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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iaries
    -0.91
    soDeliveryDate
    -0.79
    galitarian
    -0.78
    gravity
    -0.74
    Narr
    -0.73
    trump
    -0.70
    iary
    -0.69
    ailable
    -0.67
    CAP
    -0.67
    paces
    -0.67
    POSITIVE LOGITS
     disc
    0.72
     blur
    0.65
     rash
    0.65
     livest
    0.60
     Saturday
    0.59
    byter
    0.59
     Sunday
    0.59
    las
    0.58
     Slov
    0.58
     Tur
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.