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

    Neuronpedia

    INDEX
    Explanations

    phrases related to authority or directives from a higher power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political manipulation or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrasts
    -0.73
    elaide
    -0.69
    mopolitan
    -0.67
    float
    -0.66
    Studies
    -0.65
     fossils
    -0.64
    izons
    -0.63
    Decre
    -0.63
     overfl
    -0.63
     wildfires
    -0.62
    POSITIVE LOGITS
     superiors
    1.13
     management
    1.12
     supervisors
    1.11
     supervisor
    1.08
     administrators
    1.05
     manag
    1.05
     admins
    1.03
     overse
    1.02
     managers
    1.01
     administrator
    1.00
    Act Density 1.189%

    No Known Activations