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

    Neuronpedia

    INDEX
    Explanations

    keywords related to various professions, physical objects, and facilities, such as hospital, cockpit, fork lift guy, etc

    oai_token-act-pair · gpt-3.5-turbo

    nouns and related terms associated with various types of objects and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.74
     Helpful
    -0.72
    ãĤ´ãĥ³
    -0.70
    SEE
    -0.68
    ĵĺ
    -0.67
    ï¸
    -0.64
    Footnote
    -0.63
     Various
    -0.63
    £ı
    -0.62
     Known
    -0.60
    POSITIVE LOGITS
     wasn
    1.23
     sucks
    1.22
     hasn
    1.20
     isn
    1.20
     doesnt
    1.19
     doesn
    1.13
     guy
    1.09
     ain
    1.07
     didn
    1.05
     didnt
    1.00
    Act Density 0.503%

    No Known Activations