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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ̶
    -0.79
     Pose
    -0.74
     Balt
    -0.71
     Orn
    -0.70
     baskets
    -0.67
    pite
    -0.66
     Bash
    -0.65
     Gorge
    -0.65
    eatures
    -0.64
     Thumbnails
    -0.64
    POSITIVE LOGITS
    eter
    1.28
    edly
    0.79
     ¶
    0.78
    quer
    0.77
    cele
    0.74
    rum
    0.71
    official
    0.69
    lda
    0.68
    VK
    0.68
    patrick
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.