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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .steps
    -0.07
     shit
    -0.07
     сет
    -0.07
    Bits
    -0.07
    -white
    -0.06
    ==
    -0.06
    �
    -0.06
    “We
    -0.06
    ел
    -0.06
     tile
    -0.06
    POSITIVE LOGITS
    Paginator
    0.08
     predator
    0.07
     refuge
    0.07
     HOLDERS
    0.07
     FOX
    0.07
    (VALUE
    0.07
    _result
    0.07
    렧
    0.07
    (od
    0.06
    	opt
    0.06
    Act Density 0.001%

    No Known Activations