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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and function-related syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pol
    -0.67
     real
    -0.66
     column
    -0.66
     kh
    -0.62
     post
    -0.62
    guint
    -0.62
     Jas
    -0.62
     Column
    -0.61
     pl
    -0.61
    -
    -0.61
    POSITIVE LOGITS
    ↵
    1.27
    }));
    1.21
    })));
    1.13
     }));
    1.09
    ])));
    1.07
    ')));
    1.05
    }});
    1.05
    ↵↵
    1.05
     });
    1.04
    });
    1.04
    Act Density 0.246%

    No Known Activations