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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    деж
    -0.07
     advertis
    -0.07
     الز
    -0.07
    👁
    -0.07
    醮
    -0.06
    Cancellation
    -0.06
    iche
    -0.06
    失眠
    -0.06
     Jedi
    -0.06
    关停
    -0.06
    POSITIVE LOGITS
    astery
    0.08
     galer
    0.08
    都在
    0.07
    منظم
    0.07
    SWG
    0.07
     w
    0.07
    ✋
    0.07
    wi
    0.07
     Matcher
    0.06
     similarity
    0.06
    Act Density 0.002%

    No Known Activations