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

    Neuronpedia

    INDEX
    Explanations

    specific references to dates and structured information in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    🫡
    -0.77
    🥹
    -0.70
    🫣
    -0.64
    🫶
    -0.64
    🫠
    -0.63
    🫤
    -0.54
    🫢
    -0.53
    🫱
    -0.52
     Inflation
    -0.52
    🪩
    -0.52
    POSITIVE LOGITS
     coronavirus
    1.03
    Coronavirus
    1.02
     Coronavirus
    0.98
    coronavirus
    0.91
     corona
    0.85
     quarantine
    0.84
     COVID
    0.83
    COVID
    0.82
    新型コロナ
    0.79
    corona
    0.76
    Act Density 0.109%

    No Known Activations