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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     of
    -0.08
     Bene
    -0.07
     Nur
    -0.07
     בעוד
    -0.06
    民心
    -0.06
     memberships
    -0.06
     setOpen
    -0.06
    蚕
    -0.06
    闾
    -0.06
    POCH
    -0.06
    POSITIVE LOGITS
     theory
    0.09
    烩
    0.08
     Theory
    0.07
     theories
    0.07
     Celtics
    0.07
     cooked
    0.07
     كرة
    0.07
    	real
    0.07
     proj
    0.07
    קים
    0.07
    Act Density 0.025%

    No Known Activations