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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     DIM
    -0.07
    出资
    -0.07
    풋
    -0.07
    inine
    -0.07
    isChecked
    -0.07
    ḡ
    -0.07
     },↵↵↵
    -0.07
     underestimate
    -0.07
    Nama
    -0.07
    粱
    -0.07
    POSITIVE LOGITS
     בגל
    0.07
    veis
    0.07
    𝕭
    0.06
    '>
    0.06
    ']/
    0.06
    erglass
    0.06
    نامج
    0.06
    辘
    0.06
    ——
    0.06
     Check
    0.06
    Act Density 0.002%

    No Known Activations