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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric identifiers, specifically numerical codes or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    drawn
    -0.79
    estine
    -0.77
    esan
    -0.71
    asts
    -0.71
    aned
    -0.69
    mac
    -0.68
    fman
    -0.68
    loaded
    -0.68
    auri
    -0.68
    soDeliveryDate
    -0.67
    POSITIVE LOGITS
    011
    0.93
    005
    0.93
    003
    0.91
    004
    0.90
    ĸļ
    0.89
    009
    0.88
    018
    0.87
    008
    0.87
    0002
    0.85
    006
    0.85
    Act Density 0.010%

    No Known Activations