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

    Neuronpedia

    INDEX
    Explanations

    words denoting exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     giuri
    -0.78
     ansatte
    -0.67
     publiques
    -0.66
     varandra
    -0.64
     MessageBoxIcon
    -0.63
     avviene
    -0.61
     giornal
    -0.59
     sanitaires
    -0.59
     medlems
    -0.58
    клопе
    -0.58
    POSITIVE LOGITS
    头
    0.72
    ########.
    0.67
    Offensive
    0.63
     Anterior
    0.63
    ographiques
    0.62
    頭
    0.61
     offensi
    0.61
    *{
    0.60
     anterior
    0.60
    Incoming
    0.59
    Act Density 0.146%

    No Known Activations