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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     capsule
    -0.16
    okit
    -0.15
    exus
    -0.15
    ÃŃm
    -0.14
    acks
    -0.14
    Å¡ek
    -0.14
     ÙĨÙĪر
    -0.14
    ży
    -0.14
     æĹ
    -0.14
    εβ
    -0.14
    POSITIVE LOGITS
    istas
    0.15
    ë¶
    0.15
    ista
    0.15
    oldem
    0.14
    RunLoop
    0.14
    urai
    0.13
    iores
    0.13
    ledon
    0.13
    /Internal
    0.13
    лÑĥб
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.