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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    iliate
    -0.25
    -weight
    -0.25
    swing
    -0.25
     ÑģвÑıзан
    -0.24
    uition
    -0.24
    eyJ
    -0.24
    noinspection
    -0.24
    åĪ©çī©
    -0.24
    (&:
    -0.23
    æ·±åħ¥äººå¿ĥ
    -0.23
    POSITIVE LOGITS
    ffee
    0.29
    äºŀ
    0.27
    è´£
    0.26
    äºļ
    0.26
    \Modules
    0.25
    åĪº
    0.25
     smile
    0.25
    çĵ¦
    0.25
    awai
    0.25
    带åĽŀ
    0.24
    Act Density 0.158%

    No Known Activations

    This feature has no known activations.