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

    Neuronpedia

    INDEX
    Explanations

    terms related to data analysis and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.68
     testSet
    -0.55
    /*
    -0.55
    quela
    -0.55
    AddTagHelper
    -0.52
    __*/
    -0.52
     Efq
    -0.51
     entirety
    -0.50
    Traceback
    -0.50
     ModelExpression
    -0.49
    POSITIVE LOGITS
     some
    1.28
     examples
    1.26
     Examples
    1.24
    Examples
    1.18
    examples
    1.08
     Some
    1.07
    主な
    1.07
     among
    1.06
    Some
    1.06
    some
    1.05
    Act Density 0.299%

    No Known Activations