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

    Neuronpedia

    INDEX
    Explanations

    instances of legal terminology and references to legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baum
    -0.16
    quist
    -0.15
    WARE
    -0.15
    croft
    -0.15
    ffi
    -0.14
    bere
    -0.14
     mdi
    -0.14
    wares
    -0.14
    builtin
    -0.14
     å£
    -0.13
    POSITIVE LOGITS
    419
    0.28
    论åĿĽ
    0.21
    åĵªéĩĮ
    0.19
    131
    0.19
    å¤ľ
    0.19
    楼
    0.18
    Integral
    0.18
     Integral
    0.18
    è´µ
    0.17
    yl
    0.16
    Act Density 0.002%

    No Known Activations