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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "average."

    oai_token-act-pair · gpt-3.5-turbo

    statistical references to averages and means

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Soft
    -0.71
    ocaly
    -0.66
    mare
    -0.66
    LINE
    -0.65
    fect
    -0.62
    lez
    -0.59
    otech
    -0.59
     Stall
    -0.58
    nuts
    -0.58
    lords
    -0.58
    POSITIVE LOGITS
     expectancy
    0.74
     ninety
    0.69
     Seym
    0.65
    versely
    0.64
    ccording
    0.63
     uptake
    0.63
    serving
    0.63
    expected
    0.63
     yearly
    0.63
    gain
    0.62
    Act Density 0.026%

    No Known Activations