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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     targ
    -0.80
    ords
    -0.77
    alert
    -0.64
    saf
    -0.64
     imprison
    -0.63
     JUSTICE
    -0.62
     incarcer
    -0.61
     abduct
    -0.61
     aliens
    -0.61
     Alive
    -0.60
    POSITIVE LOGITS
    ħĭ
    0.88
    boa
    0.82
    icum
    0.80
    Cas
    0.79
    antam
    0.78
     Tycoon
    0.78
    romeda
    0.75
    Interstitial
    0.74
    riad
    0.72
    ogun
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.