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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to people, especially in contexts of responsibility and consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stad
    -0.17
    ade
    -0.16
    antom
    -0.16
    _:*
    -0.15
    omu
    -0.15
    mana
    -0.14
     Mund
    -0.14
    lectron
    -0.14
    undy
    -0.14
    ss
    -0.14
    POSITIVE LOGITS
    kees
    0.16
    ActionCreators
    0.15
    354
    0.15
    ãģ¡ãģ¯
    0.14
    ãģĭãĤĭ
    0.14
    byname
    0.14
    akit
    0.14
    -regexp
    0.14
     Arts
    0.13
    missive
    0.13
    Act Density 0.107%

    No Known Activations