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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     CT
    -0.07
    抑え
    -0.07
     masked
    -0.06
    uct
    -0.06
    なくなった
    -0.06
    cheon
    -0.06
    뇗
    -0.06
    :&
    -0.06
    ԑ
    -0.06
     ceasefire
    -0.06
    POSITIVE LOGITS
    PRESSION
    0.07
    -transparent
    0.07
    bildung
    0.07
    冷链
    0.06
    preset
    0.06
    ドレス
    0.06
     forn
    0.06
    𝙧
    0.06
    联赛
    0.06
    北约
    0.06
    Act Density 0.006%

    No Known Activations