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

    Neuronpedia

    INDEX
    Explanations

    numerical values represented as two-digit pairs

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with specific categories or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.86
    iday
    -0.80
    ishing
    -0.76
    igating
    -0.75
    igators
    -0.75
    iped
    -0.74
    ary
    -0.73
    ential
    -0.72
    ition
    -0.71
    aries
    -0.68
    POSITIVE LOGITS
    teenth
    0.86
    393
    0.82
    ptive
    0.81
    UTH
    0.77
    cffff
    0.76
     satell
    0.74
    LECT
    0.73
    00
    0.73
    stasy
    0.72
    ongyang
    0.71
    Act Density 0.065%

    No Known Activations