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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zelfs
    -0.65
    Baca
    -0.51
     cualquiera
    -0.46
    Nothing
    -0.45
     nór
    -0.45
    しかも
    -0.44
    ago
    -0.43
     nothing
    -0.43
     myš
    -0.43
     unless
    -0.43
    POSITIVE LOGITS
    </h2>
    1.47
    </h4>
    1.39
    </h6>
    1.35
    </h3>
    1.27
    </h5>
    1.15
     فريبيس
    1.14
     }}$}
    1.11
    .")]
    1.04
    */}
    1.00
    tvguidetime
    0.99
    Act Density 0.052%

    No Known Activations