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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tm
    -0.90
    quartered
    -0.80
    OUP
    -0.78
    ITAL
    -0.76
    _-
    -0.74
    uci
    -0.74
    çīĪ
    -0.72
    ¹
    -0.72
    oup
    -0.71
    HO
    -0.71
    POSITIVE LOGITS
     predec
    0.66
    Forest
    0.65
     Christie
    0.65
     Livingston
    0.65
     Commun
    0.64
     Valiant
    0.62
     Saga
    0.62
     Byrne
    0.62
     Neutral
    0.61
    JUST
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.