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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    xual
    -1.05
    raid
    -0.88
    avorite
    -0.78
    redd
    -0.75
    endish
    -0.75
    oeuv
    -0.75
    ollah
    -0.74
    ptive
    -0.71
    door
    -0.71
    ey
    -0.70
    POSITIVE LOGITS
    bie
    0.67
    itiz
    0.66
     horizont
    0.62
     Grants
    0.61
     Caucasus
    0.60
     Garrett
    0.57
     Gru
    0.57
     Sheridan
    0.57
     Gou
    0.57
     joins
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.