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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lake
    -0.20
     river
    -0.19
     lakes
    -0.18
     Lakes
    -0.17
     River
    -0.16
    River
    -0.16
     Jungle
    -0.16
     Lake
    -0.16
     jungle
    -0.16
     Nile
    -0.15
    POSITIVE LOGITS
     puff
    0.24
     Isles
    0.20
    otland
    0.19
     Atlantic
    0.19
     Setter
    0.18
    Atlantic
    0.18
    CAPE
    0.18
     Outer
    0.18
     Islanders
    0.17
     Islands
    0.17
    Act Density 0.013%

    No Known Activations