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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     conspir
    -0.65
     Fang
    -0.63
     Luk
    -0.60
     Lit
    -0.60
    eyes
    -0.60
     vind
    -0.58
    heit
    -0.58
    wagen
    -0.57
     attributed
    -0.57
     Sly
    -0.56
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.71
    æ©
    0.69
    ³³³³
    0.68
    entary
    0.68
    OUNT
    0.67
    ³³³³³³³³
    0.67
    Newsletter
    0.67
    Assembly
    0.66
    AMP
    0.66
    OOL
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.