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

    Neuronpedia

    INDEX
    Explanations

    references to social and cultural identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħĸ
    -0.15
    маг
    -0.14
    acci
    -0.13
    âĻª↵↵
    -0.13
     Township
    -0.13
     csrf
    -0.13
     Dodd
    -0.13
    StringRef
    -0.12
    686
    -0.12
    ãĤĤãģ£ãģ¨
    -0.12
    POSITIVE LOGITS
     IK
    0.21
     MOD
    0.18
     congress
    0.17
     MEDIA
    0.16
     Loot
    0.16
     Mods
    0.15
     foolish
    0.15
     Shame
    0.15
     Mod
    0.15
     Sanity
    0.15
    Act Density 0.037%

    No Known Activations