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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    00200000
    -0.74
     unison
    -0.71
     disadvant
    -0.70
    uner
    -0.69
    byss
    -0.69
    ãĥ´
    -0.68
    raviolet
    -0.67
     redress
    -0.67
    renheit
    -0.67
    fits
    -0.66
    POSITIVE LOGITS
     Dangerous
    0.66
    bean
    0.65
     Disapp
    0.62
    Episode
    0.62
     COUR
    0.61
     Related
    0.61
    LIST
    0.60
    walk
    0.59
    history
    0.58
    course
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.