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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the establishment of various kinds of relationships, communities, or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uen
    -0.15
    atter
    -0.14
    oa
    -0.14
    weets
    -0.14
    eler
    -0.14
    sted
    -0.14
     various
    -0.14
    ee
    -0.14
    alta
    -0.14
    ÃŃte
    -0.14
    POSITIVE LOGITS
    orton
    0.17
    aver
    0.17
    itu
    0.16
    лÑİ
    0.16
    636
    0.15
    ardy
    0.15
    EDI
    0.15
    vů
    0.14
    .boost
    0.14
    .Features
    0.14
    Act Density 0.088%

    No Known Activations