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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cin
    -0.86
    eport
    -0.80
    omsky
    -0.78
    ammers
    -0.76
    ramids
    -0.76
    aghetti
    -0.75
    rontal
    -0.74
    abulary
    -0.74
    reads
    -0.73
    uture
    -0.71
    POSITIVE LOGITS
     illum
    0.65
     encour
    0.62
     Preferred
    0.62
     goodness
    0.60
     Creator
    0.60
     forthcoming
    0.59
    Reviewed
    0.59
     earthly
    0.58
     Leader
    0.58
     fav
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.