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

    Neuronpedia

    INDEX
    Explanations

    references to deserts and related geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lish
    -0.16
    ningen
    -0.15
     Salmon
    -0.15
    sono
    -0.14
     trout
    -0.14
    ÙĬدÙĬ
    -0.14
    ISE
    -0.13
     ÐĴики
    -0.13
    Overflow
    -0.13
    æł
    -0.13
    POSITIVE LOGITS
     desert
    0.51
     Desert
    0.50
     Tucson
    0.31
     Sahara
    0.30
     Arizona
    0.28
     sand
    0.28
     Oasis
    0.27
     sands
    0.26
    Arizona
    0.26
     Mesa
    0.25
    Act Density 0.188%

    No Known Activations