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

    Neuronpedia

    INDEX
    Explanations

    symbols and indicators of mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.81
    SBATCH
    -0.61
    PMailer
    -0.53
     Niz
    -0.53
    principalColumn
    -0.50
     typelib
    -0.49
    WriteLiteral
    -0.49
     discogs
    -0.49
    arakat
    -0.48
    RTLU
    -0.48
    POSITIVE LOGITS
    riwal
    0.66
    Extinguishing
    0.56
    serviceWorker
    0.56
    thâu
    0.54
    mybatisplus
    0.53
    uker
    0.50
    entas
    0.49
    //*[@
    0.49
     &___
    0.48
    \}\\
    0.48
    Act Density 0.164%

    No Known Activations