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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    elements related to coding or programming syntax, particularly those used in web development or data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Petro
    -0.61
     pains
    -0.57
     Ying
    -0.57
     puzzling
    -0.56
     Shiv
    -0.56
     shedding
    -0.56
     Ripple
    -0.55
     stewards
    -0.55
     unveiling
    -0.54
     haw
    -0.54
    POSITIVE LOGITS
    ))
    2.51
    )))
    2.46
    )).
    2.40
    )),
    2.36
    )]
    2.34
    ))))
    2.26
    ])
    2.23
    ));
    2.18
    )].
    2.06
    ]).
    2.05
    Act Density 0.104%

    No Known Activations