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

    Neuronpedia

    INDEX
    Explanations

    words related to players and users in a gaming or virtual environment

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals participating in gaming and narrative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arus
    -0.78
    ories
    -0.76
    ources
    -0.75
    hift
    -0.74
    ilon
    -0.74
    veyard
    -0.72
    hots
    -0.72
    Corp
    -0.70
    chwitz
    -0.69
    hell
    -0.68
    POSITIVE LOGITS
    's
    0.94
    ÃŃs
    0.87
     perce
    0.84
     palate
    0.75
     thirst
    0.71
     learns
    0.71
    ´
    0.70
     immersed
    0.70
     engaged
    0.70
     diseng
    0.70
    Act Density 0.206%

    No Known Activations