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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases suggesting various quantities, amounts, or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.82
    >`;
    -0.76
    )');
    -0.72
    initComponents
    -0.69
     }},
    -0.69
    Controllo
    -0.69
    "]));
    -0.68
    RegressionTest
    -0.67
    autres
    -0.66
    >');
    -0.65
    POSITIVE LOGITS
     as
    0.74
     autant
    0.69
    떻
    0.62
    tagHelperRunner
    0.61
     муніципалі
    0.60
     ProtoMessage
    0.58
    CJK
    0.57
     zoveel
    0.56
     незавершена
    0.56
     tantas
    0.55
    Act Density 0.141%

    No Known Activations