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

    Neuronpedia

    INDEX
    Explanations

    various instances of the word "team"

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alam
    -0.72
     Franch
    -0.71
    Film
    -0.67
    icted
    -0.66
    forward
    -0.62
     Authority
    -0.59
    ãģĦ
    -0.59
     Plate
    -0.58
    cott
    -0.57
     Celeb
    -0.57
    POSITIVE LOGITS
    members
    1.23
     members
    1.15
     member
    1.06
    member
    0.96
     mates
    0.96
    peak
    0.96
    liquid
    0.90
    sters
    0.89
     consisting
    0.85
    rons
    0.84
    Act Density 0.072%

    No Known Activations