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

    Neuronpedia

    INDEX
    Explanations

    elements related to gaming mechanics and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.18
    Stride
    -0.18
    overn
    -0.16
    bic
    -0.15
    Fold
    -0.15
    Fight
    -0.15
     pari
    -0.15
     stabbing
    -0.15
    æŃ©
    -0.14
    .localized
    -0.14
    POSITIVE LOGITS
     Lives
    0.26
     lives
    0.23
     Bonus
    0.22
     bonus
    0.21
     score
    0.19
     scoring
    0.19
     bonuses
    0.19
     Score
    0.18
     obstacles
    0.18
     screen
    0.18
    Act Density 0.049%

    No Known Activations