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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and programming-related keywords like 'boost', 'char' and 'URI'

    oai_token-act-pair · gpt-3.5-turbo

    less-than signs and associated symbols, typically used in markup or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Polk
    -0.68
     clock
    -0.63
     Rodgers
    -0.61
     Peterson
    -0.60
     laps
    -0.59
     pronounce
    -0.56
     compound
    -0.55
     practices
    -0.55
     Guer
    -0.55
     spectacular
    -0.55
    POSITIVE LOGITS
    <
    3.94
     <
    2.30
    <?
    2.28
    .<
    2.21
    </
    2.04
    <<
    1.94
     "<
    1.76
    \<
    1.75
     <[
    1.69
    ><
    1.68
    Act Density 0.014%

    No Known Activations