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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    each
    -0.85
    Bron
    -0.79
    ogie
    -0.75
    amphetamine
    -0.74
    hemy
    -0.69
    uckland
    -0.69
    arak
    -0.68
     Aden
    -0.68
    usercontent
    -0.67
    cair
    -0.67
    POSITIVE LOGITS
     flavorful
    0.67
     pse
    0.64
     surprises
    0.63
     customizable
    0.61
    nesses
    0.60
     hopeful
    0.60
     organisms
    0.59
     contenders
    0.59
     interpretations
    0.59
     spoiled
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.