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

    Neuronpedia

    INDEX
    Explanations

    punctuations and sentence terminators

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

    Followed by a subject pronoun

    np_acts-logits-general · gemini-2.0-flash

    life and being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TYPED
    -0.60
    rairie
    -0.57
    anias
    -0.56
     interesar
    -0.55
     Sélectionnez
    -0.55
     uninsured
    -0.54
     Barracks
    -0.54
     Regulator
    -0.53
     Copies
    -0.52
    AttributeSet
    -0.52
    POSITIVE LOGITS
     Life
    1.05
    Life
    1.00
    Being
    0.88
     life
    0.85
     Being
    0.83
     LIFE
    0.78
    People
    0.78
     People
    0.78
    being
    0.73
    life
    0.71
    Act Density 0.296%

    No Known Activations