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

    Neuronpedia

    INDEX
    Explanations

    content related to video game characters and battles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     centrally
    -0.58
     eleph
    -0.57
     proble
    -0.56
    abwe
    -0.53
    handler
    -0.52
     fingerprint
    -0.51
     thrott
    -0.48
     barr
    -0.47
     responds
    -0.47
     careg
    -0.47
    POSITIVE LOGITS
     Brawl
    0.72
    Gamer
    0.62
     onwards
    0.60
     Worlds
    0.57
     Legends
    0.57
     Skies
    0.56
     Mortal
    0.56
     Rarity
    0.56
     Console
    0.55
     Quake
    0.54
    Act Density 9.034%

    No Known Activations