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

    Neuronpedia

    INDEX
    Explanations

    references to underwater environments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to underwater environments and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ============
    -0.90
    ioxide
    -0.89
    ========
    -0.89
    rar
    -0.84
    ques
    -0.83
    anan
    -0.77
    glers
    -0.77
    wan
    -0.76
    inton
    -0.76
    ku
    -0.76
    POSITIVE LOGITS
    eatures
    0.79
    stairs
    0.73
     landsl
    0.70
    comings
    0.70
     stairs
    0.69
     obstacle
    0.69
     prelim
    0.68
    gradation
    0.66
    ¥ŀ
    0.66
     satell
    0.66
    Act Density 0.048%

    No Known Activations