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

    Neuronpedia

    INDEX
    Explanations

    words related to organizational structures and ranking systems

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social structures and hierarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Gl
    -0.77
    null
    -0.74
    ib
    -0.71
    bs
    -0.70
     Faith
    -0.70
    Faith
    -0.69
     Gore
    -0.69
    alone
    -0.69
    words
    -0.66
    shows
    -0.65
    POSITIVE LOGITS
     hierarchy
    1.31
    xual
    1.13
     hierarch
    1.03
     structure
    0.88
     pyramid
    0.87
     tiers
    0.84
     hierarchical
    0.78
     precedence
    0.78
    chwitz
    0.77
    MpServer
    0.77
    Act Density 0.014%

    No Known Activations