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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Groups
    -0.07
    emente
    -0.07
     все
    -0.06
     asshole
    -0.06
    (am
    -0.06
    党委
    -0.06
     million
    -0.06
    _NAME
    -0.06
    Apellido
    -0.06
    ced
    -0.06
    POSITIVE LOGITS
     있는데
    0.07
     frec
    0.07
     relev
    0.07
     MX
    0.07
     Lux
    0.07
     Evalu
    0.07
     wc
    0.07
    🎏
    0.07
    לין
    0.07
    oklyn
    0.06
    Act Density 0.080%

    No Known Activations