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

    Neuronpedia

    INDEX
    Explanations

    legal and official announcements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to announcements or formal communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.60
    ustomed
    -0.58
     contrace
    -0.58
    ahime
    -0.55
    tu
    -0.55
    lain
    -0.54
    urat
    -0.54
    ãĤ¼ãĤ¦ãĤ¹
    -0.54
     revol
    -0.52
    inen
    -0.52
    POSITIVE LOGITS
    £ı
    0.66
     paragraph
    0.66
     omission
    0.66
     regarding
    0.64
     factual
    0.63
     clar
    0.63
     concise
    0.62
     clarify
    0.61
    behind
    0.61
    ©¶æ
    0.61
    Act Density 0.775%

    No Known Activations