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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nin
    -0.72
    uty
    -0.67
    quit
    -0.62
    pill
    -0.62
    english
    -0.61
    TH
    -0.61
    aho
    -0.60
    oday
    -0.60
    Dialog
    -0.60
    Represent
    -0.60
    POSITIVE LOGITS
    ulate
    0.73
    ulates
    0.72
    akedown
    0.68
    ulated
    0.68
    icky
    0.68
    irus
    0.66
    esty
    0.64
     although
    0.64
    ovie
    0.63
    ulation
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.