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

    Neuronpedia

    INDEX
    Explanations

    code structure components like function calls, object attributes, and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵      ↵
    -0.20
    ↵  ↵
    -0.17
    ấp
    -0.17
    ÅĻet
    -0.17
    COPE
    -0.15
          ↵      ↵
    -0.15
     Fetish
    -0.15
    iners
    -0.15
    .SetString
    -0.15
    ÙĨز
    -0.14
    POSITIVE LOGITS
    0.34
    0.33
    0.28
        ↵
    0.26
    0.24
    0.23
            ↵
    0.20
    0.19
    0.19
    ↵    ↵
    0.19
    Act Density 0.158%

    No Known Activations