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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating high levels of certainty or potentiality

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating ability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.78
    CI
    -0.66
     Lis
    -0.62
    IL
    -0.60
     CI
    -0.59
     wherever
    -0.59
     Rolls
    -0.58
     announcements
    -0.58
     revolving
    -0.57
     Cutting
    -0.57
    POSITIVE LOGITS
     afford
    1.13
     comprehend
    1.00
     overcome
    0.94
     muster
    0.94
     convince
    0.92
     withstand
    0.90
     adequately
    0.89
     cope
    0.89
     conceive
    0.88
     justify
    0.88
    Act Density 0.134%

    No Known Activations