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

    Neuronpedia

    INDEX
    Explanations

    phrases related to groups or teams

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to groups of people or teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lly
    -0.73
    cape
    -0.73
    uations
    -0.71
    initions
    -0.70
    let
    -0.69
    phase
    -0.69
    uer
    -0.68
    runtime
    -0.67
    catentry
    -0.67
    tesy
    -0.67
    POSITIVE LOGITS
     explorers
    0.98
     adventurers
    0.95
     volunteers
    0.94
     advisors
    0.92
     advisers
    0.91
     strangers
    0.90
     scholars
    0.89
     thinkers
    0.89
     sorts
    0.88
     robbers
    0.86
    Act Density 0.128%

    No Known Activations