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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    selves
    -0.66
     Filipino
    -0.63
     Manila
    -0.62
    new
    -0.58
    NEW
    -0.58
    court
    -0.58
    _-
    -0.57
     lease
    -0.57
    street
    -0.57
    glass
    -0.57
    POSITIVE LOGITS
    wic
    0.81
    ayers
    0.79
    eri
    0.75
     plunged
    0.72
    uton
    0.69
    encer
    0.68
     Kob
    0.67
    olith
    0.66
    ÄŁ
    0.65
    obbies
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.