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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or possibility

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

    Text following "Maybe"

    np_acts-logits-general · gemini-2.0-flash

    introducing possibilities and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.08
     pleaſure
    -0.81
    Datuak
    -0.79
     itſelf
    -0.77
    featureID
    -0.75
     ويكيميديا
    -0.72
    كويكب
    -0.65
     Jefus
    -0.65
     ſever
    -0.65
     iſt
    -0.65
    POSITIVE LOGITS
    anskje
    0.89
     even
    0.83
     maybe
    0.81
     Maybe
    0.80
    maybe
    0.76
    Maybe
    0.75
     something
    0.70
     someone
    0.67
     someday
    0.67
    EOUS
    0.63
    Act Density 0.047%

    No Known Activations