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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Johan
    -0.07
     Florian
    -0.07
     Whoever
    -0.07
    鳀
    -0.06
     awkward
    -0.06
     technically
    -0.06
    someone
    -0.06
     Thermal
    -0.06
     ברח
    -0.06
     VALUES
    -0.06
    POSITIVE LOGITS
    Descriptors
    0.07
    ext
    0.07
    حفظ
    0.07
    _ACCEPT
    0.07
    expire
    0.07
    YES
    0.07
     التط
    0.07
    ists
    0.07
     eviction
    0.07
    uess
    0.07
    Act Density 0.141%

    No Known Activations