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

    Neuronpedia

    INDEX
    Explanations

    terms related to instructions or specifications

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and jargon associated with various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.72
     ('
    -0.61
     Trace
    -0.60
     ,"
    -0.58
    Dialogue
    -0.58
    ãĢIJ
    -0.57
     Cheong
    -0.57
     Yard
    -0.55
     Meter
    -0.55
    olicy
    -0.54
    POSITIVE LOGITS
    )
    1.25
    -)
    1.24
    ?)
    1.22
    +)
    1.20
    !),
    1.13
    )."
    1.12
    )=
    1.11
    !)
    1.11
    %)
    1.11
    )/
    1.10
    Act Density 0.196%

    No Known Activations