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

    Neuronpedia

    INDEX
    Explanations

    numerical values written with the number 40

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, particularly related to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.85
    vet
    -0.78
    creen
    -0.77
    vern
    -0.73
    akening
    -0.70
    ppa
    -0.67
    fecture
    -0.64
    phis
    -0.64
    forces
    -0.63
    imei
    -0.63
    POSITIVE LOGITS
    nm
    0.86
    625
    0.82
    %-
    0.78
    %
    0.72
    dfx
    0.71
    40
    0.70
     Thieves
    0.70
    rities
    0.68
     acres
    0.68
    345
    0.67
    Act Density 0.051%

    No Known Activations