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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference locations, specifically islands and related geographic terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gratis
    -0.17
     indeb
    -0.16
     oceans
    -0.15
    icerca
    -0.15
     seriousness
    -0.15
    inand
    -0.15
    'gc
    -0.15
    erç
    -0.14
    estate
    -0.14
    sono
    -0.14
    POSITIVE LOGITS
    endor
    0.17
    ushima
    0.15
    íĻĺ
    0.15
     islands
    0.14
     Island
    0.14
    ax
    0.14
    antu
    0.14
    aster
    0.14
    ìĦ
    0.14
    rosso
    0.14
    Act Density 0.009%

    No Known Activations