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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antino
    -0.15
    odule
    -0.15
    ye
    -0.15
    ajan
    -0.15
    kul
    -0.15
    unde
    -0.14
     :↵
    -0.14
    oll
    -0.14
     Barr
    -0.14
    å±ħ
    -0.14
    POSITIVE LOGITS
    itempty
    0.20
     json
    0.18
    ãĥ¼ãĥª
    0.16
    json
    0.16
    eum
    0.16
    adox
    0.16
    BitFields
    0.16
    omitempty
    0.15
     bson
    0.15
    ,json
    0.15
    Act Density 0.002%

    No Known Activations