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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.78
     Harriet
    -0.78
    yard
    -0.73
     Freed
    -0.72
    kees
    -0.71
    tumblr
    -0.71
     Nurs
    -0.70
     Dare
    -0.70
     Unleashed
    -0.70
    irez
    -0.70
    POSITIVE LOGITS
    anes
    0.72
     defenses
    0.69
     hubs
    0.63
     TBA
    0.63
    elin
    0.61
    DX
    0.60
     hub
    0.60
    comm
    0.60
     arr
    0.59
     burgeoning
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.