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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Craigslist
    -0.80
    gging
    -0.76
    cius
    -0.74
    zn
    -0.70
    auld
    -0.69
    ppard
    -0.69
    hest
    -0.67
    ARC
    -0.67
    quit
    -0.67
     DPR
    -0.67
    POSITIVE LOGITS
     emphasis
    0.65
     Attribution
    0.64
    Child
    0.62
     Bar
    0.61
     æ
    0.59
     Telephone
    0.58
     recess
    0.58
    osponsors
    0.58
    Radio
    0.58
     EN
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.