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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iband
    -0.69
    irtual
    -0.67
    edge
    -0.64
    worth
    -0.64
    ango
    -0.63
    uren
    -0.63
    mentation
    -0.62
    anca
    -0.61
    ledge
    -0.60
    ickr
    -0.60
    POSITIVE LOGITS
    -+-+
    0.72
    Ļ½
    0.70
     "$:/
    0.67
    Tokens
    0.66
    ''.
    0.66
    Secretary
    0.63
    cooked
    0.63
    姫
    0.63
    (-
    0.61
    rates
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.