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

    Neuronpedia

    INDEX
    Explanations

    references to photo credits

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation marks or end-of-text indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.96
     periodic
    -0.69
    bred
    -0.69
     correl
    -0.66
    yip
    -0.65
    onite
    -0.64
    amba
    -0.64
     obscurity
    -0.63
     giveaways
    -0.63
     respawn
    -0.63
    POSITIVE LOGITS
     Loading
    0.83
     Alternatively
    0.83
     Protesters
    0.82
     ï
    0.80
    <|endoftext|>
    0.76
     More
    0.76
     IMAGES
    0.76
     Videos
    0.76
    ↵
    0.76
     Similarly
    0.74
    Act Density 0.038%

    No Known Activations