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

    Neuronpedia

    INDEX
    Explanations

    names of authors and contributors in reports or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to news reports and their contributors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sooner
    -0.69
     viz
    -0.62
     somet
    -0.62
     alot
    -0.59
     myster
    -0.56
    ?!"
    -0.55
     downright
    -0.53
     ensu
    -0.53
     coord
    -0.53
     boasted
    -0.53
    POSITIVE LOGITS
    <|endoftext|>
    1.23
    .;
    0.92
    .
    0.81
    .''.
    0.80
    .]
    0.74
    .*
    0.74
     Subscribe
    0.73
    .</
    0.72
    Copyright
    0.68
    .}
    0.68
    Act Density 0.213%

    No Known Activations