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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a text document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    जू
    -0.88
     Smyrna
    -0.72
     Windy
    -0.70
    toon
    -0.69
     Karak
    -0.69
     Whittier
    -0.69
    \'
    -0.69
    İstinadlar
    -0.69
     !!}
    -0.68
    \":
    -0.68
    POSITIVE LOGITS
    <sup>
    1.99
    <sub>
    1.87
    <code>
    1.33
    <i>
    1.28
    <em>
    1.21
    <u>
    1.18
    <b>
    1.07
    <strong>
    1.03
    <s>
    1.02
    <h6>
    0.95
    Act Density 0.104%

    No Known Activations