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

    Neuronpedia

    INDEX
    Explanations

    references to the word "a" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.88
     iſt
    -0.87
     ་་
    -0.82
    Germain
    -0.80
     Mahomet
    -0.80
     itſelf
    -0.79
    jména
    -0.77
    ly
    -0.73
     fometimes
    -0.71
     Jefus
    -0.71
    POSITIVE LOGITS
     à
    1.03
     zu
    0.91
    Σε
    0.85
    ]<<
    0.83
     к
    0.83
     به
    0.77
     BorderRadius
    0.77
    À
    0.76
     aan
    0.75
    }}]{
    0.74
    Act Density 0.015%

    No Known Activations