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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political controversy and policy decisions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.66
    Accès
    -0.57
    Mə
    -0.55
    providedIn
    -0.55
    Largeur
    -0.55
    Poids
    -0.53
    ագրություններ
    -0.53
    Personensuche
    -0.51
    Longueur
    -0.50
    Exemples
    -0.50
    POSITIVE LOGITS
     photographe
    0.72
     getty
    0.72
     curé
    0.71
     élève
    0.70
     gti
    0.68
     jaya
    0.68
     Docteur
    0.67
     vainqueur
    0.66
     gué
    0.65
     jajaja
    0.64
    Act Density 0.121%

    No Known Activations