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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the presence of formatted data or structure in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.80
     وتسجيلات
    -0.74
    ={`/
    -0.66
     Савезне
    -0.64
    ViewFeatures
    -0.63
    NUMX
    -0.61
    xtext
    -0.60
    ultuous
    -0.57
    dafx
    -0.57
     Wikimédia
    -0.57
    POSITIVE LOGITS
    ↵↵
    0.81
    <eos>
    0.64
     Also
    0.54
     kasarigan
    0.53
     judiciaire
    0.53
    ])),
    0.53
     consectetur
    0.52
     ayrıca
    0.50
     Reprinted
    0.49
    inheritdoc
    0.48
    Act Density 0.161%

    No Known Activations