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

    Neuronpedia

    INDEX
    Explanations

    text enclosed in square brackets

    oai_token-act-pair · gpt-3.5-turbo

    brackets indicating references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redu
    -0.73
     handlers
    -0.70
     factories
    -0.70
    ramid
    -0.65
     occas
    -0.64
     ratios
    -0.64
     regression
    -0.63
     antioxid
    -0.63
    mable
    -0.62
     Vend
    -0.62
    POSITIVE LOGITS
    ?]
    1.43
    sic
    1.42
    !]
    1.28
    :]
    1.18
     edit
    1.16
    ],
    1.12
    ].
    1.11
    emphasis
    1.11
    %]
    1.10
    .]
    1.09
    Act Density 0.040%

    No Known Activations