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

    Neuronpedia

    INDEX
    Explanations

    terminology or concepts related to simplification

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.88
    yntaxException
    -0.85
    parsedMessage
    -0.80
    LookAnd
    -0.79
    ///</
    -0.79
    APORE
    -0.78
    NameInMap
    -0.77
     Tsche
    -0.77
    iotensin
    -0.75
    basicConfig
    -0.75
    POSITIVE LOGITS
    simplified
    0.70
     généraux
    0.67
     rendus
    0.63
     "/")
    0.60
    )')
    0.59
    ).\
    0.59
    );\
    0.58
    ,:);
    0.58
     loosened
    0.58
    )');
    0.57
    Act Density 0.092%

    No Known Activations