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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀ
    -0.14
     Raid
    -0.14
    oa
    -0.14
    769
    -0.14
    imet
    -0.14
    abilia
    -0.14
    aday
    -0.13
     unrelated
    -0.13
    iral
    -0.13
     cherry
    -0.13
    POSITIVE LOGITS
    ær
    0.17
     Dün
    0.16
    @js
    0.14
     Canter
    0.14
    κη
    0.14
     Wol
    0.14
     elgg
    0.14
    cket
    0.14
    ainty
    0.14
     nakne
    0.14
    Act Density 0.047%

    No Known Activations