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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bbw
    -0.07
    BarButton
    -0.07
     applies
    -0.07
     Myth
    -0.07
    荩
    -0.07
    _builder
    -0.07
    antically
    -0.06
    buffers
    -0.06
     Drawer
    -0.06
    .literal
    -0.06
    POSITIVE LOGITS
    כיוון
    0.08
    enas
    0.07
    _pago
    0.07
    erguson
    0.07
     sliding
    0.07
    接触
    0.07
     epoch
    0.07
     Want
    0.07
    "/>
↵
    0.06
    fähig
    0.06
    Act Density 0.021%

    No Known Activations