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

    Neuronpedia

    INDEX
    Explanations

    expressions related to variation or change in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ister
    -0.17
    iras
    -0.16
    ses
    -0.16
    iliz
    -0.16
    ent
    -0.15
    erior
    -0.15
    k
    -0.14
    aviour
    -0.14
    eding
    -0.14
    sie
    -0.14
    POSITIVE LOGITS
    degrees
    0.17
    ERTICAL
    0.17
    ulence
    0.15
    ÑĢоÑī
    0.15
    æĭ¼
    0.15
    intl
    0.15
    ulent
    0.14
    rous
    0.14
     degrees
    0.14
    ncy
    0.14
    Act Density 0.057%

    No Known Activations