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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arts
    -0.75
    reon
    -0.71
    inter
    -0.68
    auri
    -0.67
    parts
    -0.67
    evil
    -0.67
    ãĤ¬
    -0.66
    ios
    -0.65
    letters
    -0.65
    Rex
    -0.63
    POSITIVE LOGITS
     fairly
    0.73
     relatively
    0.72
     moderately
    0.71
     sizeable
    0.70
     nom
    0.68
    versive
    0.67
     small
    0.67
     sizable
    0.66
     calibrated
    0.65
     slight
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.