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

    Neuronpedia

    INDEX
    Explanations

    individuals or groups with specific characteristics or attributes, such as levels of experience, knowledge, power, money, or personal backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups possessing money or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecause
    -0.59
     Relax
    -0.59
    Aren
    -0.59
     indefinitely
    -0.58
    rame
    -0.56
    eatures
    -0.56
    ATCH
    -0.56
    cham
    -0.55
     again
    -0.54
     segregated
    -0.54
    POSITIVE LOGITS
     penchant
    0.96
     backgrounds
    0.94
     pedigree
    0.94
     knack
    0.90
     disabilities
    0.89
     affinity
    0.88
     stature
    0.87
     histories
    0.86
     flair
    0.86
     propensity
    0.86
    Act Density 0.399%

    No Known Activations