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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lass
    -0.96
    cro
    -0.84
    und
    -0.75
    CLASS
    -0.73
    illac
    -0.71
    vae
    -0.71
    Cass
    -0.70
    racuse
    -0.70
    plex
    -0.69
    Dial
    -0.69
    POSITIVE LOGITS
     Brig
    0.63
     Jiang
    0.62
     transmitted
    0.61
     Nasa
    0.60
     Japan
    0.59
     Goku
    0.59
     Telegram
    0.59
     Templar
    0.58
     Pyongyang
    0.58
     Tayyip
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.