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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ems
    -0.72
     downgrade
    -0.68
    aber
    -0.68
    iour
    -0.68
    iggurat
    -0.67
     bounded
    -0.66
     tho
    -0.64
    ades
    -0.63
     overpowered
    -0.62
    emic
    -0.62
    POSITIVE LOGITS
    AFTA
    0.75
    å£
    0.66
    spawn
    0.64
    estern
    0.63
    meat
    0.63
    gart
    0.63
     Veterinary
    0.62
     Au
    0.61
    ãģĤ
    0.61
    vasive
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.