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

    Neuronpedia

    INDEX
    Explanations

    mentions of societal issues and political ideologies

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.68
    Legend
    -0.67
    Located
    -0.63
    ogly
    -0.63
    Crew
    -0.61
    Custom
    -0.59
    çĶ°
    -0.59
    oji
    -0.59
     gy
    -0.58
    Pokemon
    -0.58
    POSITIVE LOGITS
     Chomsky
    1.00
     rhetorical
    0.86
     liberals
    0.85
     socialists
    0.84
     hypocrisy
    0.83
     principled
    0.81
     leftists
    0.80
     disingen
    0.80
     repud
    0.80
     perverse
    0.80
    Act Density 1.903%

    No Known Activations