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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing ability or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.78
     gynhyrchwyd
    -0.71
    expandindo
    -0.61
     withal
    -0.54
    idth
    -0.54
     OFDb
    -0.54
     aasta
    -0.53
     зовут
    -0.52
    Auszeichnungen
    -0.52
     fehlt
    -0.52
    POSITIVE LOGITS
     peut
    1.17
     puede
    1.15
     pueden
    1.14
    Puede
    1.12
     può
    1.11
     Pode
    1.10
    Pode
    1.09
     može
    1.07
     может
    1.07
    puede
    1.07
    Act Density 0.065%

    No Known Activations