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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.09
    3:0.08
    4:0.09
    5:0.08
    6:0.07
    7:0.08
    8:0.10
    9:0.07
    10:0.10
    11:0.07
    Negative Logits
    acters
    -1.73
     Slug
    -1.67
     Scouting
    -1.63
    risome
    -1.61
    oxin
    -1.60
    ongevity
    -1.58
     Signs
    -1.57
     Tracks
    -1.56
    Values
    -1.56
    Numbers
    -1.52
    POSITIVE LOGITS
    "}],"
    1.79
     pri
    1.71
     landlord
    1.70
    shi
    1.62
    ..........
    1.62
     cooperative
    1.56
     embattled
    1.56
     cooperating
    1.56
    �
    1.56
     hacker
    1.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.