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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     cord
    -0.79
     actionGroup
    -0.72
     ment
    -0.66
     Tomorrow
    -0.66
     worn
    -0.65
     Cooking
    -0.64
     clos
    -0.63
     tentacles
    -0.63
     delayed
    -0.63
    cens
    -0.61
    POSITIVE LOGITS
    fty
    0.84
    kos
    0.81
    eem
    0.80
    GM
    0.77
    VR
    0.72
    efer
    0.71
    cos
    0.71
    ERAL
    0.68
    rium
    0.68
    ESE
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.