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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    mit
    -0.67
    metic
    -0.65
    ophobia
    -0.65
    æĪ¦
    -0.65
    nesses
    -0.64
     capac
    -0.63
    aterial
    -0.61
    leep
    -0.60
     disapprove
    -0.59
    idelity
    -0.57
    POSITIVE LOGITS
    ĸļ
    0.83
     Muss
    0.72
    ĺħ
    0.71
     somew
    0.68
    arthed
    0.67
     Ambro
    0.66
    ONEY
    0.64
    alks
    0.63
     VIDE
    0.61
     Instructor
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.