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

    Neuronpedia

    INDEX
    Explanations

    references to privacy and its associated practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mount
    -0.56
    KommentareTeilen
    -0.51
     Goul
    -0.50
    RequestParam
    -0.48
    Mount
    -0.48
     mount
    -0.47
     Man
    -0.47
     Bolt
    -0.46
    shortcode
    -0.46
     mounts
    -0.44
    POSITIVE LOGITS
     privacy
    1.25
     Privacy
    1.23
     PRIVACY
    1.21
    privacy
    1.17
    Privacy
    1.17
    PRIVACY
    1.13
     privacidad
    1.11
    vacy
    0.91
     privacidade
    0.84
     confidentialité
    0.82
    Act Density 0.008%

    No Known Activations