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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns for people and their social media handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tha
    -0.87
     cumbers
    -0.72
     accelerated
    -0.72
     longevity
    -0.70
     jaws
    -0.69
     emph
    -0.68
     regener
    -0.67
     reorgan
    -0.67
     ingred
    -0.67
     packaging
    -0.67
    POSITIVE LOGITS
    NBA
    1.14
    FB
    1.13
    DN
    1.12
    NFL
    1.10
    Blog
    1.08
    Jr
    1.08
    <|endoftext|>
    1.06
    BBC
    1.05
    PB
    1.05
    _.
    1.05
    Act Density 0.067%

    No Known Activations