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

    Neuronpedia

    INDEX
    Explanations

    references to social inequalities and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apore
    -0.08
    alÄ±ÅŁ
    -0.07
     mercenaries
    -0.06
    ylvania
    -0.06
    isk
    -0.06
    _IA
    -0.06
    onde
    -0.06
    ANNER
    -0.06
    Margins
    -0.06
    prm
    -0.06
    POSITIVE LOGITS
     powerful
    0.15
     VIP
    0.14
     senior
    0.14
     politicians
    0.13
     high
    0.12
     highest
    0.12
     top
    0.12
     Powerful
    0.12
     important
    0.12
     higher
    0.12
    Act Density 0.050%

    No Known Activations