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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political events and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    references to context and circumstances surrounding events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wine
    -0.82
     yourselves
    -0.72
     ourselves
    -0.68
    bish
    -0.67
     Yourself
    -0.65
    ovy
    -0.62
    acky
    -0.62
    ilian
    -0.62
     fabulous
    -0.62
    upiter
    -0.61
    POSITIVE LOGITS
    âĢ
    1.85
     âĢ
    1.49
    ãĢ
    1.26
    âĸº
    1.21
    âĸł
    1.17
    âĢł
    1.14
    ¨
    1.14
    »
    1.13
    âĶ
    1.09
    îĢ
    1.08
    Act Density 0.554%

    No Known Activations