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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pha
    -0.15
    ICODE
    -0.15
    ows
    -0.15
    Æ¡i
    -0.14
    aign
    -0.14
     åı¤
    -0.14
    esda
    -0.14
    abwe
    -0.14
    ằ
    -0.14
    amon
    -0.14
    POSITIVE LOGITS
     sh
    0.21
     Bour
    0.18
     echo
    0.17
     bash
    0.16
     touch
    0.16
     set
    0.16
     Bash
    0.15
    trap
    0.15
     exit
    0.15
     run
    0.14
    Act Density 0.040%

    No Known Activations