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

    Neuronpedia

    INDEX
    Explanations

    instances of modal verbs and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inhoud
    -0.54
     câte
    -0.54
     الرياضيه
    -0.53
     maș
    -0.50
     gevallen
    -0.49
     bună
    -0.49
     metálica
    -0.48
     jongen
    -0.48
    seamnă
    -0.48
     noastră
    -0.47
    POSITIVE LOGITS
     Arrangement
    0.48
     Thema
    0.47
     Engagement
    0.46
    createCanvas
    0.42
     Highlight
    0.42
     Studium
    0.41
    mathematical
    0.40
    parsedMessage
    0.40
     Stadium
    0.40
     Setup
    0.40
    Act Density 0.042%

    No Known Activations