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

    Neuronpedia

    INDEX
    Explanations

    references to waterfalls and water-related features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    genodigd
    -0.60
    ientras
    -0.58
    iosync
    -0.58
     enfans
    -0.57
    ſelves
    -0.57
     <<<<<<<<<<<<<<
    -0.54
     Económica
    -0.54
     otomatig
    -0.54
    MemoryWarning
    -0.53
     dieux
    -0.53
    POSITIVE LOGITS
     waterfall
    0.79
     waterfalls
    0.68
    waterfall
    0.66
     Waterfall
    0.66
     Falls
    0.56
     cascade
    0.54
    瀑布
    0.51
     FALLS
    0.48
     cascada
    0.45
     cascades
    0.45
    Act Density 0.219%

    No Known Activations