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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority and social structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pector
    -0.15
     Curl
    -0.14
    oun
    -0.14
    onne
    -0.14
    /operators
    -0.13
    440
    -0.13
     Hein
    -0.13
    arend
    -0.13
    041
    -0.13
    MW
    -0.13
    POSITIVE LOGITS
    IGHL
    0.18
    unsch
    0.17
    زÙħ
    0.15
    idal
    0.15
    ñas
    0.14
    Ð¡Ðł
    0.14
    оке
    0.14
    aggi
    0.14
    kest
    0.14
    Looper
    0.14
    Act Density 0.195%

    No Known Activations