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

    Neuronpedia

    INDEX
    Explanations

    dates in the format 'MM-DD'

    oai_token-act-pair · gpt-3.5-turbo

    dates formatted in a specific numerical style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olson
    -0.79
     exha
    -0.75
     reluct
    -0.73
     suspic
    -0.71
    byn
    -0.71
    anguage
    -0.69
     tremend
    -0.69
     exting
    -0.69
    culosis
    -0.66
     sensit
    -0.65
    POSITIVE LOGITS
    00
    1.10
    01
    0.88
    raction
    0.88
    -+
    0.87
    08
    0.81
    05
    0.80
    09
    0.80
    ers
    0.80
    06
    0.80
    003
    0.79
    Act Density 0.022%

    No Known Activations