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

    Neuronpedia

    INDEX
    Explanations

    specific nouns or terms related to significant concepts, actions, or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agan
    -0.15
    ee
    -0.15
    PushButton
    -0.14
    ww
    -0.14
    struct
    -0.14
    uce
    -0.14
    ÙĦع
    -0.14
     REP
    -0.14
    993
    -0.14
    kee
    -0.13
    POSITIVE LOGITS
    ipay
    0.14
    _simps
    0.14
    çek
    0.14
    visibility
    0.14
    ongs
    0.14
    uri
    0.14
    opa
    0.14
    ะ
    0.14
    IDD
    0.13
    terra
    0.13
    Act Density 0.001%

    No Known Activations