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

    Neuronpedia

    INDEX
    Explanations

    terms related to authentication tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.10
     Jefus
    -1.01
     Majefty
    -1.00
     Shakspeare
    -1.00
     myſelf
    -0.98
     Diſ
    -0.97
    expandindo
    -0.97
     Theſe
    -0.94
     greateſt
    -0.94
     Pyrr
    -0.93
    POSITIVE LOGITS
     token
    2.64
     tokens
    2.45
     Token
    2.43
    token
    2.40
    Token
    2.31
    TOKEN
    2.12
     Tokens
    2.06
    Tokens
    2.05
    tokens
    2.04
     TOKEN
    1.98
    Act Density 0.030%

    No Known Activations