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

    Neuronpedia

    INDEX
    Explanations

    phrases and sentences related to data privacy and security

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Souha
    -0.92
     Mejía
    -0.82
     Messieurs
    -0.79
     pamph
    -0.77
     shenan
    -0.76
     Shakspeare
    -0.76
     poetical
    -0.71
     McLaugh
    -0.71
     Joaqu
    -0.69
     Mlle
    -0.68
    POSITIVE LOGITS
     privacy
    0.76
     Privacy
    0.71
    Privacy
    0.71
    ersonal
    0.66
     adat
    0.66
     frans
    0.64
    privacy
    0.63
     anonim
    0.63
     meda
    0.60
     dita
    0.59
    Act Density 0.458%

    No Known Activations