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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    IENT
    -0.70
     Ender
    -0.66
    iences
    -0.65
    orthy
    -0.64
    ience
    -0.64
    doms
    -0.64
     Shel
    -0.63
     hire
    -0.63
    ');
    -0.62
     Sly
    -0.61
    POSITIVE LOGITS
    £ı
    0.88
    ©¶æ
    0.85
    Ļ
    0.68
    ŃĶ
    0.68
    ģ«
    0.67
    Ķ
    0.66
    ļ
    0.64
     Qiao
    0.63
    okane
    0.63
    Ļ½
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.