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

    Neuronpedia

    INDEX
    Explanations

    specific references to time, primarily indicating the night or day

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OCK
    -0.71
    Edge
    -0.70
    atre
    -0.66
    ollo
    -0.65
    rahim
    -0.64
    MX
    -0.63
    ãĥĥãĥĪ
    -0.61
    Null
    -0.61
    pee
    -0.60
    hin
    -0.59
    POSITIVE LOGITS
     night
    1.46
     day
    1.43
     evening
    1.40
     afternoon
    1.36
     morning
    1.30
     fateful
    1.30
     week
    1.25
     month
    1.24
     year
    1.22
     weekend
    1.14
    Act Density 0.130%

    No Known Activations