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

    Neuronpedia

    INDEX
    Explanations

    metrics and numerical data related to performance and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gross
    -0.19
    å¢Ĺ
    -0.19
     aumento
    -0.18
     Higher
    -0.18
    Higher
    -0.18
    higher
    -0.17
     Gross
    -0.16
     higher
    -0.16
     gấp
    -0.16
     heavier
    -0.16
    POSITIVE LOGITS
     reduced
    0.33
     lowest
    0.33
     reductions
    0.33
     reduction
    0.32
     lower
    0.31
     fewer
    0.30
     low
    0.30
     reduce
    0.29
     Lowest
    0.29
     reducing
    0.29
    Act Density 0.216%

    No Known Activations