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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    figures
    -0.07
     démarch
    -0.07
    (LED
    -0.07
     Tune
    -0.07
     glued
    -0.07
     PARAM
    -0.07
     Looks
    -0.07
     Romanian
    -0.06
    +N
    -0.06
    Fri
    -0.06
    POSITIVE LOGITS
    ':''
    0.08
    شو
    0.08
    _history
    0.07
    collapse
    0.07
    icient
    0.06
    bag
    0.06
    recent
    0.06
    两岸
    0.06
     이야
    0.06
    娱乐
    0.06
    Act Density 0.001%

    No Known Activations