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

    Neuronpedia

    INDEX
    Explanations

    structured data or syntax patterns within code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.87
     yến
    -0.84
     réserver
    -0.83
     intptr
    -0.82
    TestingModule
    -0.81
     ddelweddau
    -0.81
     שוליים
    -0.80
    最快更新
    -0.77
    </tfoot>
    -0.74
    --)
    -0.74
    POSITIVE LOGITS
    ://
    0.55
     آبی
    0.49
     ujednoznacz
    0.49
    ExtendWith
    0.49
    <eos>
    0.49
    sizeCache
    0.48
     precisamente
    0.46
    underbrace
    0.46
    ↵
    0.44
     trách
    0.44
    Act Density 0.173%

    No Known Activations