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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     an
    1.61
    ס
    1.31
     overclock
    1.30
     omission
    1.30
     בל
    1.30
     imati
    1.30
     במ
    1.27
     $
    1.27
     işaret
    1.27
     אל
    1.26
    POSITIVE LOGITS
    t
    1.88
    ства
    1.25
    chen
    1.24
    cd
    1.22
    cap
    1.21
    city
    1.19
    жи
    1.13
    of
    1.12
    counter
    1.11
    )。
    1.10
    Act Density 0.000%

    No Known Activations