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

    Neuronpedia

    INDEX
    Explanations

    instances of sports-related actions, particularly those involving errors or key plays

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

    negative outcomes and mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BaseActivity
    -0.54
     enfans
    -0.52
    +#+
    -0.48
    SpringRunner
    -0.48
    CrossRef
    -0.44
     ControllerBase
    -0.44
    fattning
    -0.42
     sukienka
    -0.42
    CardBody
    -0.42
     Boletín
    -0.41
    POSITIVE LOGITS
    trui
    0.40
     fouls
    0.35
    mur
    0.35
     kaarangay
    0.35
    wrong
    0.35
    あんな
    0.34
    冤
    0.34
     unjust
    0.34
     involunt
    0.34
    induced
    0.33
    Act Density 0.030%

    No Known Activations