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

    Neuronpedia

    INDEX
    Explanations

    information related to documentation and legal agreements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eco
    -0.63
    eele
    -0.57
    iam
    -0.56
    edom
    -0.55
    uman
    -0.54
     Travels
    -0.53
    Tip
    -0.52
    idy
    -0.52
    eni
    -0.51
    board
    -0.50
    POSITIVE LOGITS
     nor
    2.12
    nor
    1.73
    yet
    1.31
     anymore
    1.26
    unless
    1.18
     preferring
    1.17
     unless
    1.17
     Nor
    1.12
     except
    1.10
    Nor
    1.04
    Act Density 0.309%

    No Known Activations