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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    conservancy
    -0.83
    ashtra
    -0.83
    hedon
    -0.82
    Constructed
    -0.77
    én
    -0.76
    rolet
    -0.76
    etsk
    -0.76
    nai
    -0.75
     \'
    -0.75
    egal
    -0.74
    POSITIVE LOGITS
     regress
    0.84
     Seah
    0.70
     shif
    0.66
     martial
    0.66
     skeletal
    0.65
     eyeb
    0.64
     aging
    0.64
     regression
    0.63
    ©¶æ¥µ
    0.62
     medium
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.