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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     awa
    -0.69
     tongues
    -0.65
    myra
    -0.65
     gamble
    -0.64
     Despair
    -0.63
    addons
    -0.63
    itters
    -0.62
     rejoice
    -0.61
     certainty
    -0.61
    uke
    -0.61
    POSITIVE LOGITS
    ORY
    0.79
    Ott
    0.79
    Dutch
    0.73
    ISA
    0.71
    ļéĨĴ
    0.70
    ãĥ¼ãĥ³
    0.67
    osc
    0.67
    isol
    0.67
    MAC
    0.66
    Bed
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.