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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or sections within square brackets

    oai_token-act-pair · gpt-3.5-turbo

    references to data or results denoted by brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redu
    -0.79
    edIn
    -0.74
    ramid
    -0.68
     factories
    -0.68
     seams
    -0.66
     Elys
    -0.66
     handlers
    -0.66
    mable
    -0.66
     ratios
    -0.65
     antioxid
    -0.64
    POSITIVE LOGITS
    ?]
    1.33
    !]
    1.21
     edit
    1.21
    sic
    1.19
    ËĪ
    1.17
    Footnote
    1.16
    ],
    1.10
    emphasis
    1.09
    actionDate
    1.08
    ].
    1.07
    Act Density 0.041%

    No Known Activations