Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     isChecked
    -0.07
     colonies
    -0.07
     professional
    -0.07
    道德
    -0.07
    يمن
    -0.07
     ø
    -0.07
    ropolitan
    -0.07
    fname
    -0.07
     בעיר
    -0.07
     Cuisine
    -0.07
    POSITIVE LOGITS
    ❅
    0.08
    Mix
    0.08
     =>
↵
    0.07
     Hub
    0.07
     MIX
    0.06
     units
    0.06
     unm
    0.06
     teamed
    0.06
     çer
    0.06
     במהל
    0.06
    Act Density 0.867%

    No Known Activations