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

    Neuronpedia

    INDEX
    Explanations

    references to timelines or making early decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.16
    ouro
    -0.15
    mund
    -0.14
    ÙĨÚ¯
    -0.14
     pul
    -0.14
    ful
    -0.14
    illa
    -0.14
    aln
    -0.14
    ulf
    -0.14
     Miz
    -0.14
    POSITIVE LOGITS
     into
    0.24
     in
    0.22
    -on
    0.18
     doors
    0.18
     Doors
    0.17
     during
    0.17
     în
    0.17
    aneously
    0.16
    à¹Ĩ
    0.16
     enough
    0.16
    Act Density 0.024%

    No Known Activations