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

    Neuronpedia

    INDEX
    Explanations

    questions and references to fun or engaging content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avit
    -0.17
    aversable
    -0.16
    رش
    -0.15
    athe
    -0.15
    washer
    -0.15
    vida
    -0.14
    lichkeit
    -0.14
    Äħż
    -0.14
    ocs
    -0.13
    meer
    -0.13
    POSITIVE LOGITS
    asc
    0.15
    ully
    0.15
    argv
    0.14
    subst
    0.14
    idis
    0.14
    Ĭ
    0.14
    anto
    0.14
    ocr
    0.13
     Mö
    0.13
    ιλο
    0.13
    Act Density 0.002%

    No Known Activations