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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and attractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     canoe
    -0.17
     Snake
    -0.17
     snake
    -0.17
    Snake
    -0.16
     downstream
    -0.16
     valley
    -0.16
    lier
    -0.15
    Å¡ka
    -0.15
     River
    -0.15
     Rivers
    -0.15
    POSITIVE LOGITS
     beach
    0.42
     surf
    0.39
     Beach
    0.39
     beaches
    0.33
     Surf
    0.32
     surfing
    0.29
     sands
    0.29
     sand
    0.29
     waves
    0.28
     wave
    0.28
    Act Density 0.380%

    No Known Activations