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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🥲
    1.33
    🥰
    1.30
    🥹
    1.26
    🤎
    1.22
    🫶
    1.20
    🥺
    1.17
    🫧
    1.14
    ☺️
    1.14
    Hence
    1.13
    ✅
    1.13
    POSITIVE LOGITS
     vitally
    1.21
     very
    1.17
     absolutely
    1.16
     often
    1.16
     notoriously
    1.13
     seldom
    1.11
     systems
    1.11
     armies
    1.10
     radically
    1.09
     problems
    1.08
    Act Density 0.105%

    No Known Activations