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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     inhabit
    -0.08
    悲
    -0.08
    dead
    -0.08
     frosting
    -0.07
    自然灾害
    -0.07
    _LONG
    -0.07
    さまざまな
    -0.07
    ━
    -0.07
     nouvelles
    -0.07
    🍶
    -0.07
    POSITIVE LOGITS
    וכ
    0.07
    callee
    0.07
    byter
    0.07
    _Profile
    0.07
    招聘会
    0.06
    穿越
    0.06
     효과
    0.06
    刘邦
    0.06
    .chdir
    0.06
    (op
    0.06
    Act Density 0.004%

    No Known Activations