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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     restroom
    -0.67
     Genie
    -0.66
     wolves
    -0.65
     thefts
    -0.64
     gangs
    -0.63
     delinqu
    -0.62
     entrances
    -0.61
     childhood
    -0.61
     bathroom
    -0.60
     custody
    -0.60
    POSITIVE LOGITS
    itsch
    0.92
    Mos
    0.74
    Month
    0.70
    yip
    0.69
    ause
    0.69
    =-=-
    0.68
    ayer
    0.67
    oubted
    0.67
    figure
    0.66
    operator
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.