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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ayn
    -0.82
    arre
    -0.78
    yn
    -0.77
    byter
    -0.74
    jah
    -0.74
     awoken
    -0.72
    Ô
    -0.71
    ookie
    -0.69
    ays
    -0.69
    ylum
    -0.65
    POSITIVE LOGITS
     Veh
    0.77
     Solitaire
    0.67
     bulls
    0.66
    cube
    0.66
     Directions
    0.65
    PDATE
    0.64
     Sponsor
    0.62
    ESA
    0.61
    crew
    0.61
    strap
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.