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

    Neuronpedia

    INDEX
    Explanations

    numbers with colons

    oai_token-act-pair · gpt-3.5-turbo

    colons and their usage in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hett
    -0.74
     behavi
    -0.73
    dinand
    -0.72
    ivable
    -0.71
    Reilly
    -0.71
    onna
    -0.69
    eston
    -0.69
    estones
    -0.68
    GoldMagikarp
    -0.68
    aston
    -0.67
    POSITIVE LOGITS
    hover
    0.95
    cv
    0.82
     Logged
    0.78
     +#
    0.75
     {}
    0.74
    flags
    0.74
     {:
    0.72
    param
    0.72
    href
    0.72
    export
    0.71
    Act Density 0.068%

    No Known Activations