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

    Neuronpedia

    INDEX
    Explanations

    references to tokens and token-related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shakspeare
    -0.94
     Hec
    -0.88
     Monfieur
    -0.88
     Pyrr
    -0.88
     GLS
    -0.85
     screenWidth
    -0.84
     Diſ
    -0.83
     Jefus
    -0.82
     HAP
    -0.82
     Purdy
    -0.82
    POSITIVE LOGITS
     token
    2.12
     tokens
    2.07
     Token
    1.98
    token
    1.88
    Token
    1.83
    TOKEN
    1.76
    tokens
    1.72
     Tokens
    1.72
    Tokens
    1.67
     TOKEN
    1.63
    Act Density 0.044%

    No Known Activations