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

    Neuronpedia

    INDEX
    Explanations

    direct addresses or references to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ostel
    -0.14
     Trab
    -0.14
    throp
    -0.14
    licos
    -0.14
    gp
    -0.13
    »
    -0.13
     kraj
    -0.13
     insensitive
    -0.13
    à¸Ľà¸£
    -0.13
    urs
    -0.13
    POSITIVE LOGITS
     briefing
    0.17
     briefed
    0.16
    brief
    0.16
     formations
    0.15
     γαÏģ
    0.15
     situ
    0.15
     perms
    0.15
    주ìĭľ
    0.14
     players
    0.14
     shit
    0.14
    Act Density 0.000%

    No Known Activations