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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating notable distinctions or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Registration
    -0.15
    _AES
    -0.15
    _CBC
    -0.14
    _DECLS
    -0.14
     Placement
    -0.14
     Credits
    -0.14
    istence
    -0.13
    Registration
    -0.13
     Legislation
    -0.13
     Installation
    -0.12
    POSITIVE LOGITS
     Lovely
    0.29
     Sexy
    0.29
     Beautiful
    0.28
     Gorgeous
    0.28
     Elegant
    0.28
     Delicious
    0.28
     Brilliant
    0.27
     Cool
    0.26
     Wonderful
    0.26
     Pleasant
    0.26
    Act Density 0.138%

    No Known Activations