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

    Neuronpedia

    INDEX
    Explanations

    statistical or numerical information

    oai_token-act-pair · gpt-3.5-turbo

    references to financial statistics and political processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rax
    -0.44
    ourning
    -0.43
     Mandatory
    -0.43
    \",
    -0.42
     nutshell
    -0.42
    ,,,,,,,,
    -0.42
    ensional
    -0.41
     Dimensions
    -0.41
     (?,
    -0.40
     ------
    -0.40
    POSITIVE LOGITS
    ).[
    0.66
    !).
    0.61
     thereof
    0.56
     thereto
    0.56
     accordingly
    0.54
    ?).
    0.54
    ).
    0.52
    ]."
    0.50
     thereafter
    0.49
    )."
    0.44
    Act Density 3.599%

    No Known Activations