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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases indicating potential or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĥÏĦ
    -0.14
    ÃŃny
    -0.14
    گز
    -0.14
    åIJĪæł¼
    -0.14
    uls
    -0.14
    amps
    -0.13
    esters
    -0.13
     Vict
    -0.13
    enty
    -0.13
    neutral
    -0.13
    POSITIVE LOGITS
    Rnd
    0.15
    导èĩ´
    0.14
    Dup
    0.14
    awl
    0.14
    ãģ³
    0.14
    lav
    0.13
    coma
    0.13
    ruk
    0.13
     results
    0.13
    격
    0.13
    Act Density 0.364%

    No Known Activations