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

    Neuronpedia

    INDEX
    Explanations

    numerical percentages with specific formatting

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics expressed as percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.67
    Mand
    -0.62
    izoph
    -0.62
     redist
    -0.60
     reasonable
    -0.56
     rightfully
    -0.56
    icians
    -0.56
     orderly
    -0.55
     unsus
    -0.55
     hawk
    -0.55
    POSITIVE LOGITS
    ĸļ
    0.93
    isSpecialOrderable
    0.72
     crore
    0.68
    billion
    0.68
     Coverage
    0.68
    cro
    0.68
     Percent
    0.67
    undred
    0.67
    iosity
    0.66
    ãĤ¢ãĥ«
    0.66
    Act Density 0.181%

    No Known Activations