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

    Neuronpedia

    INDEX
    Explanations

    references to professional interactions and etiquette in business settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.85
    sizeCache
    -0.70
     GenerationType
    -0.70
    featureID
    -0.65
     صوتيه
    -0.65
    GEBURTSDATUM
    -0.65
    providedIn
    -0.63
    Pautan
    -0.63
     esternos
    -0.61
     autorytatywna
    -0.61
    POSITIVE LOGITS
     happier
    0.67
     avoids
    0.63
     avoid
    0.62
     safer
    0.61
     healthier
    0.61
     chances
    0.60
     smoother
    0.58
     maximizes
    0.55
     reassured
    0.55
     assuré
    0.54
    Act Density 0.215%

    No Known Activations