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

    Neuronpedia

    INDEX
    Explanations

    punctuation and markers of emotional reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dữ
    -0.13
     holy
    -0.13
     Installer
    -0.13
    Ø®ÛĮ
    -0.13
    (strtolower
    -0.13
     Contractor
    -0.13
     truth
    -0.13
     Updates
    -0.13
     Spreadsheet
    -0.13
     Tabs
    -0.13
    POSITIVE LOGITS
     Humanity
    0.24
     Humans
    0.23
     Nietzsche
    0.22
    Humans
    0.21
     Society
    0.21
     Happiness
    0.21
     Judaism
    0.20
     Human
    0.20
     Freedom
    0.20
     Buddhism
    0.20
    Act Density 0.305%

    No Known Activations