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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Suc
    -0.79
     FTA
    -0.70
     Tribune
    -0.68
     Cabrera
    -0.68
     Gutierrez
    -0.66
     Ars
    -0.64
     DH
    -0.63
     Giov
    -0.63
     Discover
    -0.62
    ¢
    -0.62
    POSITIVE LOGITS
     life
    0.90
     warr
    0.83
    ģ«
    0.81
     "$:/
    0.80
    izoph
    0.77
     behavi
    0.76
    £
    0.74
     conclud
    0.73
    ¨
    0.72
    ²
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.