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

    Neuronpedia

    INDEX
    Explanations

    references to figures and graphs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äįe
    -0.17
    ousel
    -0.16
    estar
    -0.15
     Magnus
    -0.14
    liÄį
    -0.14
    ibel
    -0.14
    uet
    -0.14
    oš
    -0.14
    uce
    -0.13
    aw
    -0.13
    POSITIVE LOGITS
    _macros
    0.16
    anki
    0.14
    lest
    0.14
    oplan
    0.14
    .scalablytyped
    0.14
     Sok
    0.14
    folio
    0.14
    аков
    0.13
    ansen
    0.13
    åIJ
    0.13
    Act Density 0.006%

    No Known Activations