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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    離れ
    -0.08
    tipo
    -0.07
     lightning
    -0.07
    เทพ
    -0.07
    考え
    -0.07
    甥
    -0.07
    fee
    -0.07
    俍
    -0.06
    	de
    -0.06
    交际
    -0.06
    POSITIVE LOGITS
    =.
    0.07
    _fit
    0.07
    四
    0.07
    拥护
    0.07
    _space
    0.07
    _neighbors
    0.06
    =random
    0.06
    ors
    0.06
    _every
    0.06
    over
    0.06
    Act Density 0.067%

    No Known Activations