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

    Neuronpedia

    INDEX
    Explanations

    quantitative phrases relating to percentages and proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imen
    -0.16
    osa
    -0.16
     masses
    -0.14
    udi
    -0.14
    á»ĩu
    -0.14
    mer
    -0.14
    inal
    -0.14
    pler
    -0.13
     dims
    -0.13
    lements
    -0.13
    POSITIVE LOGITS
     total
    0.27
    total
    0.21
    overall
    0.20
     overall
    0.20
     TOTAL
    0.20
    -total
    0.19
     all
    0.17
    .total
    0.17
    	total
    0.17
    _total
    0.16
    Act Density 0.048%

    No Known Activations