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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to legal and formal language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.84
    ьаж
    -0.82
    Autoritní
    -0.75
    المناصب
    -0.75
     lenker
    -0.73
    قایناق‌لار
    -0.71
    Pautan
    -0.71
    цездатний
    -0.70
    Приятного
    -0.70
    Havolalar
    -0.70
    POSITIVE LOGITS
     Ви
    0.61
     समीक्षाएं
    0.60
     LoggerFactory
    0.60
    Κα
    0.57
     Ε
    0.56
    ظ
    0.56
     Е
    0.55
     О
    0.55
     problem
    0.55
     Ре
    0.55
    Act Density 0.246%

    No Known Activations