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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and adverbs expressing possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kla
    -0.15
     Hlav
    -0.14
    ÏģαÏĤ
    -0.14
    ampie
    -0.14
    eward
    -0.14
    ithe
    -0.14
     Scotia
    -0.13
     segue
    -0.13
    едÑĮ
    -0.13
    dream
    -0.13
    POSITIVE LOGITS
     Refresh
    0.21
     refresh
    0.20
    Refresh
    0.20
    -refresh
    0.18
    refresh
    0.18
     resetting
    0.17
    _refresh
    0.17
    Refreshing
    0.17
    .Refresh
    0.17
    fill
    0.16
    Act Density 0.010%

    No Known Activations