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

    Neuronpedia

    INDEX
    Explanations

    words related to borrowing or loans

    oai_token-act-pair · gpt-3.5-turbo

    words related to labor and labor unions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.84
    erity
    -0.75
    HER
    -0.73
    paio
    -0.72
    emaker
    -0.70
    erva
    -0.70
    hiba
    -0.68
    jriwal
    -0.67
    idious
    -0.66
    ery
    -0.64
    POSITIVE LOGITS
    hood
    1.20
    bor
    0.84
    rowing
    0.80
     Gw
    0.73
    rower
    0.72
    neau
    0.71
    theless
    0.70
    bour
    0.70
    ing
    0.70
    izon
    0.68
    Act Density 0.049%

    No Known Activations