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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions involving durations of days, weeks, hours, and months

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egu
    -0.81
    alg
    -0.64
    ranch
    -0.63
    gall
    -0.61
    hest
    -0.60
    owler
    -0.60
    emort
    -0.60
    natureconservancy
    -0.60
     VIDEOS
    -0.59
    enko
    -0.59
    POSITIVE LOGITS
     straight
    1.09
     afterward
    1.02
     consecut
    0.96
     afterwards
    0.95
     uninterrupted
    0.94
     apiece
    0.92
     beforehand
    0.90
     thereafter
    0.89
     consecutive
    0.88
     ago
    0.84
    Act Density 0.085%

    No Known Activations