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

    Neuronpedia

    INDEX
    Explanations

    names or handles on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    Twitter handles and social media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tha
    -0.71
     cumbers
    -0.71
     bragging
    -0.69
     orphans
    -0.64
     heights
    -0.64
     \"
    -0.63
     upgr
    -0.62
     accelerated
    -0.61
    )",
    -0.61
     Ended
    -0.61
    POSITIVE LOGITS
    <|endoftext|>
    1.01
    odcast
    0.99
    _.
    0.98
    official
    0.93
    NFL
    0.92
    biz
    0.92
    Follow
    0.91
    dp
    0.89
    Jr
    0.89
    NBA
    0.87
    Act Density 0.062%

    No Known Activations