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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rities
    -0.71
    odes
    -0.70
    ©¶æ
    -0.69
    0000000000000000
    -0.66
    ostic
    -0.64
    orbit
    -0.64
    ouses
    -0.62
    ities
    -0.62
    ¿½
    -0.61
    uala
    -0.61
    POSITIVE LOGITS
    rer
    0.67
     tru
    0.65
    rench
    0.62
    ft
    0.61
     cla
    0.59
     pleading
    0.59
     iT
    0.59
    vern
    0.56
     fielding
    0.54
    ocene
    0.54
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.