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

    Neuronpedia

    INDEX
    Explanations

    punctuation and exclamatory sentence structures

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

    end of utterance or thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Manbalar
    -0.72
     EconPapers
    -0.70
    Cyfeiriadau
    -0.65
    Referencies
    -0.64
    DoubleQuotes
    -0.63
     ujednoznacz
    -0.63
     faſt
    -0.61
    astéroïdes
    -0.60
     invokingState
    -0.59
     Habana
    -0.58
    POSITIVE LOGITS
     diante
    0.42
     entanto
    0.35
     extraordinario
    0.33
    However
    0.33
     However
    0.32
     précé
    0.32
    Actually
    0.31
     TÉCN
    0.31
     terlebih
    0.31
     absolutamente
    0.31
    Act Density 0.003%

    No Known Activations