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

    Neuronpedia

    INDEX
    Explanations

    references to constraints and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     impression
    -0.18
     Milton
    -0.16
     compressed
    -0.15
    eti
    -0.15
     generally
    -0.15
     Frank
    -0.15
     til
    -0.15
     impressions
    -0.14
    baugh
    -0.14
    ucher
    -0.14
    POSITIVE LOGITS
    еÑĢин
    0.16
     presente
    0.15
    amu
    0.15
    esome
    0.14
    oes
    0.14
    ewater
    0.14
    ewise
    0.14
    меÑĩ
    0.14
    ep
    0.14
    Extent
    0.14
    Act Density 0.004%

    No Known Activations