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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific prepositions and adverbs indicating spatial or temporal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upp
    -0.15
    ats
    -0.14
    ond
    -0.14
     Harden
    -0.14
    iflower
    -0.13
    urd
    -0.13
    ils
    -0.13
    ãĥķãĤ
    -0.13
    ÑĤÑĥ
    -0.13
     Dickinson
    -0.13
    POSITIVE LOGITS
    bens
    0.18
    vron
    0.15
    uxe
    0.15
    inis
    0.14
     Conte
    0.14
    zbek
    0.13
    vik
    0.13
    ensi
    0.13
     etiqu
    0.13
    odate
    0.13
    Act Density 0.231%

    No Known Activations