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

    Neuronpedia

    INDEX
    Explanations

    keywords related to importance and intense emotions

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions related to significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iren
    -0.81
    viks
    -0.80
    Ñı
    -0.80
    姫
    -0.73
    orthy
    -0.72
    vik
    -0.71
    idel
    -0.70
    akespe
    -0.70
    endants
    -0.69
    atorial
    -0.68
    POSITIVE LOGITS
     Integrity
    0.92
     Efficiency
    0.92
     accessibility
    0.90
     mindfulness
    0.88
     mobility
    0.87
     homelessness
    0.83
     Attention
    0.82
     Transparency
    0.82
     Conversion
    0.81
     obesity
    0.80
    Act Density 0.576%

    No Known Activations