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

    Neuronpedia

    INDEX
    Explanations

    instructions or warnings related to file editing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ſelf
    -0.80
    følgelig
    -0.79
     Houſe
    -0.78
    醐
    -0.78
    ſelves
    -0.77
     leaſt
    -0.77
    alakip
    -0.77
    StoreMessageInfo
    -0.76
    actéristi
    -0.75
     Monfieur
    -0.75
    POSITIVE LOGITS
    jen
    0.50
    ंदीखरीदारी
    0.46
    httphttps
    0.43
     principal
    0.43
    GOTREF
    0.43
    mante
    0.41
     G
    0.41
     man
    0.41
    ori
    0.41
     pas
    0.40
    Act Density 0.018%

    No Known Activations