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

    Neuronpedia

    INDEX
    Explanations

    themes related to economics and political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal structures and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.79
    trak
    -0.78
    ikarp
    -0.78
    uve
    -0.71
    isode
    -0.69
     Nare
    -0.68
    hovah
    -0.67
    yip
    -0.67
    ersen
    -0.67
    handle
    -0.66
    POSITIVE LOGITS
     necessity
    1.30
     rationality
    1.27
     inev
    1.22
     causation
    1.20
     realism
    1.19
     indifference
    1.16
     realities
    1.16
     excellence
    1.15
     competence
    1.15
     righteousness
    1.14
    Act Density 0.239%

    No Known Activations