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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters and battles

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and gameplay mechanics in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    espie
    -0.81
     mosqu
    -0.79
    coni
    -0.76
    mercial
    -0.74
     Siem
    -0.74
     eleph
    -0.73
    unicip
    -0.73
    negie
    -0.73
     Weiner
    -0.72
     horizont
    -0.71
    POSITIVE LOGITS
     dungeons
    1.20
    Battle
    1.18
    RPG
    1.17
     RPG
    1.16
     playable
    1.12
    battle
    1.11
     Summoner
    1.10
     dungeon
    1.08
     RPGs
    1.08
     Dungeons
    1.08
    Act Density 1.154%

    No Known Activations