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

    Neuronpedia

    INDEX
    Explanations

    references to different religious and cultural identities

    oai_token-act-pair · gpt-3.5-turbo

    references to religious and political identities, particularly focused on Muslims and Republicans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.61
    uador
    -0.60
     Guan
    -0.57
    ]'
    -0.55
     Salv
    -0.53
    KER
    -0.53
     GOODMAN
    -0.53
     Rohing
    -0.52
     oneself
    -0.52
     extrad
    -0.52
    POSITIVE LOGITS
     counterparts
    1.07
     counterpart
    0.94
     brethren
    0.84
     selves
    0.80
     cousins
    0.79
     buddies
    0.77
     holdings
    0.75
     arsenal
    0.74
     cousin
    0.74
     ancestors
    0.72
    Act Density 0.801%

    No Known Activations