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

    Neuronpedia

    INDEX
    Explanations

    articles and modifiers related to nouns

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

    The letter "a" in French text

    np_acts-logits-general · gemini-2.0-flash

    mon à moi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.95
     Efq
    -0.94
     Shakspeare
    -0.93
     Jefus
    -0.91
     iſt
    -0.90
     ་་
    -0.89
     myſelf
    -0.88
    theless
    -0.88
     ſever
    -0.88
     Majefty
    -0.87
    POSITIVE LOGITS
     be
    0.71
     the
    0.70
     a
    0.66
     least
    0.63
     liquid
    0.57
     pe
    0.56
     work
    0.56
     à
    0.56
     rate
    0.56
     make
    0.55
    Act Density 0.030%

    No Known Activations