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

    Neuronpedia

    INDEX
    Explanations

    references to privacy policies and data protection practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    box
    -0.17
    ucer
    -0.16
    /msg
    -0.15
    avec
    -0.15
    illery
    -0.15
    edb
    -0.14
    ibox
    -0.14
    orks
    -0.14
    ouser
    -0.14
     нап
    -0.14
    POSITIVE LOGITS
     privacy
    0.23
     Privacy
    0.23
    privacy
    0.21
    Privacy
    0.21
    -policy
    0.19
     Policy
    0.18
    _priv
    0.18
     Datensch
    0.18
    policy
    0.17
     policy
    0.17
    Act Density 0.021%

    No Known Activations