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

    Neuronpedia

    INDEX
    Explanations

    statements expressing confidence or conjecture

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    avenport
    -0.07
    /downloads
    -0.07
    anel
    -0.06
    imedia
    -0.06
    opens
    -0.06
    ss
    -0.06
    MainFrame
    -0.06
    .au
    -0.06
    ÑģÑĮ
    -0.06
    imiento
    -0.06
    POSITIVE LOGITS
    antha
    0.07
    moth
    0.07
    anca
    0.07
    quot
    0.07
    yen
    0.06
    cly
    0.06
    اÙĤ
    0.06
    vise
    0.06
    çļĦäºĭ
    0.06
    вÑĸ
    0.06
    Act Density 0.041%

    No Known Activations