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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     spoil
    -0.71
    oda
    -0.63
    ument
    -0.62
    adic
    -0.61
    gettable
    -0.61
    tery
    -0.60
    kind
    -0.60
    iliated
    -0.58
    lé
    -0.57
    ifty
    -0.57
    POSITIVE LOGITS
     Nightmares
    0.79
    ãģ®å®
    0.79
     Roose
    0.78
     Hed
    0.77
    FORE
    0.72
    ãģ®ç
    0.70
    vP
    0.70
    æ©Ł
    0.69
    Maker
    0.69
    Desktop
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.