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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and features related to computer hardware

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pamph
    -1.31
     Shakspeare
    -1.12
     Mlle
    -0.94
    <bos>
    -0.90
     Abbé
    -0.88
     philosophic
    -0.88
     clergymen
    -0.86
     Moslem
    -0.85
     poetical
    -0.83
     Shaksp
    -0.82
    POSITIVE LOGITS
     trouva
    0.62
     fumo
    0.59
     tenda
    0.55
     exé
    0.55
     specchio
    0.54
     ristor
    0.54
     peccato
    0.54
     démoc
    0.53
     brutto
    0.52
     attacco
    0.52
    Act Density 0.173%

    No Known Activations