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

    Neuronpedia

    INDEX
    Explanations

    words related to society and various societal aspects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.60
    Picture
    -0.59
    à¥
    -0.58
    CLOSE
    -0.58
     looph
    -0.56
    come
    -0.56
    ailable
    -0.56
    AND
    -0.55
    uckland
    -0.54
    Reloaded
    -0.54
    POSITIVE LOGITS
     alike
    1.97
     respectively
    1.70
     versa
    0.94
     thereof
    0.88
     attRot
    0.78
     industries
    0.76
     thereafter
    0.76
     sectors
    0.76
     afterward
    0.72
    .).
    0.70
    Act Density 0.640%

    No Known Activations