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

    Neuronpedia

    INDEX
    Explanations

    references to the Niagara Falls and related experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     плав
    -0.15
    harma
    -0.14
     Licht
    -0.14
    ød
    -0.14
    _DISK
    -0.14
    _VARS
    -0.14
    midt
    -0.14
    opher
    -0.14
    iola
    -0.13
    æ³Ĭ
    -0.13
    POSITIVE LOGITS
     falls
    0.41
     Falls
    0.40
    falls
    0.35
     waterfall
    0.34
     Niagara
    0.31
     Casc
    0.27
     FALL
    0.26
     water
    0.26
     casc
    0.26
     falling
    0.25
    Act Density 0.032%

    No Known Activations