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

    Neuronpedia

    INDEX
    Explanations

    active verbs and verbs that indicate change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дон
    -0.17
     ******************************************************************************↵
    -0.16
    FromBody
    -0.15
    Äįek
    -0.14
    plier
    -0.14
     RequestOptions
    -0.14
    endor
    -0.13
    atoi
    -0.13
    astos
    -0.13
    uese
    -0.13
    POSITIVE LOGITS
    [s
    0.20
    es
    0.19
    LIK
    0.17
    ses
    0.17
    ssp
    0.17
    ÌĨ
    0.16
    swith
    0.16
    olor
    0.16
    sto
    0.15
    ws
    0.15
    Act Density 0.195%

    No Known Activations