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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and adverbs indicating superiority or difference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comparison: X is [adjective] than Y

    np_acts-logits-general · gemini-2.0-flash

    compares magnitudes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -1.09
     myſelf
    -1.01
    +#+
    -0.91
    >--}}
    -0.90
    }));
    -0.89
     Efq
    -0.89
     дописавши
    -0.88
    ſelves
    -0.86
     تضيفلها
    -0.85
    });*/
    -0.84
    POSITIVE LOGITS
     compared
    1.48
    compared
    1.22
     compare
    1.18
     сравнению
    1.09
     Compared
    1.08
     Compare
    1.07
     dibandingkan
    1.03
    Compared
    1.01
     than
    1.01
    Compare
    0.95
    Act Density 0.498%

    No Known Activations