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

    Neuronpedia

    INDEX
    Explanations

    terms related to swimming and its activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     malam
    -0.60
     Portman
    -0.60
             
    -0.60
     Dau
    -0.57
     précis
    -0.57
     Nom
    -0.57
    ☀
    -0.56
    ടു
    -0.56
                         
    -0.54
    rantes
    -0.54
    POSITIVE LOGITS
     swimming
    1.29
    swimming
    1.15
     Swimming
    1.10
    Swimming
    1.00
     فريبيس
    0.97
     swim
    0.95
     Swim
    0.94
    Swim
    0.92
    swim
    0.91
     swimmers
    0.90
    Act Density 0.100%

    No Known Activations