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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters or symbols, suggesting a focus on non-alphanumeric elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @student
    -0.15
    legg
    -0.15
    ynes
    -0.14
    _dom
    -0.13
    groupid
    -0.13
    _ABI
    -0.13
    é¨
    -0.13
    eki
    -0.13
    abi
    -0.13
    дон
    -0.13
    POSITIVE LOGITS
     exposure
    0.17
     Exposure
    0.16
     pressing
    0.15
    essor
    0.15
    Own
    0.15
     Pe
    0.14
     Owner
    0.14
    GEN
    0.14
    udic
    0.14
    crest
    0.14
    Act Density 0.007%

    No Known Activations