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

    Neuronpedia

    INDEX
    Explanations

    references to circles and circular shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dataType
    -0.40
    )';
    -0.37
     Cata
    -0.37
     Nai
    -0.37
    javax
    -0.37
    dataType
    -0.37
     Bad
    -0.36
     marten
    -0.36
    agnos
    -0.36
    }));
    -0.35
    POSITIVE LOGITS
     circle
    2.14
     CIRCLE
    2.09
    Circle
    2.06
     Circle
    2.05
    circle
    2.03
     circles
    1.88
    CIRCLE
    1.84
     Circles
    1.77
     círculo
    1.72
    circles
    1.67
    Act Density 0.171%

    No Known Activations