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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    haps
    -0.75
    Rog
    -0.69
    Dou
    -0.67
    tie
    -0.66
     unfocusedRange
    -0.66
    jury
    -0.66
    Kings
    -0.65
    hair
    -0.65
    lain
    -0.64
    $$$$
    -0.63
    POSITIVE LOGITS
     Copenhagen
    0.73
    iatus
    0.70
     Phantom
    0.70
    catentry
    0.70
     Xie
    0.69
     Kosovo
    0.69
     pretext
    0.67
     Kus
    0.66
     Rohingya
    0.66
     Dh
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.