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

    Neuronpedia

    INDEX
    Explanations

    timespan references in days

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations measured in days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.83
    inav
    -0.78
    emort
    -0.78
    emale
    -0.76
    anooga
    -0.75
    icidal
    -0.71
    found
    -0.69
    urities
    -0.69
    este
    -0.68
    cientious
    -0.65
    POSITIVE LOGITS
     ago
    0.98
    pring
    0.93
    dream
    0.91
    ilver
    0.84
    hops
    0.84
    days
    0.81
    hift
    0.77
     elapsed
    0.74
    trip
    0.74
    care
    0.71
    Act Density 0.063%

    No Known Activations