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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ϳ
    -0.07
     ámbito
    -0.07
    .sub
    -0.06
    _student
    -0.06
    /pro
    -0.06
    \">\
    -0.06
    autiful
    -0.06
     Challenger
    -0.06
     ייתכן
    -0.06
    _coll
    -0.06
    POSITIVE LOGITS
    他是
    0.08
     pit
    0.07
    他們
    0.07
    딧
    0.07
    了一批
    0.07
    ARC
    0.07
     collects
    0.06
     yi
    0.06
     consulted
    0.06
    洞
    0.06
    Act Density 0.013%

    No Known Activations