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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     slips
    -0.33
     cin
    -0.30
     Fram
    -0.29
    HELL
    -0.27
    áf
    -0.27
    elow
    -0.27
    nock
    -0.26
    裱
    -0.26
     previously
    -0.25
    æĬĸ
    -0.25
    POSITIVE LOGITS
    ãģĻãĤĭãģ®ãģĮ
    0.26
    uide
    0.26
    ankan
    0.26
    ç§ij
    0.26
    bre
    0.25
     Feinstein
    0.25
    ç§ijæĬĢ
    0.25
    stein
    0.25
    ç²¾å¿ĥ
    0.25
    },{↵
    0.25
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.