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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersist
    -0.15
     Nor
    -0.15
    OS
    -0.14
    phies
    -0.14
    ieber
    -0.14
     OS
    -0.13
     Duis
    -0.13
    âng
    -0.13
    οÏĤ
    -0.13
     Late
    -0.13
    POSITIVE LOGITS
    mann
    0.16
    umas
    0.15
    _APPEND
    0.15
    iaux
    0.15
    .Management
    0.15
    mans
    0.14
    geh
    0.14
    ancel
    0.14
    _macros
    0.14
    oin
    0.14
    Act Density 0.018%

    No Known Activations