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

    Neuronpedia

    INDEX
    Explanations

    words related to competition, interaction, or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "play" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whisk
    -0.71
     overcrowd
    -0.69
    Ĭ±
    -0.67
    ournal
    -0.66
     overloaded
    -0.65
    pora
    -0.65
     balloon
    -0.65
    ailability
    -0.64
     popular
    -0.62
    £ı
    -0.60
    POSITIVE LOGITS
    ername
    1.07
    plays
    1.05
    play
    1.05
    wright
    0.97
    halla
    0.96
    ulations
    0.85
    gression
    0.84
    sylvania
    0.84
    hyde
    0.82
    figure
    0.82
    Act Density 0.008%

    No Known Activations