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

    Neuronpedia

    INDEX
    Explanations

    time-related references, specifically durations or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, specifically days and hours

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inburgh
    -0.77
    ortium
    -0.72
    ortment
    -0.68
    ificant
    -0.66
    uliffe
    -0.65
    vae
    -0.65
    orage
    -0.65
    XT
    -0.64
    achus
    -0.63
    ļé
    -0.62
    POSITIVE LOGITS
     ago
    0.94
     Ago
    0.87
     elapsed
    0.81
     apiece
    0.80
     consecut
    0.80
     olds
    0.72
    poons
    0.69
    é¾įå¥ij士
    0.69
     logged
    0.68
    days
    0.68
    Act Density 0.097%

    No Known Activations