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

    Neuronpedia

    INDEX
    Explanations

    punctuation and the structure of sentences

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

    Tokens preceding contrasting conjunctions

    np_acts-logits-general · gemini-2.0-flash

    concessive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Waray
    -0.79
    Autoritní
    -0.75
    ----</
    -0.66
     Exactos
    -0.63
    RTEX
    -0.62
    hassee
    -0.61
     المعيارى
    -0.60
    HomeAsUpEnabled
    -0.58
    EndProject
    -0.57
     كومونز
    -0.57
    POSITIVE LOGITS
     still
    2.66
    Still
    2.61
     nevertheless
    2.60
     nonetheless
    2.58
    Nevertheless
    2.50
     Still
    2.50
    Nonetheless
    2.49
    still
    2.48
     Nonetheless
    2.43
     Nevertheless
    2.43
    Act Density 0.360%

    No Known Activations