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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols, indicating emphasis or structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nourriture
    -0.56
    baarheid
    -0.55
    boneca
    -0.55
    télé
    -0.53
    brinco
    -0.50
    guiente
    -0.49
    arbitrary
    -0.48
    gården
    -0.48
    eſ
    -0.48
    caneca
    -0.46
    POSITIVE LOGITS
     Shakspeare
    1.03
     Cæsar
    0.86
     Monfieur
    0.86
     pleaſure
    0.84
     canst
    0.83
     Majefty
    0.82
     Shaksp
    0.81
     Mahomet
    0.77
     Diſ
    0.75
     Spinoza
    0.74
    Act Density 0.175%

    No Known Activations