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

    Neuronpedia

    INDEX
    Explanations

    names of sports teams and their respective cities or players

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports teams and athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rodu
    -0.67
    arters
    -0.66
    antry
    -0.61
    hea
    -0.60
    ubb
    -0.59
    amily
    -0.59
    vironments
    -0.58
    ivation
    -0.58
    eworthy
    -0.57
    pee
    -0.57
    POSITIVE LOGITS
     counterpart
    0.83
     playbook
    0.73
     connection
    0.71
     glove
    0.70
     teammate
    0.69
     counterparts
    0.69
     dictator
    0.68
     analogy
    0.65
     colleague
    0.65
     merger
    0.65
    Act Density 0.494%

    No Known Activations