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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating submissions or requests for consideration or review

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HH
    -0.67
    LAB
    -0.67
    ]'
    -0.67
    âĶĢ
    -0.67
    NFL
    -0.66
    mare
    -0.66
    Learn
    -0.66
    edin
    -0.64
    ellen
    -0.64
    é¾
    -0.64
    POSITIVE LOGITS
    geries
    1.07
    gery
    1.06
    cible
    0.96
     purposes
    0.94
    bidden
    0.91
     sale
    0.90
     verification
    0.90
     consideration
    0.90
     clarification
    0.90
     clarity
    0.83
    Act Density 0.224%

    No Known Activations