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

    Neuronpedia

    INDEX
    Explanations

    formatting or syntax-related elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     daw
    -0.76
     Athena
    -0.75
    ing
    -0.72
     חיצוניים
    -0.71
     McClure
    -0.71
     SYS
    -0.70
    SYS
    -0.70
     Duda
    -0.69
     Dawes
    -0.69
     Toul
    -0.69
    POSITIVE LOGITS
    ));
    1.40
    "));
    1.19
    )),
    1.19
    ()));
    1.15
    ))
    1.11
    )));
    1.10
    ]))
    1.09
    ()))
    1.06
    ")),
    1.02
    )).
    1.01
    Act Density 0.142%

    No Known Activations