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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental policies and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     geschichten
    -0.17
     weiber
    -0.17
    iname
    -0.17
     jeg
    -0.16
     impost
    -0.16
     kvin
    -0.16
     piger
    -0.15
     dane
    -0.15
     ragaz
    -0.15
     kontakte
    -0.15
    POSITIVE LOGITS
     till
    0.27
     och
    0.22
     tv
    0.21
     exemp
    0.21
     prostituerade
    0.20
    iska
    0.20
     utf
    0.20
    ande
    0.20
     inte
    0.20
     efter
    0.19
    Act Density 0.259%

    No Known Activations