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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts related to game dynamics and social norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .shtml
    -0.19
    sson
    -0.15
    skou
    -0.14
    innie
    -0.14
    å·±
    -0.14
    墨
    -0.14
    Ghost
    -0.14
    кÑĸн
    -0.14
    redits
    -0.14
    çĿ
    -0.14
    POSITIVE LOGITS
    apl
    0.18
    337
    0.17
     otherwise
    0.17
    366
    0.16
     similarly
    0.16
     mere
    0.16
    279
    0.15
    ORM
    0.14
     nowhere
    0.14
    loub
    0.14
    Act Density 0.078%

    No Known Activations