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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal and political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.61
    ortium
    -0.59
    arnaev
    -0.56
    Ĭ±
    -0.55
     Prix
    -0.54
    vre
    -0.53
    lein
    -0.52
     Jub
    -0.51
    ACTED
    -0.50
    abase
    -0.49
    POSITIVE LOGITS
     therapy
    0.68
     sickness
    0.66
    bending
    0.64
    bugs
    0.63
     buffs
    0.63
     avoidance
    0.62
     regulators
    0.62
     aggregation
    0.61
     regulation
    0.61
     commissions
    0.61
    Act Density 0.519%

    No Known Activations