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

    Neuronpedia

    INDEX
    Explanations

    references to the nature of existence and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.95
    )"),
    -0.92
     leaſt
    -0.91
    []
    -0.91
     fevere
    -0.90
    ]),
    -0.89
     ―――――
    -0.89
    BibitemShut
    -0.86
     **/
    -0.86
     ſeveral
    -0.85
    POSITIVE LOGITS
    ,
    0.84
    .
    0.69
     in
    0.67
     disponibilités
    0.57
    ;
    0.55
     when
    0.52
    ?
    0.50
     (
    0.50
     anymore
    0.49
     at
    0.47
    Act Density 0.193%

    No Known Activations