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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .nan
    -0.19
    PressEvent
    -0.15
     Maj
    -0.15
    oran
    -0.14
    ourg
    -0.14
    reau
    -0.14
    SCO
    -0.14
    raith
    -0.14
    iasi
    -0.14
    pek
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.23
     lives
    0.20
     life
    0.20
     жизни
    0.16
    çĶŁæ´»
    0.15
    bere
    0.15
     ActionTypes
    0.15
    _NEED
    0.15
     vida
    0.14
    -flat
    0.14
    Act Density 0.095%

    No Known Activations