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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific numerical totals

    oai_token-act-pair · gpt-3.5-turbo

    references to totals or aggregate values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maid
    -0.80
    heid
    -0.73
    pher
    -0.71
     Racer
    -0.70
    ©¶æ
    -0.67
    lyn
    -0.66
    rir
    -0.64
     defe
    -0.64
    mare
    -0.64
    hops
    -0.63
    POSITIVE LOGITS
    itarian
    1.00
     totals
    0.80
     Estimated
    0.77
     Eclipse
    0.71
    GV
    0.70
    population
    0.69
     amount
    0.68
    itar
    0.67
    catentry
    0.67
    izen
    0.66
    Act Density 0.022%

    No Known Activations