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

    Neuronpedia

    INDEX
    Explanations

    references to tokens related to authentication or access control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phry
    -1.01
     Shakspeare
    -1.00
     Majefty
    -0.99
     Jefus
    -0.98
     myſelf
    -0.95
     Monfieur
    -0.95
     Diſ
    -0.94
     Hec
    -0.94
     greateſt
    -0.92
     Chriſt
    -0.90
    POSITIVE LOGITS
     token
    1.94
     tokens
    1.91
     Token
    1.84
    token
    1.71
    TOKEN
    1.66
    Token
    1.66
    jsonwebtoken
    1.64
    tokens
    1.62
     Tokens
    1.62
    Tokens
    1.57
    Act Density 0.070%

    No Known Activations