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

    Neuronpedia

    INDEX
    Explanations

    references to the sea and oceans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.69
    Tikang
    -0.68
     manier
    -0.66
     Kamu
    -0.65
                   
    -0.63
    kloped
    -0.62
     Fairbanks
    -0.62
     Primero
    -0.62
    aragus
    -0.61
    exitRule
    -0.61
    POSITIVE LOGITS
     Sea
    1.25
     SEA
    1.23
     sea
    1.19
    Sea
    1.10
     ocean
    1.08
    SEA
    1.03
    sea
    1.01
     Ocean
    1.01
     seaborn
    0.96
     seawater
    0.95
    Act Density 0.081%

    No Known Activations