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

    Neuronpedia

    INDEX
    Explanations

    variables or identifiers in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dodo
    -0.82
     irm
    -0.76
    rene
    -0.74
     Tinker
    -0.74
     incomplète
    -0.73
     Sarmiento
    -0.72
     ESE
    -0.71
    hs
    -0.70
    Go
    -0.69
    numerusform
    -0.68
    POSITIVE LOGITS
     VAL
    1.38
     Val
    1.36
     val
    1.35
     Valdez
    1.23
    VAL
    1.19
    Val
    1.11
    val
    1.08
     valet
    1.04
     Valky
    1.03
     Valdés
    1.00
    Act Density 0.091%

    No Known Activations