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

    Neuronpedia

    INDEX
    Explanations

    Fictional characters with powers

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of wielding or manipulating elemental powers (e.g. “Elemental,” “control,” “manipulate,” “powers,” “elements”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    descriptions of characters in a fantasy or anime setting.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ContentSize
    -0.07
     underscores
    -0.06
    最后
    -0.06
    房屋
    -0.06
     О
    -0.06
     squarely
    -0.06
     begs
    -0.06
    الق
    -0.06
     datingside
    -0.06
    ータ
    -0.06
    POSITIVE LOGITS
     )"
    0.07
     blackout
    0.07
     će
    0.06
     respondents
    0.06
    -Co
    0.06
     widths
    0.06
     كسارة
    0.06
     incumb
    0.06
    Profiler
    0.06
     Statistical
    0.06
    Act Density 0.036%

    No Known Activations