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

    Neuronpedia

    INDEX
    Explanations

    references to award nominations and announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     flagged
    -0.14
     cited
    -0.14
     revived
    -0.14
    aliz
    -0.13
    eniz
    -0.13
    alach
    -0.13
    oux
    -0.13
    ield
    -0.13
    ahi
    -0.13
    μί
    -0.13
    POSITIVE LOGITS
     revealed
    0.29
    reve
    0.28
     Reve
    0.27
     reveal
    0.25
     released
    0.24
     announced
    0.24
     revealing
    0.24
     announcement
    0.23
    çĻºè¡¨
    0.23
     list
    0.23
    Act Density 0.104%

    No Known Activations