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

    Neuronpedia

    INDEX
    Explanations

    instances of programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NUMX
    -1.27
    )";
    -1.22
    .",
    -1.21
    ^(@)
    -1.17
     $_"
    -1.17
    \<^
    -1.15
     ་་
    -1.14
    .")
    -1.14
    !")
    -1.12
    >\<^
    -1.11
    POSITIVE LOGITS
    ↵
    1.18
      
    1.02
     */
    0.84
     ->
    0.78
       
    0.78
    ↵↵
    0.77
    <eos>
    0.77
    */
    0.76
    </em>
    0.75
    ...
    0.74
    Act Density 0.199%

    No Known Activations