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

    Neuronpedia

    INDEX
    Explanations

    elements related to code and data structure in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¸ĺ
    -0.16
     Authenticate
    -0.15
     authenticated
    -0.15
    ray
    -0.15
     NOM
    -0.15
    æ®
    -0.14
    AuthToken
    -0.14
    sono
    -0.14
     authenticate
    -0.14
    ovÃŃ
    -0.14
    POSITIVE LOGITS
     Iss
    0.22
     claims
    0.22
     Claims
    0.22
     audience
    0.21
     audiences
    0.21
    Claims
    0.21
    claims
    0.20
     Audience
    0.20
     aud
    0.19
     claim
    0.18
    Act Density 0.037%

    No Known Activations