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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     lãi
    -0.07
     disag
    -0.07
    warf
    -0.07
    azole
    -0.07
     shortcuts
    -0.07
    🥇
    -0.07
     anthrop
    -0.07
     tissues
    -0.06
    -anchor
    -0.06
    词语
    -0.06
    POSITIVE LOGITS
    _DAYS
    0.07
    (DataType
    0.07
     surely
    0.06
    ﲒ
    0.06
    跟
    0.06
     וגם
    0.06
    �
    0.06
     obras
    0.06
    ecessarily
    0.06
     emulation
    0.06
    Act Density 0.003%

    No Known Activations