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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     willing
    -0.08
     adjud
    -0.08
     "%"
    -0.07
     cortex
    -0.07
     Lots
    -0.07
    iless
    -0.07
     Circuit
    -0.07
    -tested
    -0.07
    .less
    -0.07
    ʯ
    -0.07
    POSITIVE LOGITS
    彧
    0.07
    _Offset
    0.07
    做完
    0.07
    .sin
    0.07
    챔
    0.07
    ves
    0.07
    让你
    0.07
    点儿
    0.07
    émon
    0.06
    蹒
    0.06
    Act Density 0.004%

    No Known Activations