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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating specific temporal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤ¿
    -0.15
    ãĥªãĤ«
    -0.14
     accord
    -0.14
     fare
    -0.14
     Tale
    -0.14
    üz
    -0.13
    ário
    -0.13
     Serious
    -0.13
     cls
    -0.13
    hood
    -0.13
    POSITIVE LOGITS
    utenberg
    0.17
    æĪ
    0.15
    iest
    0.15
    annes
    0.15
    æģĭ
    0.14
    óng
    0.14
    igrams
    0.14
    inaire
    0.14
    entin
    0.14
    ismus
    0.14
    Act Density 0.032%

    No Known Activations