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

    Neuronpedia

    INDEX
    Explanations

    references to social media and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urlencoded
    -0.52
     charset
    -0.51
    ($__
    -0.51
     Berber
    -0.49
     للاسماء
    -0.47
    قایناقلار
    -0.47
    GeneratedCode
    -0.46
    ुन
    -0.46
     csrf
    -0.46
    svr
    -0.45
    POSITIVE LOGITS
     Twitter
    1.20
     social
    1.16
     Facebook
    1.15
     Instagram
    1.12
     LinkedIn
    1.02
     twitter
    0.98
     Linkedin
    0.98
     sociala
    0.96
    Twitter
    0.95
    Facebook
    0.93
    Act Density 0.250%

    No Known Activations