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

    Neuronpedia

    INDEX
    Explanations

    phrases related to people's names or titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific entity or name associated with "Her."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypes
    -0.74
    ————
    -0.73
    eering
    -0.70
    ozy
    -0.67
    ype
    -0.65
     Strauss
    -0.64
    eers
    -0.62
    éĹĺ
    -0.62
    govtrack
    -0.62
     Gutenberg
    -0.62
    POSITIVE LOGITS
    itage
    1.55
     Majesty
    1.33
    metic
    1.21
    ding
    1.18
    acl
    1.17
    mit
    1.14
    cule
    1.13
    itability
    1.12
    mits
    1.07
    bal
    1.03
    Act Density 0.041%

    No Known Activations