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

    Neuronpedia

    INDEX
    Explanations

    social and political issues, such as governance, relationships, and cultural dynamics

    oai_token-act-pair · gpt-3.5-turbo

    references to societal structures and critiques of cultural norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.73
    ovember
    -0.68
     Ank
    -0.67
     Backup
    -0.65
     Lucky
    -0.63
     Booster
    -0.63
     PHOTO
    -0.63
     Downing
    -0.62
     Bullets
    -0.62
     Reloaded
    -0.61
    POSITIVE LOGITS
     ideals
    0.84
     thereby
    0.83
     doctrines
    0.83
     dogma
    0.81
     notions
    0.80
     inherently
    0.80
     inherent
    0.79
     morality
    0.76
     discriminating
    0.76
     abstract
    0.76
    Act Density 0.967%

    No Known Activations