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

    Neuronpedia

    INDEX
    Explanations

    references to significant events causing damage or crisis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owa
    -0.16
    addtogroup
    -0.16
     hurricanes
    -0.15
    495
    -0.15
    usch
    -0.14
    uhn
    -0.14
    swire
    -0.14
    ±
    -0.13
    Surname
    -0.13
    adle
    -0.13
    POSITIVE LOGITS
     thousands
    0.34
     hundreds
    0.32
     Hundreds
    0.26
     Thousands
    0.26
     tens
    0.26
     dozens
    0.23
    Thousands
    0.23
     many
    0.23
     scores
    0.23
    Hundreds
    0.22
    Act Density 0.244%

    No Known Activations