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

    Neuronpedia

    INDEX
    Explanations

    references to various centers or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    over
    -0.17
    ora
    -0.17
    arten
    -0.17
    oret
    -0.17
    soever
    -0.16
    ency
    -0.16
    vat
    -0.16
    ALCHEMY
    -0.16
    /her
    -0.16
    ette
    -0.16
    POSITIVE LOGITS
    pieces
    0.26
    ial
    0.19
    fold
    0.18
    lain
    0.18
    ted
    0.17
    ennial
    0.17
    most
    0.17
    pulse
    0.16
    ing
    0.16
    prises
    0.16
    Act Density 0.047%

    No Known Activations