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

    Neuronpedia

    INDEX
    Explanations

    terms related to conversational reference and preferences in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.50
    $_['
    -0.46
    VersionUID
    -0.39
     Priory
    -0.38
     propOrder
    -0.35
     Biôgrafia
    -0.34
     phrases
    -0.34
    alogie
    -0.34
    AccessorTable
    -0.33
     écou
    -0.33
    POSITIVE LOGITS
    +#+#
    0.61
     Halliday
    0.60
     corpora
    0.60
     Leech
    0.58
     genre
    0.58
     genres
    0.57
     register
    0.57
     corpus
    0.56
     sko
    0.55
    Corpus
    0.54
    Act Density 0.210%

    No Known Activations