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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imas
    -0.18
    ymes
    -0.14
    è§
    -0.14
    .Throw
    -0.14
    ines
    -0.14
    _strlen
    -0.13
    .until
    -0.13
    ç°
    -0.13
     edip
    -0.13
    imes
    -0.13
    POSITIVE LOGITS
     privacy
    0.38
     Privacy
    0.37
    Privacy
    0.34
    privacy
    0.33
     Terms
    0.28
     terms
    0.25
    itemap
    0.25
    /terms
    0.25
     Cookie
    0.24
    Terms
    0.24
    Act Density 0.056%

    No Known Activations