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

    Neuronpedia

    INDEX
    Explanations

    references to specific page numbers, chapters, or citations within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to bibliographic or source citation information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omorphic
    -0.75
    LLOW
    -0.69
    ordinate
    -0.68
    isters
    -0.66
    apesh
    -0.66
    onna
    -0.66
    venge
    -0.65
    iru
    -0.65
    omore
    -0.63
     Klux
    -0.62
    POSITIVE LOGITS
     .)
    1.03
    .).
    0.99
    ]).
    0.97
     emphasis
    0.89
    ).
    0.87
     reprinted
    0.87
    )."
    0.86
     ).
    0.85
     pp
    0.84
    .)
    0.84
    Act Density 0.303%

    No Known Activations