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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    presence
    -0.08
    .nickname
    -0.07
    .slug
    -0.07
     Kosovo
    -0.07
    овые
    -0.07
    這是
    -0.07
    겙
    -0.07
    commands
    -0.07
     dilation
    -0.07
     kidding
    -0.07
    POSITIVE LOGITS
    _An
    0.07
    明确
    0.07
     Manhattan
    0.07
    فر
    0.07
     ünivers
    0.06
    _rc
    0.06
    _epoch
    0.06
    ��
    0.06
     tổ
    0.06
    olver
    0.06
    Act Density 0.056%

    No Known Activations