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

    Neuronpedia

    INDEX
    Explanations

    constructions involving the article "a" followed by adjectives or nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somewhat
    -0.18
     kinds
    -0.17
     very
    -0.17
    very
    -0.15
    ennen
    -0.15
     sorts
    -0.15
    ål
    -0.15
    ç§į
    -0.15
    kind
    -0.15
     muy
    -0.15
    POSITIVE LOGITS
     thing
    0.21
    thing
    0.17
     Thing
    0.17
    Thing
    0.14
    awks
    0.14
     Fauc
    0.14
     zamanda
    0.14
    TimeString
    0.14
    InnerText
    0.14
    غÙĨ
    0.14
    Act Density 0.032%

    No Known Activations