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

    Neuronpedia

    INDEX
    Explanations

    references to swimming or related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to swimming and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oned
    -0.81
    naires
    -0.76
    relevant
    -0.72
    xual
    -0.69
    CRIP
    -0.65
    oning
    -0.65
     tense
    -0.64
    Reloaded
    -0.62
    ________________________________________________________________
    -0.61
     sender
    -0.61
    POSITIVE LOGITS
    suit
    1.11
    boat
    1.05
    suits
    1.03
    tub
    0.97
    maid
    0.93
     swimming
    0.92
     ashore
    0.92
     swim
    0.91
    boats
    0.91
     Swim
    0.90
    Act Density 0.028%

    No Known Activations