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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     illustrating
    -0.74
     spoilers
    -0.73
     lengths
    -0.71
     pointers
    -0.69
    classes
    -0.69
     weaponry
    -0.68
     drawings
    -0.67
    aughs
    -0.67
    Interstitial
    -0.66
     trivia
    -0.66
    POSITIVE LOGITS
    Tier
    0.71
    Met
    0.71
    ktop
    0.69
    lda
    0.68
    /
    0.68
     Aires
    0.68
    Hen
    0.68
     FTA
    0.67
    itia
    0.66
    ãĤ£
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.