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

    Neuronpedia

    INDEX
    Explanations

    descriptions of landscapes and terrains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reek
    -0.16
     woodland
    -0.15
    ener
    -0.15
    azer
    -0.15
    736
    -0.15
     log
    -0.14
     building
    -0.13
    ä½ı
    -0.13
    adem
    -0.13
     deep
    -0.13
    POSITIVE LOGITS
     fields
    0.28
     land
    0.24
     lands
    0.23
    fields
    0.23
     landscape
    0.23
    Fields
    0.23
    -fields
    0.22
    FIELDS
    0.22
     flat
    0.22
     rolling
    0.22
    Act Density 0.167%

    No Known Activations