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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    -mm
    -0.07
    Þ
    -0.07
    -0.07
    OnClick
    -0.07
     resting
    -0.06
     sj
    -0.06
    ⤺
    -0.06
    .OutputStream
    -0.06
    	it
    -0.06
    本质上
    -0.06
    POSITIVE LOGITS
    .touches
    0.07
     betrayal
    0.07
     modifications
    0.07
     ноч
    0.07
    _mul
    0.07
    ńsk
    0.07
    lace
    0.07
    ודי
    0.07
    _params
    0.07
    _limit
    0.07
    Act Density 0.061%

    No Known Activations