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

    Neuronpedia

    INDEX
    Explanations

    references to classes, groups, or categories of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.64
     féminine
    -0.63
     pylint
    -0.63
     houſe
    -0.61
    jetunion
    -0.59
     purpoſe
    -0.57
     %}
    -0.56
     métallique
    -0.56
     ſeveral
    -0.55
     abstrait
    -0.55
    POSITIVE LOGITS
     that
    0.64
    BASELINE
    0.56
     whose
    0.54
     Chwiliwch
    0.54
     चीज़ों
    0.54
    Jeografia
    0.54
    CommandText
    0.53
    Abp
    0.53
    asmuch
    0.52
    XmlAccessType
    0.50
    Act Density 0.286%

    No Known Activations