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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ifiziert
    0.44
     repetitive
    0.42
     et
    0.39
     hebat
    0.39
    hend
    0.38
     fury
    0.38
    mx
    0.38
    力和
    0.37
    dir
    0.37
     repeats
    0.36
    POSITIVE LOGITS
    әр
    0.52
    在
    0.51
    Esto
    0.49
    薨
    0.48
    APAN
    0.48
    როს
    0.48
    Appeal
    0.48
    これは
    0.47
    Od
    0.47
    LaunchScheme
    0.47
    Act Density 0.009%

    No Known Activations