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

    Neuronpedia

    INDEX
    Explanations

    instances where exceptions are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to exceptions or specific cases in a discussion or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raph
    -0.69
    DCS
    -0.66
     nanop
    -0.65
    riz
    -0.62
    ching
    -0.62
    eton
    -0.62
     cart
    -0.62
    roph
    -0.61
     opio
    -0.61
     vengeance
    -0.61
    POSITIVE LOGITS
    perty
    0.91
    Reviewer
    0.89
    backs
    0.80
    aneous
    0.77
    ishly
    0.74
     exceptions
    0.74
     "$:/
    0.73
    ordinary
    0.72
    ality
    0.72
    arily
    0.72
    Act Density 0.021%

    No Known Activations