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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific news agencies or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.82
    etheless
    -0.76
    ãĢİ
    -0.68
    ãĢIJ
    -0.65
    answered
    -0.64
    yip
    -0.63
    profits
    -0.61
    [/
    -0.61
     disadvant
    -0.57
    $.
    -0.57
    POSITIVE LOGITS
    )"
    1.67
    )
    1.64
    )]
    1.57
    )."
    1.52
    ),"
    1.52
    âĢ¦)
    1.49
    .)
    1.47
    )—
    1.47
    )/
    1.45
    )</
    1.44
    Act Density 0.168%

    No Known Activations