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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or functions in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istically
    -0.75
    ality
    -0.73
    ime
    -0.71
    jas
    -0.68
    thia
    -0.67
    ive
    -0.65
    ton
    -0.64
    ouch
    -0.64
    anche
    -0.64
     pigeon
    -0.63
    POSITIVE LOGITS
    frac
    0.98
     $$
    0.85
     [|
    0.80
    ÏĦ
    0.77
    >(
    0.76
    displayText
    0.76
    enegger
    0.76
    MIC
    0.72
    λ
    0.70
    adr
    0.70
    Act Density 0.020%

    No Known Activations