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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     discretion
    0.39
     Heels
    0.38
    Decedent
    0.37
    Intersection
    0.37
     ensued
    0.37
    ↪
    0.36
    Colors
    0.36
     ensuing
    0.36
    鴻
    0.36
    udence
    0.35
    POSITIVE LOGITS
    jor
    0.37
    бре
    0.34
    rikt
    0.33
     ।
    0.32
    гла
    0.32
    beb
    0.32
    anderen
    0.32
    کن
    0.31
    прият
    0.31
    mrow
    0.31
    Act Density 0.000%

    No Known Activations