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

    Neuronpedia

    INDEX
    Explanations

    words related to playing or events related to performing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to playing games or game mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agan
    -0.66
    aul
    -0.66
     vou
    -0.66
     absorbed
    -0.65
     embarked
    -0.65
     transfer
    -0.64
    «ĺ
    -0.63
     collected
    -0.62
    gie
    -0.61
     planes
    -0.60
    POSITIVE LOGITS
    theless
    1.08
    playing
    1.03
    Playing
    0.92
    tenance
    0.89
    WARE
    0.85
     Playing
    0.84
    plays
    0.83
    DragonMagazine
    0.82
    \<
    0.82
    TextColor
    0.80
    Act Density 0.011%

    No Known Activations