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

    Neuronpedia

    INDEX
    Explanations

    terms related to discussions on historical slavery and its implications

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

    Follows punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    eliminated by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endpush
    -0.48
    CodeAttribute
    -0.47
     bazen
    -0.46
     кажется
    -0.46
     scheint
    -0.43
     seems
    -0.43
     seeming
    -0.43
     tampaknya
    -0.43
     Somehow
    -0.43
    好像
    -0.43
    POSITIVE LOGITS
     clearly
    0.52
    Clearly
    0.51
    clearly
    0.50
    別に
    0.49
    又不是
    0.49
     keineswegs
    0.49
     Clearly
    0.46
     المعيارى
    0.45
     ffs
    0.43
     expressly
    0.43
    Act Density 1.620%

    No Known Activations