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

    Neuronpedia

    INDEX
    Explanations

    timestamps or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly occurrences of the word "earlier" in connection with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lua
    -0.67
    hop
    -0.64
    ysis
    -0.64
    alion
    -0.63
    odor
    -0.63
    drivers
    -0.63
     Riot
    -0.61
    helm
    -0.60
    eric
    -0.60
    rous
    -0.59
    POSITIVE LOGITS
    foundland
    0.88
     versions
    0.87
     generations
    0.82
    noon
    0.77
     editions
    0.77
     stages
    0.74
     than
    0.73
     installments
    0.72
    iations
    0.71
     evening
    0.70
    Act Density 0.029%

    No Known Activations