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

    Neuronpedia

    INDEX
    Explanations

    instances of code syntax and special characters related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.79
    •••
    -0.77
    er
    -0.74
    ++++++++++++++++
    -0.71
     Ratna
    -0.69
    судар
    -0.68
    AsUp
    -0.68
    ••••
    -0.65
     Beatty
    -0.64
     Kruse
    -0.62
    POSITIVE LOGITS
    :`
    1.29
    .`
    1.26
    =`
    1.24
    >`
    1.15
     (`
    1.13
    )`
    1.10
    ]`
    1.05
    (`
    1.04
    {`
    1.04
    })`
    1.03
    Act Density 0.330%

    No Known Activations