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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     morale
    -0.70
     assassination
    -0.68
    cius
    -0.67
     prophes
    -0.66
    ħĭ
    -0.66
    holm
    -0.64
    é»Ĵ
    -0.64
     extermination
    -0.63
    peak
    -0.62
     comed
    -0.62
    POSITIVE LOGITS
    orest
    0.70
    ibur
    0.68
    escription
    0.68
     Registered
    0.66
    rying
    0.65
    ê
    0.62
    dx
    0.60
    swer
    0.59
    jo
    0.58
     Parables
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.