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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    antage
    -0.86
    akedown
    -0.78
    aeda
    -0.76
    acebook
    -0.73
    iage
    -0.73
    xtap
    -0.71
    addon
    -0.70
    aeper
    -0.68
    gage
    -0.68
    yrim
    -0.68
    POSITIVE LOGITS
     forth
    0.71
     visionary
    0.65
    chy
    0.64
    íķ
    0.63
    Reviewed
    0.62
     arrogant
    0.62
    ent
    0.61
    ought
    0.61
     cloud
    0.60
     emperor
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.