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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     purposely
    0.37
     TRY
    0.35
     properly
    0.34
     blatantly
    0.33
     actually
    0.32
     beginning
    0.32
     başlam
    0.32
    뿅
    0.31
    ärke
    0.31
    居然
    0.31
    POSITIVE LOGITS
     regard
    0.36
     down
    0.35
     foreground
    0.31
     Technik
    0.31
     consider
    0.30
    consider
    0.30
     deem
    0.30
     fores
    0.30
     Foreground
    0.30
     subordinate
    0.29
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.