INDEX
Explanations
This neuron detects mentions of the protein "fibrinogen" (including its split sub-tokens).
New Auto-Interp
Negative Logits
MMC
-0.07
Anh
-0.07
member
-0.06
Kür
-0.06
прив
-0.06
priv
-0.06
LV
-0.06
stars
-0.06
.Ship
-0.06
ody
-0.06
POSITIVE LOGITS
eson
0.07
Toolbox
0.07
ยก
0.07
oglobin
0.07
Limited
0.07
orgán
0.06
!"↵↵
0.06
.axis
0.06
Connecting
0.06
特
0.06
Activations Density 0.000%