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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the name "Andy" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Andy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hips
    -0.95
    ingen
    -0.75
    maid
    -0.73
    prise
    -0.71
    llah
    -0.69
    ledged
    -0.68
    finding
    -0.67
    daq
    -0.67
    inals
    -0.66
    iotic
    -0.66
    POSITIVE LOGITS
     Dalton
    0.91
     Coul
    0.82
     Weir
    0.80
     Griffith
    0.79
     Lyons
    0.78
     Kaufman
    0.78
     Reid
    0.78
     Carroll
    0.76
     Cohen
    0.75
     Burn
    0.74
    Act Density 0.015%

    No Known Activations