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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ip
    0.89
     tabs
    0.84
     playbook
    0.80
    :,
    0.77
     oscill
    0.76
    (:
    0.76
     imputed
    0.76
    ?
    0.76
     alp
    0.75
     ?
    0.74
    POSITIVE LOGITS
    更为
    0.88
    ബരി
    0.85
    isinde
    0.85
    ič
    0.84
    ب
    0.84
    क्राम
    0.83
    اده
    0.82
    iminary
    0.82
    たちは
    0.81
    imming
    0.80
    Act Density 0.000%

    No Known Activations