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

    Neuronpedia

    INDEX
    Explanations

    numeric ratings

    oai_token-act-pair · gpt-3.5-turbo

    ratings and numerical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     \"
    -0.59
    rious
    -0.59
    edly
    -0.57
     grave
    -0.57
    igators
    -0.56
     undo
    -0.56
    ammad
    -0.55
    axe
    -0.52
    emort
    -0.52
    ré
    -0.52
    POSITIVE LOGITS
    /,
    0.84
     alike
    0.76
    depending
    0.76
    senal
    0.76
     Generic
    0.75
    /)
    0.73
     respectively
    0.73
    tainment
    0.67
    sembly
    0.67
     combo
    0.65
    Act Density 0.339%

    No Known Activations