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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hedge
    -0.68
    akeru
    -0.66
    him
    -0.64
    hip
    -0.61
    artist
    -0.61
    ales
    -0.59
    ¶
    -0.59
    chance
    -0.59
    nels
    -0.58
    doctoral
    -0.58
    POSITIVE LOGITS
    ULE
    0.70
     same
    0.69
     compan
    0.68
    GBT
    0.68
    htar
    0.67
     bloated
    0.67
    ascript
    0.66
    ISION
    0.65
    amed
    0.63
    licts
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.