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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gered
    -0.75
     Gaw
    -0.75
    forth
    -0.73
     contrace
    -0.70
     Ferdinand
    -0.67
    î
    -0.66
    outer
    -0.64
    phe
    -0.62
    angled
    -0.62
    CLE
    -0.62
    POSITIVE LOGITS
     similar
    0.78
    ornia
    0.72
    Story
    0.66
     Story
    0.66
     srf
    0.66
     compositions
    0.65
     similarities
    0.64
     unlocks
    0.63
    éŃĶ
    0.62
    hattan
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.