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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social media posts and public remarks

    oai_token-act-pair · gpt-3.5-turbo

    instances of public remarks and complaints related to social media controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JV
    -0.74
    elsen
    -0.68
    prus
    -0.68
    asio
    -0.67
     dilig
    -0.67
    BSD
    -0.67
     longitudinal
    -0.67
     hinge
    -0.66
     stagn
    -0.65
    ggles
    -0.65
    POSITIVE LOGITS
     blasp
    1.08
     inappropriate
    1.00
     derogatory
    0.99
     insulting
    0.97
     nudity
    0.94
     falsely
    0.94
     inappropriately
    0.94
     lewd
    0.94
     pornographic
    0.93
     offending
    0.91
    Act Density 0.583%

    No Known Activations