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

    Neuronpedia

    INDEX
    Explanations

    terms related to visibility or lack thereof, particularly in contexts involving trust and impartiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vôtre
    -0.78
     éduc
    -0.75
     honte
    -0.75
     écout
    -0.74
     وتسجيلات
    -0.73
     spécifique
    -0.72
     imprimée
    -0.71
     respectivement
    -0.70
     servici
    -0.70
     abstrait
    -0.69
    POSITIVE LOGITS
     China
    0.69
     sim
    0.67
     SIM
    0.64
    CG
    0.63
     resourceCulture
    0.62
    cg
    0.61
    SIM
    0.61
     Chinese
    0.59
    ngdoc
    0.58
    aring
    0.58
    Act Density 0.149%

    No Known Activations