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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time, specifically structured around time increments

    oai_token-act-pair · gpt-3.5-turbo

    punctuation related to timestamps or time indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     audits
    -0.69
     traders
    -0.69
     sights
    -0.64
    ancies
    -0.63
     monkeys
    -0.63
     drinkers
    -0.63
     overcl
    -0.61
    enegger
    -0.61
     seized
    -0.61
     scholars
    -0.60
    POSITIVE LOGITS
    large
    0.76
    icio
    0.72
    jpg
    0.72
    small
    0.69
    GHz
    0.69
    orbit
    0.68
    ama
    0.67
    mp
    0.67
    gran
    0.66
    pole
    0.66
    Act Density 0.045%

    No Known Activations