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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements or numerical details

    oai_token-act-pair · gpt-3.5-turbo

    definitive statements about conditions or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Awakens
    -0.77
    ossom
    -0.73
    heny
    -0.72
     dishes
    -0.71
    wake
    -0.69
    ionics
    -0.66
     Ago
    -0.66
    purpose
    -0.63
    rique
    -0.63
    ador
    -0.63
    POSITIVE LOGITS
     negligible
    1.17
     estimated
    1.07
     computed
    0.99
     calculated
    0.99
     proportional
    0.98
     reduced
    0.98
     insignificant
    0.93
     nil
    0.93
     determined
    0.92
     exceeded
    0.91
    Act Density 0.232%

    No Known Activations