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

    Neuronpedia

    INDEX
    Explanations

    numbers related to age or quantity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 40 followed by a unit or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vet
    -0.77
    creen
    -0.75
    theless
    -0.74
    veyard
    -0.73
    vern
    -0.72
    akening
    -0.67
    imei
    -0.67
     quir
    -0.65
    ĵĺ
    -0.65
    ateurs
    -0.64
    POSITIVE LOGITS
    %-
    0.86
    625
    0.84
    nm
    0.80
    %
    0.77
    40
    0.72
    mph
    0.72
     acres
    0.71
    ACP
    0.70
    345
    0.70
    dfx
    0.69
    Act Density 0.046%

    No Known Activations