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

    Neuronpedia

    INDEX
    Explanations

    mentions of video games

    oai_token-act-pair · gpt-3.5-turbo

    references to video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     politic
    -0.85
    aye
    -0.73
    gencies
    -0.69
    aneously
    -0.66
    itudinal
    -0.65
    sie
    -0.64
     acknow
    -0.62
    aneous
    -0.62
     unnamed
    -0.58
    ALLY
    -0.58
    POSITIVE LOGITS
    manship
    1.25
    erver
    0.97
    OTA
    0.91
     consoles
    0.90
    chool
    0.88
    paces
    0.86
    cube
    0.85
    pad
    0.84
    pace
    0.79
    wright
    0.78
    Act Density 0.044%

    No Known Activations