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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific control structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    if
    -0.48
    stdc
    -0.48
    roek
    -0.45
    ="{
    -0.44
    formaz
    -0.43
     sembler
    -0.43
    featureID
    -0.42
     zvuky
    -0.42
     view
    -0.42
    twimg
    -0.42
    POSITIVE LOGITS
     Efq
    0.67
     quæ
    0.67
    تقاوى
    0.64
     purpoſe
    0.62
     Wikimedijinoj
    0.62
     ſta
    0.60
     defStyle
    0.60
     ſte
    0.59
     Monfieur
    0.59
     חיצוניים
    0.59
    Act Density 0.062%

    No Known Activations