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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aque
    -0.67
    founded
    -0.66
    ãĤ«
    -0.65
    adem
    -0.62
    eri
    -0.61
    Sit
    -0.61
    ãĥ¼ãĥ
    -0.61
    ãĤĮ
    -0.61
    oul
    -0.58
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.58
    POSITIVE LOGITS
    hower
    0.83
    irlf
    0.73
     msec
    0.70
    arde
    0.69
     AFTER
    0.69
     Tanks
    0.69
    culosis
    0.69
    terday
    0.69
    soever
    0.65
    llular
    0.65
    Act Density 0.041%

    No Known Activations