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

    Neuronpedia

    INDEX
    Explanations

    references to ongoing research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     things
    -0.54
     must
    -0.52
     would
    -0.50
     take
    -0.48
     may
    -0.48
     can
    -0.47
    zunehmen
    -0.47
     will
    -0.46
     I
    -0.45
     is
    -0.44
    POSITIVE LOGITS
    تقاوى
    1.00
     مرئيه
    1.00
     beginnetje
    0.94
     EconPapers
    0.90
    AsUp
    0.88
     szóci
    0.88
    +#+#
    0.83
     Numerade
    0.82
     AssemblyCulture
    0.81
    TypedDataSet
    0.80
    Act Density 0.048%

    No Known Activations