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

    Neuronpedia

    INDEX
    Explanations

    references to data structure entries and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovich
    -0.15
     forget
    -0.15
     radix
    -0.14
    adin
    -0.14
    orro
    -0.14
     Vital
    -0.14
    ongo
    -0.14
    /vnd
    -0.14
     reap
    -0.14
     Forget
    -0.14
    POSITIVE LOGITS
    erdale
    0.15
    onis
    0.15
    æ
    0.15
     VÅ¡ech
    0.15
    rieg
    0.14
    ilos
    0.14
    MouseButton
    0.14
     DISCLAIM
    0.14
    ertiary
    0.14
    زÙĦ
    0.14
    Act Density 0.355%

    No Known Activations