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

    Neuronpedia

    INDEX
    Explanations

    instances of character introductions and community engagement in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Coach
    -0.16
     coach
    -0.16
     Coach
    -0.15
    çĶ
    -0.15
    coach
    -0.14
    å°Ĭ
    -0.14
     Favorites
    -0.14
     Walter
    -0.14
    út
    -0.13
     Vimeo
    -0.13
    POSITIVE LOGITS
     sims
    0.28
     role
    0.23
     Role
    0.22
     Sims
    0.21
     sim
    0.21
    -role
    0.21
    role
    0.20
    sim
    0.19
     plots
    0.19
     ROLE
    0.19
    Act Density 0.009%

    No Known Activations