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

    Neuronpedia

    INDEX
    Explanations

    words related to knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words indicating a lack of awareness or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ListItemIcon
    -0.60
    ](#
    -0.60
    期刊论文
    -0.56
    PhysRevLett
    -0.55
     Lust
    -0.54
     שוליים
    -0.53
    ądź
    -0.51
    Dieu
    -0.50
    છ
    -0.50
     }}^{\
    -0.48
    POSITIVE LOGITS
     unaware
    0.90
     unknowingly
    0.84
     oblivious
    0.75
    Rüyada
    0.74
    blind
    0.71
    GEBURTSDATUM
    0.69
    Blind
    0.67
     desconoc
    0.61
    webElementXpaths
    0.60
     ignorance
    0.59
    Act Density 0.251%

    No Known Activations