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

    Neuronpedia

    INDEX
    Explanations

    connections and interactions between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.17
    avers
    -0.15
    strom
    -0.14
    izr
    -0.14
    strup
    -0.14
    ador
    -0.14
    ована
    -0.13
    intl
    -0.13
    ford
    -0.13
    -ÑĤо
    -0.13
    POSITIVE LOGITS
    à¹Ģà¸Ĭ
    0.17
     Monster
    0.16
    KN
    0.16
    zcze
    0.15
    à¤ł
    0.15
    icut
    0.15
    gen
    0.15
    Monster
    0.14
    piel
    0.14
    annon
    0.14
    Act Density 0.140%

    No Known Activations