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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities and counts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.77
     ddelweddau
    -0.76
     EconPapers
    -0.74
     négociations
    -0.67
     <=",
    -0.66
     chrétiens
    -0.65
     discography
    -0.63
     touristes
    -0.63
    tagHelperRunner
    -0.62
    sizeCache
    -0.62
    POSITIVE LOGITS
     different
    1.14
    teen
    0.90
     separate
    0.85
     (!)
    0.80
    zehn
    0.79
     distinct
    0.79
    TEEN
    0.76
    different
    0.76
     more
    0.73
    (!)
    0.72
    Act Density 0.550%

    No Known Activations