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

    Neuronpedia

    INDEX
    Explanations

    references to informal communication and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     helicopt
    -0.15
     wikipedia
    -0.14
    ugar
    -0.14
     Editors
    -0.14
     conven
    -0.14
    _FACTORY
    -0.14
    ÑĩаÑģ
    -0.13
    éķĩ
    -0.13
     Wikipedia
    -0.13
     gains
    -0.13
    POSITIVE LOGITS
     mus
    0.35
     Mus
    0.32
     thoughts
    0.29
     stuff
    0.28
     random
    0.27
    stuff
    0.25
    Mus
    0.24
     Thoughts
    0.24
    Stuff
    0.24
     Stuff
    0.24
    Act Density 0.377%

    No Known Activations