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

    Neuronpedia

    INDEX
    Explanations

    terms related to accuracy and precise measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gosling
    -0.62
    PathParam
    -0.61
    盪
    -0.61
    蕩
    -0.60
    DotNetBar
    -0.60
    endpush
    -0.59
    AnchorStyles
    -0.59
    vistar
    -0.57
     push
    -0.57
    пети
    -0.56
    POSITIVE LOGITS
     accuracy
    2.38
     Accuracy
    2.21
     accurate
    2.07
     Accurate
    2.02
    accuracy
    1.99
    Accuracy
    1.98
     ACCUR
    1.97
    Accurate
    1.96
    accurate
    1.92
     inaccuracy
    1.78
    Act Density 0.101%

    No Known Activations