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

    Neuronpedia

    INDEX
    Explanations

    numerical data, such as statistics or percentages

    oai_token-act-pair · gpt-3.5-turbo

    quantitative or statistical data presented in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mimic
    -0.72
     consistency
    -0.69
    anus
    -0.68
     performer
    -0.67
     pudding
    -0.67
     roam
    -0.67
    anyl
    -0.66
     sidel
    -0.66
     attacker
    -0.66
     dancing
    -0.65
    POSITIVE LOGITS
    00
    1.17
    5
    1.08
    25
    1.04
    75
    1.03
    04
    1.02
    99
    1.02
    06
    1.01
    07
    1.01
    7
    1.00
    05
    1.00
    Act Density 0.109%

    No Known Activations