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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    atures
    -0.68
     Montana
    -0.66
    aunder
    -0.65
    plain
    -0.64
     keeper
    -0.62
     Moses
    -0.62
     Parade
    -0.61
     Painter
    -0.60
     conversions
    -0.58
     rebuild
    -0.58
    POSITIVE LOGITS
    ught
    0.79
    neys
    0.73
    IDA
    0.73
    Aud
    0.71
    itone
    0.69
    OPLE
    0.68
    jad
    0.67
    benefit
    0.66
    thal
    0.65
     absentee
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.