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

    Neuronpedia

    INDEX
    Explanations

    phrases related to odds and probabilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify probabilities and odds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.82
    artney
    -0.80
    zyk
    -0.78
    ined
    -0.77
    Ô
    -0.72
    emis
    -0.69
    iners
    -0.69
    arta
    -0.68
    hetamine
    -0.67
    ovie
    -0.67
    POSITIVE LOGITS
    llor
    1.11
     ratio
    0.88
     ratios
    0.77
     occurrence
    0.75
     probability
    0.74
    busters
    0.70
     odds
    0.70
    finding
    0.69
    worthiness
    0.67
     density
    0.67
    Act Density 0.051%

    No Known Activations