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

    Neuronpedia

    INDEX
    Explanations

    references to the platform Twitter

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

    twitter feed or account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sac
    -0.49
    serious
    -0.49
     LEC
    -0.47
     jspb
    -0.47
    reqs
    -0.46
    込
    -0.46
     Orm
    -0.45
    MOC
    -0.45
    ある
    -0.45
     Kind
    -0.45
    POSITIVE LOGITS
     Twitter
    1.36
    Twitter
    1.29
     twitter
    1.28
    twitter
    1.20
     TWITTER
    1.13
    TWITTER
    0.94
     tweet
    0.75
     tweeting
    0.75
     Twit
    0.72
     tweeter
    0.70
    Act Density 0.002%

    No Known Activations