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

    Neuronpedia

    INDEX
    Explanations

    highly frequent variable names or identifiers in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dodo
    -0.80
    abestanden
    -0.80
     Leopoldo
    -0.77
    rene
    -0.73
     Cleo
    -0.73
     ESE
    -0.72
     irm
    -0.72
     ASR
    -0.71
    Go
    -0.71
     Tinker
    -0.70
    POSITIVE LOGITS
     val
    1.54
     Val
    1.50
     VAL
    1.47
    VAL
    1.31
    val
    1.27
    Val
    1.26
     Valdez
    1.23
     Valky
    1.08
     valet
    1.06
     Valenzuela
    1.05
    Act Density 0.141%

    No Known Activations