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

    Neuronpedia

    INDEX
    Explanations

    terms of casual address and informal speech patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eg
    -0.17
    ilogy
    -0.16
    ailability
    -0.16
    empo
    -0.15
    agger
    -0.14
    é¼
    -0.14
     dick
    -0.14
     Gut
    -0.14
    å£
    -0.14
    alty
    -0.14
    POSITIVE LOGITS
     trib
    0.14
    allis
    0.14
     subt
    0.14
    .lin
    0.14
    uele
    0.14
    654
    0.14
    asse
    0.14
    adin
    0.13
    stm
    0.13
    UrlParser
    0.13
    Act Density 0.054%

    No Known Activations