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

    Neuronpedia

    INDEX
    Explanations

    mentions of liquids, particularly liquid substances

    oai_token-act-pair · gpt-3.5-turbo

    references to different states or types of liquids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.73
    BOOK
    -0.70
    saf
    -0.69
    ^^^^
    -0.68
    reon
    -0.67
    CVE
    -0.65
     Commissioners
    -0.65
    OA
    -0.65
    ovation
    -0.63
     Bicycle
    -0.62
    POSITIVE LOGITS
     nitrogen
    1.11
    ation
    0.82
    itate
    0.82
     cooled
    0.80
     soup
    0.79
    atable
    0.79
     liquid
    0.77
    ocaust
    0.77
    izable
    0.76
     intellig
    0.76
    Act Density 0.023%

    No Known Activations