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

    Neuronpedia

    INDEX
    Explanations

    references to built-in features or components in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odie
    -0.15
    دÙĨ
    -0.15
    _Api
    -0.15
    ossa
    -0.14
    acco
    -0.14
    åIJ¾
    -0.14
    usz
    -0.14
    hay
    -0.14
    bose
    -0.13
    levator
    -0.13
    POSITIVE LOGITS
     Built
    0.26
     sẵn
    0.26
    Built
    0.25
    built
    0.23
     built
    0.23
    /embed
    0.22
    builtin
    0.20
     builtin
    0.19
    -built
    0.19
    .dex
    0.17
    Act Density 0.050%

    No Known Activations