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

    Neuronpedia

    INDEX
    Explanations

    words related to abstract concepts or qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of belonging or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sites
    -0.81
    olicy
    -0.79
    iaries
    -0.76
    nces
    -0.75
    nets
    -0.72
     Tycoon
    -0.70
    ģĸ
    -0.69
    ials
    -0.69
    aughters
    -0.68
    ittees
    -0.68
    POSITIVE LOGITS
     urgency
    0.94
     warmth
    0.91
     humor
    0.91
     humour
    0.87
     intimacy
    0.81
     optimism
    0.80
     parity
    0.76
     bodily
    0.75
     realism
    0.75
     reckoning
    0.75
    Act Density 0.063%

    No Known Activations