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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to decision-making and consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceae
    -0.15
     midpoint
    -0.15
    kke
    -0.14
     Techniques
    -0.14
     shortfall
    -0.14
     attacker
    -0.14
    pite
    -0.14
    ATA
    -0.14
    λικ
    -0.14
    oya
    -0.13
    POSITIVE LOGITS
     organization
    0.18
     disfr
    0.18
     Senator
    0.17
     caucus
    0.17
     resolutions
    0.17
     organized
    0.16
     colored
    0.16
     honorable
    0.16
     Southern
    0.16
     nominations
    0.15
    Act Density 0.039%

    No Known Activations