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

    Neuronpedia

    INDEX
    Explanations

    abstracts or introductory sections in academic writing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    }));
    -0.90
    >';
    -0.88
    "]));
    -0.88
    Hochspringen
    -0.86
    }))
    -0.85
    >';
    -0.84
     '\\;'
    -0.83
    ="#"><
    -0.83
    !';
    -0.82
    ])):
    -0.81
    POSITIVE LOGITS
    ABSTRACT
    0.52
     summary
    0.52
     Zusammenfassung
    0.50
     Summary
    0.50
     SUMMARY
    0.48
    SUMMARY
    0.48
    summary
    0.48
    Summary
    0.46
     toch
    0.46
     ABSTRACT
    0.44
    Act Density 0.018%

    No Known Activations