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

    Neuronpedia

    INDEX
    Explanations

    locations or related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uster
    -0.81
    usters
    -0.77
    iasco
    -0.72
    lict
    -0.71
    ifer
    -0.71
    uates
    -0.69
    ividual
    -0.68
     livest
    -0.67
    urated
    -0.63
    icio
    -0.63
    POSITIVE LOGITS
    fare
    1.33
    ward
    1.23
    point
    1.15
    finding
    1.14
    points
    1.09
    WARD
    1.01
    bill
    0.99
    forward
    0.94
    bos
    0.93
    yy
    0.91
    Act Density 0.060%

    No Known Activations