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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ‬
    1.27
    <0x0D>
    1.27
    </b>
    1.25
    </h3>
    1.23
    </h2>
    1.22
    </h4>
    1.21
    </i>
    1.17
    </h6>
    1.14
    ↵↵
    1.12
    </h1>
    1.08
    POSITIVE LOGITS
    er
    1.21
    the
    1.11
    c
    1.04
    ed
    0.98
    il
    0.98
    r
    0.96
    ali
    0.95
    (
    0.95
    ion
    0.93
    á
    0.92
    Act Density 0.000%

    No Known Activations