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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social structures and systemic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fundamental
    -0.24
     Fundamental
    -0.18
    itive
    -0.18
    rade
    -0.18
    fund
    -0.17
    bred
    -0.15
     Acres
    -0.15
     Brock
    -0.15
     Brew
    -0.15
     fund
    -0.14
    POSITIVE LOGITS
    abil
    0.32
    ibil
    0.30
    bil
    0.22
    emat
    0.22
    ÑĸлÑĸ
    0.21
    antis
    0.21
    ativ
    0.20
     Kir
    0.20
    ibal
    0.19
    ometr
    0.18
    Act Density 0.141%

    No Known Activations