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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.79
    Downloadha
    -0.78
     CM
    -0.71
     Tec
    -0.70
    steen
    -0.70
    éļ
    -0.69
    é¾įå
    -0.68
    bell
    -0.68
    "]=>
    -0.68
    »Ĵ
    -0.67
    POSITIVE LOGITS
     faked
    0.65
     diplomacy
    0.64
    oran
    0.62
    ................
    0.61
     infl
    0.58
     Spread
    0.57
     spreads
    0.57
     figures
    0.56
     spread
    0.56
     Defeat
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.