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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lccn
    -0.56
    печат
    -0.47
    zü
    -0.46
    extAlignment
    -0.44
    astify
    -0.43
    CONDITIONS
    -0.43
    oubliez
    -0.43
    MLLoader
    -0.41
    newArrayList
    -0.41
     chính
    -0.40
    POSITIVE LOGITS
     africain
    0.70
    tangentMode
    0.70
     Euripides
    0.64
     asiatique
    0.63
    StoryboardSegue
    0.63
     romain
    0.62
    ⓧ
    0.62
     témoin
    0.62
     indisponible
    0.61
     myſelf
    0.61
    Act Density 0.020%

    No Known Activations