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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    chie
    -0.71
    effic
    -0.70
    elong
    -0.67
    heter
    -0.67
    cyl
    -0.66
    ilan
    -0.65
    adder
    -0.64
    ilts
    -0.64
     persisted
    -0.63
    asy
    -0.63
    POSITIVE LOGITS
     Mori
    0.77
     weap
    0.70
     Krug
    0.69
    âĺ
    0.65
     Situation
    0.65
     Akin
    0.64
     spect
    0.63
    laughter
    0.63
     roy
    0.62
     Amend
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.