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

    Neuronpedia

    INDEX
    Explanations

    references to popular TV series and their related narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    203
    -0.17
    輪
    -0.16
    ropolis
    -0.16
    oodoo
    -0.16
    owie
    -0.15
     Illinois
    -0.15
     Hercules
    -0.15
    apore
    -0.14
    ANTA
    -0.14
     cmdline
    -0.14
    POSITIVE LOGITS
     HBO
    0.19
     Belfast
    0.18
     Game
    0.16
     Dro
    0.16
    elfast
    0.16
     Stark
    0.16
    \<^
    0.15
    Game
    0.15
     Roose
    0.15
    ì±ħ
    0.15
    Act Density 0.015%

    No Known Activations