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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating familiarity or experience with various situations or topics

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal characteristics or tendencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.80
     Anthem
    -0.76
    idas
    -0.76
    alion
    -0.71
    etheus
    -0.69
    yan
    -0.68
    ciation
    -0.68
     Pact
    -0.65
     Kore
    -0.65
    ankind
    -0.64
    POSITIVE LOGITS
     tink
    0.89
     mischief
    0.84
     unpredict
    0.78
     bullies
    0.77
     surprises
    0.77
     fools
    0.77
     understatement
    0.77
     patience
    0.76
     unpredictable
    0.76
     humor
    0.75
    Act Density 0.466%

    No Known Activations