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

    Neuronpedia

    INDEX
    Explanations

    references to probabilities or likelihoods

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DATA
    -0.83
    Meta
    -0.81
    ILE
    -0.78
    Series
    -0.73
    Physical
    -0.71
    Hardware
    -0.69
    Nap
    -0.69
    Switch
    -0.68
    CAST
    -0.68
    Cart
    -0.68
    POSITIVE LOGITS
    pring
    0.92
    llor
    0.91
     chances
    0.87
    hift
    0.87
    ensical
    0.75
     Rouhani
    0.72
    awaru
    0.68
     abound
    0.68
     worsh
    0.67
    ¬¼
    0.67
    Act Density 0.019%

    No Known Activations