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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    mentions of numerical values or identifiers related to votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellation
    -0.84
    liga
    -0.78
    ype
    -0.75
    anooga
    -0.74
    enzie
    -0.74
    orney
    -0.74
    ensed
    -0.72
    andise
    -0.72
    arios
    -0.70
    illation
    -0.70
    POSITIVE LOGITS
    th
    1.00
    00
    0.90
    26
    0.81
    017
    0.80
    650
    0.79
    66
    0.79
    31
    0.79
    teen
    0.78
    27
    0.78
    71
    0.78
    Act Density 0.041%

    No Known Activations