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

    Neuronpedia

    INDEX
    Explanations

    references to water in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anine
    -0.18
     æĪ
    -0.15
    aren
    -0.15
    oxide
    -0.15
    rvine
    -0.14
    دÙĬ
    -0.14
    è¦ı
    -0.14
    reff
    -0.14
    aeper
    -0.14
     dÄ±ÅŁÄ±
    -0.14
    POSITIVE LOGITS
    logged
    0.28
    melon
    0.24
    fall
    0.21
    color
    0.21
    falls
    0.21
    ways
    0.21
    bury
    0.21
    loo
    0.21
    works
    0.20
    borne
    0.20
    Act Density 0.026%

    No Known Activations