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

    Neuronpedia

    INDEX
    Explanations

    phrases related to benefiting or gaining an advantage

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gaining benefits or advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.97
    channelAvailability
    -0.76
    pole
    -0.72
    IFE
    -0.72
    mouth
    -0.69
    actionDate
    -0.68
    fing
    -0.66
    Nap
    -0.64
    sf
    -0.62
    zona
    -0.61
    POSITIVE LOGITS
    Reward
    0.72
     hindsight
    0.72
     ATI
    0.65
     deferred
    0.65
     exploiting
    0.65
     outweigh
    0.64
     diminished
    0.64
    vertisement
    0.64
     Samar
    0.63
     riches
    0.62
    Act Density 0.145%

    No Known Activations