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

    Neuronpedia

    INDEX
    Explanations

    references to dungeons or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    dungeons, prison, bondage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }))
    -0.45
     zufolge
    -0.43
     Vitae
    -0.42
    {*}
    -0.42
    ()")
    -0.41
    skraft
    -0.41
    ()}}
    -0.39
    ')).
    -0.39
    ()}>
    -0.39
    ")).
    -0.39
    POSITIVE LOGITS
     dungeon
    2.09
     Dungeon
    2.02
     dungeons
    1.83
    dungeon
    1.76
    Dungeon
    1.75
     Dungeons
    1.57
    ungeons
    1.36
    ungeon
    1.10
     prison
    0.83
     Prison
    0.81
    Act Density 0.001%

    No Known Activations