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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of exits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     pudesse
    -0.44
    tonode
    -0.41
    setCell
    -0.40
    Stephen
    -0.39
    ESOME
    -0.38
    biamo
    -0.38
     Stephen
    -0.38
     julho
    -0.38
     pemas
    -0.37
    řev
    -0.36
    POSITIVE LOGITS
     exit
    1.25
     Exit
    1.24
    exit
    1.14
     EXIT
    1.13
    Exit
    1.11
     exits
    1.09
     exited
    1.01
    EXIT
    1.00
    exits
    0.93
     exiting
    0.86
    Act Density 0.102%

    No Known Activations