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

    Neuronpedia

    INDEX
    Explanations

    phrases or keywords related to user interface actions or elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gratuites
    -0.97
     humaines
    -0.90
     financières
    -0.89
     noires
    -0.89
     suivantes
    -0.86
     énergé
    -0.86
    ThroughAttribute
    -0.86
     gratuits
    -0.82
     publiques
    -0.82
     vertes
    -0.82
    POSITIVE LOGITS
     de
    0.55
     Geme
    0.47
    cienti
    0.46
     Sist
    0.45
    fis
    0.44
    afat
    0.43
     بالق
    0.43
    De
    0.42
     electron
    0.42
     interne
    0.42
    Act Density 0.047%

    No Known Activations