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

    Neuronpedia

    INDEX
    Explanations

    numerical references related to court cases or legal citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urat
    -0.19
    urr
    -0.16
    -urlencoded
    -0.16
    kok
    -0.15
    gren
    -0.15
    asion
    -0.15
    akter
    -0.15
    buat
    -0.15
    pytest
    -0.15
    inder
    -0.15
    POSITIVE LOGITS
     wax
    0.16
     beating
    0.15
     FAR
    0.15
     Guardian
    0.15
     Barcl
    0.14
     Wax
    0.14
     force
    0.14
    ISE
    0.14
     Mig
    0.13
    ORA
    0.13
    Act Density 0.014%

    No Known Activations