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

    Neuronpedia

    INDEX
    Explanations

    references to various fields and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abyrin
    -0.16
    ifter
    -0.16
    itu
    -0.16
    disp
    -0.15
    pt
    -0.15
    phere
    -0.15
    ategory
    -0.15
    eum
    -0.15
    é
    -0.15
    alli
    -0.14
    POSITIVE LOGITS
    work
    0.24
    crest
    0.23
    side
    0.21
    names
    0.20
    ed
    0.20
    sg
    0.18
     зÑĢениÑı
    0.17
    notes
    0.17
    ers
    0.17
    (Field
    0.17
    Act Density 0.037%

    No Known Activations