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

    Neuronpedia

    INDEX
    Explanations

    elements related to formal rules, protocols, or official orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nat
    -0.16
    æĽ²
    -0.14
    atte
    -0.14
     Lag
    -0.14
     pond
    -0.14
     Grund
    -0.13
    orig
    -0.13
    bs
    -0.13
     Lager
    -0.13
     late
    -0.13
    POSITIVE LOGITS
    GBK
    0.15
    postalcode
    0.15
    важа
    0.14
    efe
    0.14
    uster
    0.14
    _ASSUME
    0.14
    engu
    0.14
     خاطر
    0.14
    GameManager
    0.14
    eyh
    0.14
    Act Density 0.326%

    No Known Activations