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

    Neuronpedia

    INDEX
    Explanations

    specific sections or parts of a document

    oai_token-act-pair · gpt-3.5-turbo

    references to distinct sections within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.74
    Iv
    -0.70
    ILLE
    -0.67
    claimed
    -0.66
     opio
    -0.66
    aukee
    -0.64
     monetary
    -0.63
     gripping
    -0.62
    Fel
    -0.60
     Bridges
    -0.60
    POSITIVE LOGITS
     sections
    0.85
    enium
    0.82
    witz
    0.80
    edin
    0.77
    ĸļ
    0.75
    osaurs
    0.75
    crew
    0.73
    opus
    0.73
    arians
    0.73
    lation
    0.73
    Act Density 0.011%

    No Known Activations