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

    Neuronpedia

    INDEX
    Explanations

    specific types of proper nouns and references in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lée
    -0.57
     Autorisations
    -0.56
     mijne
    -0.56
     mukaan
    -0.55
    ності
    -0.53
     avulla
    -0.52
    criture
    -0.52
     CURIAM
    -0.52
    ACEAE
    -0.52
    MathML
    -0.52
    POSITIVE LOGITS
     himself
    0.59
     ReactDOM
    0.52
     своя
    0.51
     grandson
    0.48
    culable
    0.48
    ISupport
    0.47
    CodedInputStream
    0.47
     gros
    0.47
     gentleman
    0.46
    دانشنامهٔ
    0.46
    Act Density 0.163%

    No Known Activations