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

    Neuronpedia

    INDEX
    Explanations

    references to sports teams and their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opposing teams

    np_acts-logits-general · gemini-2.0-flash

    opponent or team descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    衝
    -0.50
    SharedCtor
    -0.49
    (!__
    -0.48
    ambilan
    -0.46
    bió
    -0.45
     kese
    -0.45
     aio
    -0.44
    melli
    -0.44
    Revolution
    -0.44
    linde
    -0.43
    POSITIVE LOGITS
     opponents
    1.08
     opponent
    1.07
     opposition
    0.94
     teams
    0.88
     rivales
    0.87
     foes
    0.86
     сопер
    0.84
    opposition
    0.84
     advers
    0.83
    opponent
    0.83
    Act Density 0.173%

    No Known Activations