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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    TIME
    -0.08
    .onOptionsItemSelected
    -0.08
    抿
    -0.07
    ליט
    -0.07
    以为
    -0.07
    سيطر
    -0.06
     TERMS
    -0.06
    还未
    -0.06
    tees
    -0.06
     hete
    -0.06
    POSITIVE LOGITS
    ◇
    0.07
     Scala
    0.07
     Zukunft
    0.07
    asco
    0.07
     завод
    0.07
    两条
    0.07
     PCR
    0.07
    𝙻
    0.07
     Nar
    0.07
    _epoch
    0.07
    Act Density 0.001%

    No Known Activations