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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     exha
    -0.81
     proport
    -0.75
     encount
    -0.74
    vae
    -0.72
    etheus
    -0.70
     reluct
    -0.69
     enthusi
    -0.68
    */(
    -0.68
    ön
    -0.68
     Sag
    -0.66
    POSITIVE LOGITS
    Desk
    0.77
     Dragonbound
    0.74
     Deal
    0.66
     Caucus
    0.66
    Deb
    0.64
     Knock
    0.64
    UGH
    0.63
     Transition
    0.63
     mine
    0.63
     Pound
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.