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

    Neuronpedia

    INDEX
    Explanations

    mentions of water, liquid, and gas in a scientific or planetary context

    oai_token-act-pair · gpt-3.5-turbo

    references to water and its forms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.94
     Brand
    -0.75
    ettings
    -0.74
     adjourn
    -0.74
     showc
    -0.73
     Prevention
    -0.73
    ilitary
    -0.72
     Homeless
    -0.71
    asio
    -0.70
    stakes
    -0.69
    POSITIVE LOGITS
     molecules
    1.15
     deposits
    1.03
     particles
    1.00
     ejected
    0.98
     chunks
    0.97
     fragments
    0.97
     blob
    0.96
     molecule
    0.94
     residue
    0.90
     vap
    0.89
    Act Density 0.176%

    No Known Activations