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

    Neuronpedia

    INDEX
    Explanations

    terms related to dungeons and role-playing games

    oai_token-act-pair · gpt-3.5-turbo

    references to dungeons or related concepts in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.75
    henko
    -0.71
     FTA
    -0.67
    hovah
    -0.67
     Debor
    -0.66
    vant
    -0.65
    LM
    -0.63
    ciation
    -0.62
     iod
    -0.62
     PROV
    -0.61
    POSITIVE LOGITS
    geons
    0.97
     craw
    0.95
     crawling
    0.93
     dungeons
    0.89
    geon
    0.89
     crawl
    0.89
     dungeon
    0.82
     Dungeon
    0.82
    Leaks
    0.82
     raiding
    0.79
    Act Density 0.010%

    No Known Activations