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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or the unknown potential of future events

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

    Comes before questions or speculation with "know"

    np_acts-logits-general · gemini-2.0-flash

    possibilities and unknowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.82
     Efq
    -0.71
    ContentAlignment
    -0.66
     Italijanski
    -0.62
     myſelf
    -0.59
     itſelf
    -0.57
     Jefus
    -0.57
    &
    -0.57
    stalt
    -0.57
    )");
    -0.57
    POSITIVE LOGITS
    说不定
    0.95
     unpredictable
    0.86
     may
    0.77
     potential
    0.77
     potentially
    0.76
     might
    0.74
     unexpected
    0.73
    の可能性
    0.73
     maybe
    0.72
    有可能
    0.71
    Act Density 0.161%

    No Known Activations