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

    Neuronpedia

    INDEX
    Explanations

    elements related to narrative structure and continuity in storytelling

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

    "entire" or "fill" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    entire or whole span

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    цездатний
    -0.63
     onAnimation
    -0.63
    டம்
    -0.62
     Roskov
    -0.61
    Numerology
    -0.57
    AutoScale
    -0.56
     unknownFields
    -0.56
     bäst
    -0.52
     فريبيس
    -0.52
    DataMember
    -0.52
    POSITIVE LOGITS
     entire
    3.56
     whole
    3.38
    whole
    3.20
    entire
    2.92
     Entire
    2.87
    Whole
    2.72
    Entire
    2.69
     WHOLE
    2.62
     ENTIRE
    2.57
     Whole
    2.43
    Act Density 0.506%

    No Known Activations