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

    Neuronpedia

    INDEX
    Explanations

    mentions of swimming and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to swimming activities and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.69
    eq
    -0.66
    oppers
    -0.66
    ________________________
    -0.65
     misplaced
    -0.64
     Engel
    -0.64
     stuffing
    -0.63
    orate
    -0.63
    relevant
    -0.63
    ________________________________________________________________
    -0.62
    POSITIVE LOGITS
     swimming
    1.04
     pools
    0.99
     pool
    0.91
     swim
    0.91
    pool
    0.89
     baths
    0.88
    suits
    0.86
    estone
    0.86
     Swim
    0.86
    halla
    0.85
    Act Density 0.008%

    No Known Activations