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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ration
    -0.83
    oise
    -0.74
     Vald
    -0.73
    oration
    -0.72
    aching
    -0.72
    oulos
    -0.70
    borg
    -0.68
    Rachel
    -0.68
    acers
    -0.68
    ached
    -0.67
    POSITIVE LOGITS
    nexus
    0.81
     lane
    0.72
     unexplained
    0.63
     brow
    0.61
     CPC
    0.61
     carpet
    0.61
    anmar
    0.61
    uggle
    0.60
     Mub
    0.60
     Continent
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.