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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scoring and points in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anka
    -0.16
    orr
    -0.14
    icense
    -0.14
    abay
    -0.14
    elay
    -0.14
     Duty
    -0.14
    akat
    -0.13
     Monte
    -0.13
     world
    -0.13
    icens
    -0.13
    POSITIVE LOGITS
     bonus
    0.24
    bonus
    0.19
     bonuses
    0.19
    _bonus
    0.18
     award
    0.18
     reward
    0.18
     Bonus
    0.18
     scoring
    0.17
     rewards
    0.16
     penalty
    0.16
    Act Density 0.046%

    No Known Activations