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

    Neuronpedia

    INDEX
    Explanations

    comparisons or likelihoods of certain characteristics or behaviors between different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating comparative likelihoods or increases in probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    comings
    -0.90
    skirts
    -0.78
    rompt
    -0.73
     Lets
    -0.72
    ovie
    -0.71
    æ©
    -0.70
    adding
    -0.70
    facts
    -0.69
    agues
    -0.68
    agna
    -0.68
    POSITIVE LOGITS
     likely
    1.35
     than
    1.13
     prone
    1.07
    likely
    1.04
     susceptible
    1.03
     pronounced
    1.03
     Likely
    1.00
     prevalent
    0.98
     frequent
    0.97
     expensive
    0.95
    Act Density 0.146%

    No Known Activations