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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future plans or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.82
    ritical
    -0.70
    lights
    -0.68
    minus
    -0.67
     Explan
    -0.66
    eros
    -0.65
    worthy
    -0.64
     Passion
    -0.63
    cius
    -0.60
    problem
    -0.60
    POSITIVE LOGITS
     pursue
    1.06
     retire
    1.05
     continue
    1.03
     revise
    1.02
     utilize
    1.01
     explore
    0.98
     invest
    0.98
     spend
    0.98
     keep
    0.98
     marry
    0.96
    Act Density 0.088%

    No Known Activations