
-0.15
tür
-0.15
tica
-0.14
çľī
-0.14
llum
-0.14
POSITIVE LOGITS
stem
0.35
iac
0.33
wave
0.32
waves
0.31
washing
0.30
child
0.30
storms
0.29
power
0.29
storm
0.28
dead
0.24
Activations Density 0.015%