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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the article "a" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -0.84
     contextLoads
    -0.80
    Personendaten
    -0.80
     itſelf
    -0.74
    ഢ
    -0.73
     Italijani
    -0.71
     Purg
    -0.71
     myſelf
    -0.70
    ImageContext
    -0.69
     ―――――
    -0.68
    POSITIVE LOGITS
     à
    1.05
     to
    0.98
     к
    0.82
     به
    0.80
     إلى
    0.78
     ל
    0.78
     TO
    0.76
     zu
    0.76
    Σε
    0.75
     σε
    0.74
    Act Density 0.030%

    No Known Activations