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

    Neuronpedia

    INDEX
    Explanations

    words indicating isolation or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    {}",
    -0.95
    ()",
    -0.88
     ?',
    -0.87
    "]),
    -0.85
     "));
    -0.85
    ()',
    -0.84
     "}";
    -0.84
    }'.
    -0.81
    ()");
    -0.79
    ]<<
    -0.79
    POSITIVE LOGITS
     estimés
    0.62
    bollah
    0.61
    baguna
    0.60
     Lainnya
    0.59
     Unito
    0.59
    usda
    0.58
    лтемелер
    0.57
    engkapnya
    0.57
     Palestina
    0.57
    bewerken
    0.56
    Act Density 0.368%

    No Known Activations