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

    Neuronpedia

    INDEX
    Explanations

    coding-related operations involving concatenation and data modification expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pig
    -0.17
    pj
    -0.15
    ToF
    -0.15
    pip
    -0.14
     Clint
    -0.14
    inal
    -0.14
    mek
    -0.14
    aju
    -0.14
    inality
    -0.13
    avras
    -0.13
    POSITIVE LOGITS
    _compat
    0.16
    .usermodel
    0.16
    ervo
    0.15
    428
    0.14
    igli
    0.14
    846
    0.14
    Äįel
    0.13
    387
    0.13
     Lag
    0.13
    389
    0.13
    Act Density 0.027%

    No Known Activations