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

    Neuronpedia

    INDEX
    Explanations

    words related to "tokens" and their management in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schluss
    -0.45
     izquier
    -0.42
    SetUp
    -0.42
    sy
    -0.41
     High
    -0.41
     Comprehensive
    -0.40
     Midwest
    -0.40
     preparing
    -0.40
    sss
    -0.39
     setUp
    -0.38
    POSITIVE LOGITS
     token
    2.03
     Token
    1.94
    Token
    1.88
    token
    1.84
     tokens
    1.77
     Tokens
    1.75
     TOKEN
    1.72
    TOKEN
    1.62
    tokens
    1.55
    Tokens
    1.49
    Act Density 0.098%

    No Known Activations