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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oretically
    0.89
    ない
    0.84
    ться
    0.84
    depart
    0.84
    lma
    0.76
    امن
    0.75
     paragra
    0.74
    iidae
    0.73
    audio
    0.73
    ెస్
    0.73
    POSITIVE LOGITS
     heirloom
    0.86
     такой
    0.82
    м
    0.80
     understands
    0.80
     loves
    0.77
     dole
    0.77
     lask
    0.77
     какой
    0.76
     которую
    0.76
     состояния
    0.75
    Act Density 0.004%

    No Known Activations