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

    Neuronpedia

    INDEX
    Explanations

    keywords related to theoretical concepts or models

    oai_token-act-pair · gpt-3.5-turbo

    terms related to theoretical concepts and models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    win
    -0.81
    ards
    -0.75
    guard
    -0.74
     Cele
    -0.73
    guards
    -0.73
    words
    -0.69
    worthy
    -0.69
    wyn
    -0.69
    lest
    -0.68
    velt
    -0.68
    POSITIVE LOGITS
     physicist
    1.03
     physicists
    0.97
     theoretical
    0.78
    ulously
    0.73
     hypot
    0.73
     explor
    0.73
    ity
    0.71
    istically
    0.69
     extrap
    0.69
     feasibility
    0.69
    Act Density 0.028%

    No Known Activations