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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    款
    -0.27
    awe
    -0.26
     LOVE
    -0.25
    ikel
    -0.25
    ibly
    -0.23
    SRC
    -0.23
     Mods
    -0.23
     app
    -0.23
     mods
    -0.23
    -ups
    -0.23
    POSITIVE LOGITS
    omat
    0.32
    til
    0.26
    ä¸įèµ·
    0.25
    å¼ĵ
    0.24
    agus
    0.24
    inton
    0.24
    neau
    0.24
     далÑĮ
    0.23
    иÑģк
    0.23
    ToInt
    0.23
    Act Density 0.039%

    No Known Activations

    This feature has no known activations.