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

    Neuronpedia

    INDEX
    Explanations

    specific legal references and citations, often related to court cases or legal standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новниш
    -0.56
     CreateTagHelper
    -0.56
     '\\;'
    -0.55
    featureID
    -0.54
     ModelExpression
    -0.54
     rheumat
    -0.52
    ########.
    -0.52
    fjspx
    -0.51
    RTCF
    -0.50
     informée
    -0.50
    POSITIVE LOGITS
     ALEXANDER
    0.39
     Alexander
    0.39
     apologised
    0.38
     Rohr
    0.38
    pflan
    0.35
     plat
    0.35
     circun
    0.35
    Alexander
    0.34
     serre
    0.34
     kém
    0.34
    Act Density 2.767%

    No Known Activations