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

    Neuronpedia

    INDEX
    Explanations

    elements related to image captions and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oku
    -0.15
    ingham
    -0.15
    lier
    -0.14
    737
    -0.14
     Boeh
    -0.14
     Sylv
    -0.14
     Chapter
    -0.14
     Chapters
    -0.14
    ochrome
    -0.13
     Daly
    -0.13
    POSITIVE LOGITS
    embed
    0.18
    untu
    0.18
     embed
    0.17
    cta
    0.16
    fusion
    0.16
    chg
    0.16
    arin
    0.16
    egin
    0.16
    .flink
    0.15
    akis
    0.15
    Act Density 0.334%

    No Known Activations