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

    Neuronpedia

    INDEX
    Explanations

    references to swimming safety and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xcb
    -0.15
    .Internal
    -0.15
     Dust
    -0.14
    ANJI
    -0.14
    å°ĺ
    -0.14
     boÅŁ
    -0.14
     dust
    -0.14
    æľºåľº
    -0.14
    xCC
    -0.14
     snowy
    -0.14
    POSITIVE LOGITS
     swim
    0.60
     swimming
    0.57
     Swimming
    0.50
     Swim
    0.50
     swims
    0.43
     float
    0.39
     pool
    0.39
    æ³³
    0.38
     flotation
    0.36
    -sw
    0.35
    Act Density 0.336%

    No Known Activations