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

    Neuronpedia

    INDEX
    Explanations

    language related to consent and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Generation
    -0.14
    raquo
    -0.14
    å£Ĭ
    -0.14
    ìĩ
    -0.13
     Corruption
    -0.13
     VARIABLES
    -0.13
    견
    -0.13
    çİ°åľº
    -0.13
    spor
    -0.13
    decorators
    -0.13
    POSITIVE LOGITS
     data
    0.27
     tracking
    0.24
     privacy
    0.23
     trackers
    0.22
     surveillance
    0.21
     collecting
    0.21
     Privacy
    0.21
     Data
    0.20
     TRACK
    0.20
     profil
    0.20
    Act Density 0.063%

    No Known Activations