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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "program" along with various expressions of "real" or related sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    feld
    -0.15
    ÑĩаÑĤ
    -0.15
    erece
    -0.14
    rence
    -0.14
    }());↵
    -0.14
    ChartData
    -0.14
    à¥ģश
    -0.14
    çİĦ
    -0.14
    getti
    -0.14
     batt
    -0.14
    POSITIVE LOGITS
    (:
    0.17
     intent
    0.17
     subroutine
    0.16
    ìĿ´ìĸ´
    0.16
    logical
    0.16
    ynn
    0.16
     Fort
    0.16
     Jacqu
    0.15
     &↵
    0.15
    intent
    0.15
    Act Density 0.016%

    No Known Activations