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

    Neuronpedia

    INDEX
    Explanations

    string literals and specific formatting characters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </em>
    -0.74
    </blockquote>
    -0.68
    ↵
    -0.66
     (
    -0.64
    ,
    -0.64
    </strong>
    -0.63
     
    -0.63
    ↵↵
    -0.63
    </h5>
    -0.61
     Don
    -0.59
    POSITIVE LOGITS
    ſelves
    1.23
     wikipagina
    1.23
     purpoſe
    1.21
     pleaſure
    1.20
     houſe
    1.18
    Portail
    1.14
     Jefus
    1.14
     myſelf
    1.13
     CreateTagHelper
    1.13
     ainfi
    1.13
    Act Density 0.037%

    No Known Activations