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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    م
    1.55
     staw
    1.24
     bashing
    1.23
     mo
    1.18
    <0xDC>
    1.13
    𝓽
    1.13
     scrapped
    1.12
    ଦ
    1.12
    reqParams
    1.11
    𝘴
    1.10
    POSITIVE LOGITS
    ilerin
    0.93
    ileri
    0.92
    icii
    0.91
     LTE
    0.91
    |=
    0.90
    vk
    0.90
    iegler
    0.87
    ilerden
    0.86
     skill
    0.84
     competente
    0.84
    Act Density 0.000%

    No Known Activations