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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations, particularly those involving parameters and functions within formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    })));
    -0.83
    ]]);
    -0.76
    ]<<
    -0.75
    ])));
    -0.73
    ()));
    -0.69
    ()));
    -0.69
    }]{
    -0.68
    ()].
    -0.67
    '])
    -0.66
    "]);
    -0.65
    POSITIVE LOGITS
    IntoConstraints
    0.72
     Hälfte
    0.69
    Half
    0.64
     moitié
    0.63
     Half
    0.62
    一半
    0.59
    半分
    0.59
     halves
    0.58
    half
    0.57
     Majesté
    0.54
    Act Density 0.238%

    No Known Activations