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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals, particularly in political and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -1.07
    LookAnd
    -1.06
    ſelves
    -1.00
     Anſ
    -1.00
     perfons
    -0.98
     فريبيس
    -0.97
     myſelf
    -0.95
    новниш
    -0.94
     Perſ
    -0.94
     Majefty
    -0.91
    POSITIVE LOGITS
    SuppressLint
    0.45
     Singh
    0.45
     M
    0.44
     atas
    0.43
     Ein
    0.42
     rein
    0.42
     họ
    0.41
    щу
    0.41
    ੱ
    0.41
     G
    0.41
    Act Density 0.201%

    No Known Activations