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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defects
    -0.67
    sole
    -0.66
     recoil
    -0.66
    enary
    -0.66
     unborn
    -0.64
     remission
    -0.64
    aterasu
    -0.64
    ittal
    -0.64
    benef
    -0.64
    aez
    -0.64
    POSITIVE LOGITS
     Facebook
    1.26
     Twitter
    1.25
     Youtube
    1.25
     Instagram
    1.25
     blogs
    1.24
    facebook
    1.20
    Twitter
    1.17
     facebook
    1.16
     YouTube
    1.16
     LinkedIn
    1.16
    Act Density 0.296%

    No Known Activations