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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kindred
    -0.77
     longitudinal
    -0.68
     fasting
    -0.65
     pse
    -0.64
     calming
    -0.62
     ubiquitous
    -0.62
     masc
    -0.61
     appellate
    -0.61
     constitutionally
    -0.59
     benches
    -0.59
    POSITIVE LOGITS
    resses
    0.80
     Collider
    0.77
    ovie
    0.76
     Haku
    0.75
    hack
    0.74
    ipedia
    0.74
    aton
    0.71
    SHIP
    0.70
    Sov
    0.69
    atable
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.