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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Quoted word or phrase

    np_acts-logits-general · gemini-2.0-flash

    quoted words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esetén
    -0.81
     religieuses
    -0.79
     alguno
    -0.73
     cherchez
    -0.71
    يميديا
    -0.70
     the
    -0.70
     solche
    -0.68
     personnelles
    -0.68
     religiosas
    -0.67
     sœur
    -0.65
    POSITIVE LOGITS
     same
    0.96
     original
    0.91
     largest
    0.90
     slightest
    0.89
     latter
    0.88
     entire
    0.85
     highest
    0.83
     biggest
    0.83
     final
    0.82
    iniest
    0.82
    Act Density 0.243%

    No Known Activations