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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pling
    -0.90
    inho
    -0.84
    achev
    -0.80
    PET
    -0.79
    interstitial
    -0.75
    oney
    -0.74
    inet
    -0.73
    iod
    -0.72
    rals
    -0.72
    otle
    -0.71
    POSITIVE LOGITS
     Shin
    0.72
     Panic
    0.71
     Aut
    0.71
     Collider
    0.69
     Trib
    0.69
     Curiosity
    0.68
     Bullet
    0.67
     Chase
    0.66
     Fault
    0.66
     Lifetime
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.