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

    Neuronpedia

    INDEX
    Explanations

    information related to giveaways or promotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to giveaways or contests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.70
    olit
    -0.70
    amina
    -0.69
     stresses
    -0.68
     faults
    -0.68
     Gork
    -0.68
     warnings
    -0.66
     anchor
    -0.66
     deport
    -0.65
     sluggish
    -0.65
    POSITIVE LOGITS
     prizes
    1.30
    affle
    1.20
     prize
    1.17
     giveaway
    1.13
     Winners
    1.08
     coupon
    1.07
     winner
    1.05
     Prize
    1.05
     reward
    1.03
     Reward
    1.01
    Act Density 0.549%

    No Known Activations