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

    Neuronpedia

    INDEX
    Explanations

    phrases related to modal verbs and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.38
     beschä
    -0.38
     urgently
    -0.36
     geldi
    -0.36
    ########.
    -0.36
     compared
    -0.35
     dulu
    -0.35
     опубликова
    -0.35
     phased
    -0.35
     çıktı
    -0.35
    POSITIVE LOGITS
    된
    0.62
    lanan
    0.59
     kurulan
    0.55
    された
    0.55
     olan
    0.53
     olev
    0.53
    한
    0.49
     bezeichneter
    0.47
     edilen
    0.47
     occurring
    0.47
    Act Density 0.096%

    No Known Activations