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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions or rights, particularly 'privileges'

    oai_token-act-pair · gpt-4-turbo

    phrases related to legal rights and regulations, particularly those concerning medical practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or official permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ning
    -0.73
    skip
    -0.70
    forth
    -0.69
    ality
    -0.68
    NING
    -0.68
    allo
    -0.68
    block
    -0.68
    ns
    -0.67
    ALLY
    -0.66
    worm
    -0.66
    POSITIVE LOGITS
    poons
    1.19
    ktop
    1.08
    uits
    1.00
    ayers
    0.97
    poon
    0.91
    raints
    0.90
    ighting
    0.89
    hare
    0.88
    ettings
    0.88
    oft
    0.86
    Act Density 0.028%

    No Known Activations