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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    瑰
    -0.07
     Orch
    -0.07
    crast
    -0.07
    един
    -0.07
     Lum
    -0.07
     Semester
    -0.06
    .hasMore
    -0.06
    .inst
    -0.06
    机电
    -0.06
     featured
    -0.06
    POSITIVE LOGITS
     hát
    0.07
     repar
    0.07
    停产
    0.07
    sad
    0.07
    !)↵
    0.07
    translations
    0.07
    훈
    0.07
     corazón
    0.07
    شاب
    0.07
     jumping
    0.06
    Act Density 0.000%

    No Known Activations