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

    Neuronpedia

    INDEX
    Explanations

    references to social media platforms and their associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    üy
    -0.17
    .crt
    -0.15
    _Style
    -0.15
    oine
    -0.15
     Www
    -0.15
    HORT
    -0.14
    .inspect
    -0.14
    inic
    -0.14
     Decomp
    -0.14
    ôt
    -0.14
    POSITIVE LOGITS
     themselves
    0.19
     itself
    0.16
     logs
    0.15
    Æ°á»Łng
    0.15
     thems
    0.14
     propriet
    0.14
     authorities
    0.14
    elog
    0.14
    atis
    0.14
     despre
    0.14
    Act Density 0.186%

    No Known Activations