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

    Neuronpedia

    INDEX
    Explanations

    words related to ratings and evaluations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ratings and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aina
    -0.81
    umi
    -0.78
    amar
    -0.78
    auga
    -0.75
    inis
    -0.69
    antis
    -0.66
    aki
    -0.66
    ippi
    -0.66
     undone
    -0.66
    unta
    -0.64
    POSITIVE LOGITS
    senal
    0.96
    xual
    0.84
    mble
    0.77
    zinski
    0.75
    ration
    0.73
    itual
    0.71
    rated
    0.70
    rating
    0.70
     Quit
    0.70
     ..............
    0.68
    Act Density 0.021%

    No Known Activations