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

    Neuronpedia

    INDEX
    Explanations

    phrases related to underground locations and activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of underground structures or environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cific
    -0.79
    lda
    -0.77
    ño
    -0.75
    awed
    -0.75
    Äĩ
    -0.75
    eln
    -0.75
    ============
    -0.74
    ointed
    -0.74
    neapolis
    -0.73
    ======
    -0.73
    POSITIVE LOGITS
     tunnels
    0.98
     cavern
    0.97
     labyrinth
    0.96
     workings
    0.91
     passages
    0.91
    ranean
    0.91
     bunker
    0.90
     condu
    0.90
     Railroad
    0.89
     Bunker
    0.87
    Act Density 0.048%

    No Known Activations