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

    Neuronpedia

    INDEX
    Explanations

    json-like structures and syntax elements, indicating it is focused on extracting or recognizing data formats and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢħ
    -0.25
    âĢ¦.
    -0.24
    âĢIJ
    -0.23
    âĢ¦the
    -0.23
    âĢij
    -0.23
    –
    -0.23
    âĢ¦
    -0.23
    âĢ¦and
    -0.21
    ÂŃ
    -0.21
    .âĢ¦
    -0.21
    POSITIVE LOGITS
     {↵
    0.18
     {}↵
    0.18
     /*
    0.18
     {!!
    0.17
     /**
    0.17
     %%↵
    0.17
     /*!
    0.17
     ;;↵
    0.17
     ){↵
    0.16
     @{↵
    0.16
    Act Density 7.446%

    No Known Activations