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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gtest
    -0.08
     datatable
    -0.08
    _fire
    -0.07
    ḵ
    -0.07
    🐸
    -0.07
    （
    -0.07
     riches
    -0.07
     candidate
    -0.07
    “And
    -0.07
    (compare
    -0.07
    POSITIVE LOGITS
    
↵

↵
    0.07
     addUser
    0.06
    ꧈
    0.06
     unidad
    0.06
     SQLAlchemy
    0.06
     Special
    0.06
     chapter
    0.06
    江区
    0.06
    私たち
    0.06
    •↵↵
    0.06
    Act Density 0.058%

    No Known Activations