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

    Neuronpedia

    INDEX
    Explanations

    references to authentication tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.04
     Shakspeare
    -1.02
     Phry
    -1.01
     Hec
    -0.98
     greateſt
    -0.96
     Monfieur
    -0.95
     Jefus
    -0.95
     Diſ
    -0.94
     Chriſt
    -0.94
     GridLayout
    -0.91
    POSITIVE LOGITS
     token
    1.99
     tokens
    1.94
     Token
    1.87
    token
    1.79
    Token
    1.74
    TOKEN
    1.71
    tokens
    1.68
    Tokens
    1.67
     Tokens
    1.61
     TOKEN
    1.52
    Act Density 0.068%

    No Known Activations