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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning societal norms and addressing racial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LLocation
    -0.61
    owohl
    -0.59
    apimachinery
    -0.58
    cheinend
    -0.57
     noqa
    -0.56
    verwijspagina
    -0.54
    ätie
    -0.53
    ʒ
    -0.52
    inaire
    -0.51
    tangentMode
    -0.51
    POSITIVE LOGITS
     Савезне
    0.52
     panne
    0.48
     Chwiliwch
    0.47
    meyen
    0.46
     Danemark
    0.45
     corners
    0.44
    Попис
    0.43
     nowhere
    0.43
    Autoritní
    0.43
     kneeling
    0.43
    Act Density 0.312%

    No Known Activations