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

    Neuronpedia

    INDEX
    Explanations

    descriptive terms related to geographical formations and caves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .LoggerFactory
    -0.15
     overposting
    -0.14
    folio
    -0.13
     toItem
    -0.13
    Ú¯ÙĦ
    -0.13
    į¼
    -0.13
     geri
    -0.12
    atched
    -0.12
    岸
    -0.12
    ecute
    -0.12
    POSITIVE LOGITS
     cave
    0.45
     underground
    0.44
     caves
    0.43
     cavern
    0.40
     Underground
    0.38
     tunnels
    0.37
     Cave
    0.37
     tunnel
    0.34
     spel
    0.33
     chambers
    0.30
    Act Density 0.060%

    No Known Activations