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

    Neuronpedia

    INDEX
    Explanations

    exceptions to rules or general trends

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exceptions and deviations from rules or norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cart
    -0.65
    went
    -0.64
    DCS
    -0.64
     ancest
    -0.61
     courier
    -0.61
     mathemat
    -0.60
    phalt
    -0.60
     Tycoon
    -0.60
     neighb
    -0.60
    raph
    -0.60
    POSITIVE LOGITS
    perty
    0.86
    backs
    0.83
    aneous
    0.81
    Reviewer
    0.79
     exceptions
    0.77
    ality
    0.75
    alties
    0.74
    ishly
    0.74
    aux
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.71
    Act Density 0.021%

    No Known Activations