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

    Neuronpedia

    INDEX
    Explanations

    specific numerical thresholds and comparisons in quantitative contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    )");
    -0.82
    }],
    -0.73
     Efq
    -0.70
    ")));
    -0.69
    }}}
    -0.66
    $.
    -0.66
    setVerticalGroup
    -0.64
    Zitat
    -0.63
    IsContent
    -0.63
    })));
    -0.63
    POSITIVE LOGITS
    saraba
    0.59
    ่
    0.54
    Start
    0.48
     Start
    0.48
    ja
    0.48
     start
    0.47
    dec
    0.46
    они
    0.45
    getOut
    0.44
    起
    0.44
    Act Density 0.163%

    No Known Activations