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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ized
    0.67
     inoculated
    0.58
     degradation
    0.58
    ک
    0.57
     used
    0.57
     properties
    0.57
     exceeds
    0.56
     decompositions
    0.56
     quench
    0.56
     arrays
    0.55
    POSITIVE LOGITS
    itabbo
    0.68
    Ꮑ
    0.68
    躊
    0.66
    ちょっと
    0.66
    addAction
    0.65
     ))->
    0.64
    願
    0.64
     зді
    0.63
    さは
    0.63
    öglichkeiten
    0.63
    Act Density 0.062%

    No Known Activations