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

    Neuronpedia

    INDEX
    Explanations

    references to scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.80
     يتيمه
    -0.76
     незавершена
    -0.74
     Houſe
    -0.74
    تقاوى
    -0.73
     myſelf
    -0.69
     Majefty
    -0.68
     itſelf
    -0.68
     Theſe
    -0.67
     Monfieur
    -0.67
    POSITIVE LOGITS
    balls
    0.87
     Balls
    0.79
     balls
    0.77
    Balls
    0.77
     Wright
    0.72
    기에
    0.58
     ста
    0.57
    기
    0.57
     readers
    0.57
     "...
    0.56
    Act Density 0.069%

    No Known Activations