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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     this
    -0.19
    è¿Ļä¸Ģ
    -0.17
     these
    -0.17
    blr
    -0.16
     This
    -0.15
     Relay
    -0.15
     boj
    -0.15
    atura
    -0.15
     thought
    -0.15
    rup
    -0.14
    POSITIVE LOGITS
    esson
    0.18
    elly
    0.18
    ÙIJÙħ
    0.16
    aight
    0.15
    .gson
    0.15
    gle
    0.14
    CESS
    0.14
    gem
    0.14
    ute
    0.14
    å¸Ń
    0.14
    Act Density 0.602%

    No Known Activations