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

    Neuronpedia

    INDEX
    Explanations

    references in a document to specific passages or statements within brackets

    oai_token-act-pair · gpt-3.5-turbo

    bracketed references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interf
    -0.67
     comprom
    -0.61
     receivers
    -0.61
     clash
    -0.61
     sergeant
    -0.61
     fitt
    -0.60
     Orn
    -0.60
     compliment
    -0.60
     regression
    -0.60
     receiver
    -0.60
    POSITIVE LOGITS
    Pg
    1.42
    âĢ¦]
    1.37
    ...]
    1.25
    sic
    1.22
    ?]
    1.22
    .]
    1.14
    :]
    1.14
    note
    1.08
     ].
    1.06
    PDF
    1.04
    Act Density 0.030%

    No Known Activations