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

    Neuronpedia

    INDEX
    Explanations

    concepts related to governance and public policy initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sti
    -0.16
    kaar
    -0.14
    chw
    -0.13
    angers
    -0.13
    requently
    -0.13
     dÆ°
    -0.13
    uge
    -0.13
     erst
    -0.13
    -appointed
    -0.13
     appointed
    -0.12
    POSITIVE LOGITS
     model
    0.27
     capable
    0.22
     modeled
    0.21
     able
    0.21
    -model
    0.19
     modelo
    0.19
    model
    0.19
     based
    0.18
     MODEL
    0.18
     modèle
    0.17
    Act Density 0.281%

    No Known Activations