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

    Neuronpedia

    INDEX
    Explanations

    information about various subjects or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a wide variety of topics or issues addressed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faced
    -0.77
    tailed
    -0.73
    quote
    -0.72
    wick
    -0.70
    ense
    -0.70
    lyak
    -0.69
    iple
    -0.69
    Guide
    -0.67
    mask
    -0.67
    Study
    -0.66
    POSITIVE LOGITS
     afar
    1.12
     scratch
    0.73
     cradle
    0.72
     whence
    0.67
     either
    0.66
     kindergarten
    0.65
     anywhere
    0.64
     Juda
    0.64
     across
    0.63
     everywhere
    0.62
    Act Density 0.073%

    No Known Activations