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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various groups of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.66
     arteries
    -0.64
    Ħ¢
    -0.63
    èª
    -0.61
     artery
    -0.61
     Pradesh
    -0.59
     Basin
    -0.58
     veins
    -0.57
     Cathedral
    -0.56
     Highest
    -0.55
    POSITIVE LOGITS
    members
    1.01
     members
    0.97
    mates
    0.92
    think
    0.91
    leader
    0.89
     member
    0.88
    roups
    0.87
    Members
    0.83
    member
    0.80
    mate
    0.76
    Act Density 0.055%

    No Known Activations