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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and concepts related to scientific research and methodology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.83
    </strong>
    -0.72
    </blockquote>
    -0.64
    </u>
    -0.63
    <s>
    -0.62
    </i>
    -0.61
    <em>
    -0.61
    </h2>
    -0.60
    <u>
    -0.54
     $\
    -0.53
    POSITIVE LOGITS
     purpoſe
    1.03
     themſelves
    1.02
    antaranya
    1.02
     becauſe
    0.98
     ſtate
    0.96
     Eſ
    0.95
     poffible
    0.93
     Monfieur
    0.93
     whoſe
    0.93
     auffi
    0.91
    Act Density 0.762%

    No Known Activations