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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Year."

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĵĺ
    -0.76
    leep
    -0.76
     tremend
    -0.75
    omorphic
    -0.73
     instinct
    -0.73
     minded
    -0.73
    earch
    -0.73
     grap
    -0.72
    uggest
    -0.72
     footing
    -0.71
    POSITIVE LOGITS
    ...)
    0.95
    GB
    0.84
    shown
    0.81
    2006
    0.81
    1993
    0.78
    excluding
    0.78
    1988
    0.78
    2005
    0.77
    2009
    0.77
    pg
    0.76
    Act Density 0.164%

    No Known Activations