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

    Neuronpedia

    INDEX
    Explanations

    dates that follow a specific format

    oai_token-act-pair · gpt-3.5-turbo

    references to the age of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.83
    andise
    -0.82
    liga
    -0.80
    orney
    -0.80
    ellation
    -0.77
    enzie
    -0.77
    herical
    -0.75
    akens
    -0.75
    awaru
    -0.74
    anooga
    -0.74
    POSITIVE LOGITS
    th
    0.94
    26
    0.84
    31
    0.82
    27
    0.80
    37
    0.80
    00
    0.79
    25
    0.79
    33
    0.78
    66
    0.76
    214
    0.76
    Act Density 0.018%

    No Known Activations