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

    Neuronpedia

    INDEX
    Explanations

    discussions about social media interactions and user-generated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    social media posts and tweets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.44
     CreateTagHelper
    -0.35
     kohdetta
    -0.34
     menn
    -0.33
    WriteLiteral
    -0.31
    大人
    -0.30
    ExtendWith
    -0.30
    municipi
    -0.29
    AMPLE
    -0.29
    onAttach
    -0.29
    POSITIVE LOGITS
     posts
    0.57
     posting
    0.57
     replies
    0.56
     Posting
    0.55
     announcements
    0.54
     tweets
    0.53
     replying
    0.52
     upload
    0.52
     announcement
    0.51
     speeches
    0.51
    Act Density 0.026%

    No Known Activations