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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    majority
    -0.77
    rage
    -0.74
    volt
    -0.73
    ynski
    -0.73
    bay
    -0.71
    å¿
    -0.70
    aban
    -0.67
    threat
    -0.63
    awk
    -0.63
    exper
    -0.62
    POSITIVE LOGITS
    terness
    0.72
    ©¶æ
    0.69
    ibilities
    0.67
     pairs
    0.66
     rot
    0.64
    WithNo
    0.63
    ð
    0.61
     constructor
    0.61
    ption
    0.61
    iar
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.