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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    é¾
    -0.76
     anecd
    -0.74
    soDeliveryDate
    -0.74
    ials
    -0.74
     Stream
    -0.71
     Tribunal
    -0.69
     Peb
    -0.68
     Bullets
    -0.65
     inacc
    -0.64
     behavi
    -0.64
    POSITIVE LOGITS
    xon
    0.82
    rencies
    0.70
    evil
    0.70
    âĢİ
    0.68
    bash
    0.68
    rero
    0.68
    ordering
    0.66
    ffect
    0.65
    pper
    0.65
    untu
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.