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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions such as days, weeks, and months

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or frequencies of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otto
    -0.70
    resy
    -0.66
    arton
    -0.64
    UCT
    -0.64
    ociate
    -0.64
    ItemTracker
    -0.63
    anamo
    -0.62
    emort
    -0.62
    URES
    -0.62
    aleb
    -0.61
    POSITIVE LOGITS
     thereafter
    1.17
     throughout
    0.86
    night
    0.82
     until
    0.80
     except
    0.78
     since
    0.76
     during
    0.74
    til
    0.74
     imaginable
    0.73
     regardless
    0.73
    Act Density 0.071%

    No Known Activations