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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social class division and polarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ounter
    -0.18
    argas
    -0.17
    aghetti
    -0.16
    alleries
    -0.15
    olume
    -0.15
    olley
    -0.14
    aub
    -0.14
    veau
    -0.14
    ewire
    -0.14
     breadcrumb
    -0.14
    POSITIVE LOGITS
     division
    0.27
    division
    0.23
     differences
    0.22
    åĪĨ
    0.22
     separation
    0.22
     difference
    0.21
     divide
    0.20
     dividing
    0.20
     divisions
    0.20
     partition
    0.20
    Act Density 0.316%

    No Known Activations