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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    adi
    -0.71
     laun
    -0.68
    rive
    -0.68
    atar
    -0.68
    nexus
    -0.65
    dam
    -0.64
     dism
    -0.62
     compens
    -0.62
    adjust
    -0.60
     improv
    -0.60
    POSITIVE LOGITS
     Ibid
    0.67
     Citation
    0.61
     Primary
    0.61
     Bans
    0.61
     Gree
    0.60
     Gust
    0.59
     Armory
    0.59
     campuses
    0.59
     Judd
    0.57
     Freeze
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.