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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases describing political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hander
    -0.91
    ittee
    -0.88
    adder
    -0.87
    ortium
    -0.83
    iggurat
    -0.82
    orah
    -0.82
    cellent
    -0.80
    gdala
    -0.80
    linger
    -0.78
    along
    -0.78
    POSITIVE LOGITS
     scenarios
    1.43
     situations
    1.42
     environments
    1.34
     alternatives
    1.33
     setups
    1.25
     solutions
    1.24
     amounts
    1.23
     proportions
    1.23
     outcomes
    1.22
     behaviors
    1.22
    Act Density 0.263%

    No Known Activations