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

    Neuronpedia

    INDEX
    Explanations

    references to waterfalls and related water features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     heir
    -0.15
    UILD
    -0.15
     Lane
    -0.15
    æ³Ĭ
    -0.15
    lane
    -0.14
     warmth
    -0.14
    ød
    -0.14
    dock
    -0.14
    inea
    -0.14
    uild
    -0.14
    POSITIVE LOGITS
     falls
    0.32
     casc
    0.31
     Falls
    0.30
     Niagara
    0.29
     rap
    0.29
     waterfall
    0.28
     cascade
    0.28
    falls
    0.28
     Casc
    0.25
     drops
    0.25
    Act Density 0.025%

    No Known Activations