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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and verbs that indicate importance or attention in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Teddy
    -0.16
    /by
    -0.16
    iT
    -0.15
     itr
    -0.14
     Tir
    -0.14
    aset
    -0.14
     terr
    -0.14
    _approved
    -0.13
     Dram
    -0.13
     Juda
    -0.13
    POSITIVE LOGITS
    leted
    0.17
    ãĥ³ãĤº
    0.15
    ίκ
    0.15
    ousse
    0.15
    etten
    0.15
    ÏĦεÏį
    0.15
    orest
    0.14
     дÑĥмкÑĥ
    0.14
    elman
    0.14
    ноÑģÑĤ
    0.14
    Act Density 0.030%

    No Known Activations