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

    Neuronpedia

    INDEX
    Explanations

    assignment and declaration patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     présidenti
    -0.63
    Autoritní
    -0.58
     élé
    -0.50
    providedIn
    -0.50
     célé
    -0.50
    OutOfRange
    -0.49
    ProductList
    -0.47
     BoxFit
    -0.47
     insuffisamment
    -0.46
     fidèles
    -0.46
    POSITIVE LOGITS
    escape
    0.79
     sanitize
    0.77
     clean
    0.76
     escape
    0.75
     strip
    0.74
    Escape
    0.73
     sanitized
    0.70
     decode
    0.69
     Clean
    0.69
     cleaned
    0.69
    Act Density 0.102%

    No Known Activations