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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating personal engagement or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supérieures
    -0.65
     automatiques
    -0.63
     käns
    -0.61
     avoient
    -0.60
     élevées
    -0.58
     hjär
    -0.57
     mariée
    -0.55
     vocale
    -0.54
     spéciaux
    -0.54
     idéia
    -0.53
    POSITIVE LOGITS
     prepares
    1.18
     prepare
    1.06
     progresses
    1.01
     continue
    0.97
     continues
    0.96
     nears
    0.91
    Tembelea
    0.79
     Prepare
    0.78
     Continue
    0.78
     preparations
    0.78
    Act Density 0.186%

    No Known Activations