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

    Neuronpedia

    INDEX
    Explanations

    the character "Ċ" at different positions in the text

    oai_token-act-pair · gpt-3.5-turbo

    the presence of numerical data or specific counts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     steroids
    -0.79
     inactive
    -0.75
     unprepared
    -0.73
     diving
    -0.72
     outwe
    -0.71
     occas
    -0.71
     fronts
    -0.70
     biod
    -0.70
     ideal
    -0.68
     aging
    -0.68
    POSITIVE LOGITS
    ³³³³
    1.43
    ³³³³³³³³
    1.41
    ³³³³³³³³³³³³³³³³
    1.38
    ³³³
    1.37
    ³³
    1.18
    Palestinian
    1.09
    à¨
    1.07
    Born
    1.05
    Anonymous
    1.04
    Posted
    1.04
    Act Density 0.074%

    No Known Activations