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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "exception" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exceptions or deviations from a rule

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ching
    -0.63
    DCS
    -0.63
     Carth
    -0.61
     mathemat
    -0.60
     courier
    -0.59
     pestic
    -0.58
    raph
    -0.58
     nanop
    -0.58
     ox
    -0.58
     opio
    -0.57
    POSITIVE LOGITS
    ional
    0.89
    als
    0.88
    arily
    0.87
    perty
    0.85
    ĸļ
    0.83
    ality
    0.80
    alties
    0.76
    aux
    0.76
    itably
    0.76
    izzle
    0.75
    Act Density 0.035%

    No Known Activations