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

    Neuronpedia

    INDEX
    Explanations

    mentions of teams or groups of people working together

    oai_token-act-pair · gpt-3.5-turbo

    mentions of teams and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forward
    -0.76
    tml
    -0.71
    Sov
    -0.66
     Franch
    -0.65
    ously
    -0.65
    Film
    -0.62
    fect
    -0.62
     Celeb
    -0.62
    ibrary
    -0.62
    mone
    -0.61
    POSITIVE LOGITS
    members
    1.25
     members
    1.09
    peak
    1.08
     mates
    1.03
    member
    1.00
     member
    0.99
    sters
    0.92
    rons
    0.90
    mates
    0.89
     Members
    0.85
    Act Density 0.066%

    No Known Activations