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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    orsi
    -0.74
    GP
    -0.72
     hindsight
    -0.66
     comrade
    -0.61
    andowski
    -0.60
     Lamp
    -0.58
     comrades
    -0.58
    inho
    -0.58
     Patron
    -0.56
     Sven
    -0.55
    POSITIVE LOGITS
    ://
    2.93
    :/
    1.08
    :\
    0.86
    ËĪ
    0.82
    ="/
    0.77
    ={
    0.73
    http
    0.72
    =\"
    0.71
    www
    0.70
    https
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.