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

    Neuronpedia

    INDEX
    Explanations

    words related to game turns and actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "turn" and its variations in the context of gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ropolitan
    -0.94
    è¦ļéĨĴ
    -0.79
    inately
    -0.79
    foundation
    -0.72
    llah
    -0.70
    capacity
    -0.70
    mble
    -0.68
     Photographer
    -0.66
    namese
    -0.65
     franc
    -0.64
    POSITIVE LOGITS
    buck
    0.90
    about
    0.81
    turn
    0.77
    edit
    0.73
    aho
    0.71
    abouts
    0.71
    undo
    0.70
    overs
    0.69
    ibility
    0.68
     rob
    0.68
    Act Density 0.028%

    No Known Activations