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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific durations of time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "days"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.82
    inav
    -0.82
    emale
    -0.82
    anooga
    -0.81
    emort
    -0.80
    found
    -0.75
    tymology
    -0.75
    umbn
    -0.75
    ablished
    -0.68
    Reviewer
    -0.67
    POSITIVE LOGITS
     ago
    0.96
    days
    0.88
    pring
    0.88
    ilver
    0.87
    dream
    0.86
    trip
    0.76
    hift
    0.75
    DAY
    0.75
     Ago
    0.74
     elapsed
    0.72
    Act Density 0.057%

    No Known Activations