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

    Neuronpedia

    INDEX
    Explanations

    references to capacities and comparisons between groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.61
     kaarangay
    -0.59
    تقاوى
    -0.56
     estekak
    -0.53
    findpost
    -0.53
     Roskov
    -0.52
    MessageTagHelper
    -0.52
    setVerticalGroup
    -0.51
    ArgumentParser
    -0.50
    LabelTagHelper
    -0.50
    POSITIVE LOGITS
     صوتيه
    0.75
     HttpNotFound
    0.54
     AssemblyCompany
    0.54
     übrigens
    0.53
     AttributeSet
    0.52
    DoubleQuotes
    0.51
    etera
    0.50
    wußt
    0.50
     Derfor
    0.50
    IntoConstraints
    0.50
    Act Density 0.349%

    No Known Activations