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

    Neuronpedia

    INDEX
    Explanations

    programming and code-related syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     пÑĢож
    -0.16
    опаÑģ
    -0.15
    aro
    -0.15
    ritz
    -0.15
     knights
    -0.14
     strip
    -0.14
     knight
    -0.14
     inbound
    -0.14
    (Optional
    -0.13
     Vander
    -0.13
    POSITIVE LOGITS
     ret
    0.35
    ret
    0.33
    _ret
    0.31
     Ret
    0.31
    -ret
    0.30
    (ret
    0.29
    .ret
    0.29
     exit
    0.29
     EXIT
    0.28
     Exit
    0.28
    Act Density 0.106%

    No Known Activations