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

    Neuronpedia

    INDEX
    Explanations

    individual names and proper nouns

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

    poets and writers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.63
     Wikimedijinoj
    -0.52
    AddTagHelper
    -0.52
    LookAnd
    -0.51
    enumii
    -0.49
    Дереккөздер
    -0.48
    AutoScale
    -0.48
     CanadaChoose
    -0.48
    PreferredItem
    -0.46
    modb
    -0.45
    POSITIVE LOGITS
     verse
    0.48
     poet
    0.47
     rhyme
    0.46
     poetry
    0.46
     poets
    0.45
     Keats
    0.44
     versi
    0.43
     Poetry
    0.43
     poem
    0.43
     Tennyson
    0.43
    Act Density 0.037%

    No Known Activations