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

    Neuronpedia

    INDEX
    Explanations

    hierarchical structures and power dynamics within social systems

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ting
    -0.45
    Interstitial
    -0.43
    Ñĥ
    -0.41
    DonaldTrump
    -0.39
    CTV
    -0.39
     Wonderland
    -0.39
    ties
    -0.37
    Madison
    -0.37
    MK
    -0.37
    GA
    -0.36
    POSITIVE LOGITS
    onym
    0.56
    onymous
    0.56
    ogly
    0.47
    archs
    0.46
     hierarchy
    0.46
    archy
    0.46
     theoret
    0.45
     Hier
    0.43
    achy
    0.42
    arch
    0.41
    Act Density 0.196%

    No Known Activations