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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences or emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $
    -0.16
    abis
    -0.15
    ême
    -0.14
    adam
    -0.14
    ết
    -0.14
    led
    -0.14
    portun
    -0.14
    ãĥIJãĥ¼
    -0.14
     RESP
    -0.14
    endum
    -0.14
    POSITIVE LOGITS
     sic
    0.28
    sic
    0.27
    +]
    0.17
    iazza
    0.16
    ¦
    0.15
    asics
    0.15
    eparator
    0.14
    arra
    0.14
    hic
    0.14
    ROS
    0.14
    Act Density 0.012%

    No Known Activations