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

    Neuronpedia

    INDEX
    Explanations

    instances where a specific quantity of something is mentioned or compared

    oai_token-act-pair · gpt-3.5-turbo

    references to job opportunities and gender representation in the workforce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atcher
    -0.60
    addin
    -0.58
    uart
    -0.56
    wright
    -0.54
    icians
    -0.53
    emi
    -0.52
    oyer
    -0.51
     Inspector
    -0.51
     incorpor
    -0.50
    haw
    -0.50
    POSITIVE LOGITS
     spare
    0.68
    bucks
    0.65
     amount
    0.62
     watts
    0.59
     precious
    0.57
     firepower
    0.57
     trophies
    0.56
     goodies
    0.56
     pounds
    0.56
     ounce
    0.56
    Act Density 0.943%

    No Known Activations