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

    Neuronpedia

    INDEX
    Explanations

    references to public perception and social dynamics involving people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PÅĻi
    -0.17
    aÄįnÃŃ
    -0.16
    itte
    -0.15
    ayne
    -0.14
    ï¸ı
    -0.14
    _BS
    -0.13
    serie
    -0.13
    rang
    -0.13
    kbd
    -0.13
    ucz
    -0.13
    POSITIVE LOGITS
    orca
    0.14
    pair
    0.14
    ÏĮ
    0.14
    Ùħار
    0.13
     Tone
    0.13
    ãģĵãģĨ
    0.13
    éo
    0.13
    528
    0.13
    pin
    0.13
     CommonModule
    0.13
    Act Density 0.110%

    No Known Activations