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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical notation or symbols related to upper and lower bounds

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Pod
    -0.71
     Sid
    -0.69
    raisal
    -0.69
     Sin
    -0.69
    द
    -0.69
     Theil
    -0.67
    antMatchers
    -0.65
    irkus
    -0.65
    ting
    -0.65
     Bil
    -0.63
    POSITIVE LOGITS
    overline
    1.72
    клопе
    0.89
     ¦
    0.89
    ()")
    0.89
    "}>
    0.86
    ‾
    0.85
    .",
    0.84
     ‚
    0.84
    (;;)
    0.84
    }>;
    0.83
    Act Density 0.003%

    No Known Activations