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

    Neuronpedia

    INDEX
    Explanations

    numbers that are being emphasized in the text

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical or reference identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.69
     Luther
    -0.66
     Allaah
    -0.61
    door
    -0.61
    gaard
    -0.60
    ippery
    -0.60
    perties
    -0.59
     Murdoch
    -0.58
     Sanford
    -0.58
    inyl
    -0.57
    POSITIVE LOGITS
     ,"
    1.41
     ):
    1.40
     )
    1.38
     ),
    1.34
     )]
    1.31
     ."
    1.26
     ).
    1.25
     ].
    1.22
     ]
    1.22
     ))
    1.20
    Act Density 0.170%

    No Known Activations