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

    Neuronpedia

    INDEX
    Explanations

    concepts related to consent and permissions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arshal
    -0.16
     fasc
    -0.15
    akov
    -0.15
    arp
    -0.15
    Ä©
    -0.14
    æ°Ĺãģ«åħ¥
    -0.14
    ãĥŃãĥ¼
    -0.14
    Appe
    -0.14
    rades
    -0.13
    KI
    -0.13
    POSITIVE LOGITS
     consent
    0.54
     permission
    0.46
    cons
    0.45
    -cons
    0.41
     cons
    0.40
    Cons
    0.40
     Consent
    0.40
     express
    0.35
    permission
    0.35
     Permission
    0.34
    Act Density 0.093%

    No Known Activations