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

    Neuronpedia

    INDEX
    Explanations

    instances of quotation marks indicating dialogue or notable quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UDA
    -0.17
    onia
    -0.16
    енко
    -0.15
    ington
    -0.15
    ignon
    -0.15
    bis
    -0.14
     ORD
    -0.14
    /view
    -0.14
    chez
    -0.14
    ORD
    -0.14
    POSITIVE LOGITS
    -prepend
    0.15
    -anchor
    0.14
    ustralian
    0.14
    sak
    0.14
    attle
    0.14
    BuilderInterface
    0.13
    ána
    0.13
    oty
    0.13
    hin
    0.13
    raries
    0.13
    Act Density 0.063%

    No Known Activations