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

    Neuronpedia

    INDEX
    Explanations

    references to social dynamics and power structures among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /dialog
    -0.16
    otron
    -0.15
    isman
    -0.15
    ruba
    -0.15
    345
    -0.15
    ãĥķãĤ
    -0.14
    389
    -0.14
    elson
    -0.14
    issen
    -0.14
    afone
    -0.14
    POSITIVE LOGITS
     humans
    0.22
     Gift
    0.19
     abilities
    0.19
     powers
    0.19
     training
    0.18
     human
    0.18
     Council
    0.18
     Earth
    0.18
     Gifts
    0.17
     protections
    0.17
    Act Density 0.193%

    No Known Activations