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

    Neuronpedia

    INDEX
    Explanations

    times expressed in a specific format, possibly related to schedules or programming

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly timestamps and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.92
    rison
    -0.67
    xon
    -0.66
    heid
    -0.66
     Flavoring
    -0.65
    uyomi
    -0.64
    lier
    -0.62
    ppelin
    -0.62
    draw
    -0.61
    itude
    -0.61
    POSITIVE LOGITS
    dfx
    1.16
    ovember
    0.84
    arious
    0.81
    asted
    0.78
    00
    0.78
    ULT
    0.76
    eenth
    0.76
    329
    0.76
    OTE
    0.75
    rieve
    0.74
    Act Density 0.029%

    No Known Activations