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

    Neuronpedia

    INDEX
    Explanations

    references to competitions or tournament outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illon
    -0.17
     Middleton
    -0.15
    aal
    -0.15
    ived
    -0.15
    alto
    -0.15
    uras
    -0.14
    reach
    -0.14
    ale
    -0.14
    grave
    -0.14
    oner
    -0.14
    POSITIVE LOGITS
     victory
    0.18
     Dispatch
    0.17
     defeating
    0.17
     victories
    0.17
     dispatch
    0.17
    oldt
    0.17
    åĭĿ
    0.16
    ↵↵
    0.16
    against
    0.16
     defeat
    0.15
    Act Density 0.066%

    No Known Activations