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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "worth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.71
     Nou
    -0.66
     Ars
    -0.64
    ++++++++++++++++
    -0.64
    âĸ¬âĸ¬
    -0.61
     verbs
    -0.61
     heartbeat
    -0.60
    iolet
    -0.59
     Quit
    -0.58
     Verge
    -0.58
    POSITIVE LOGITS
    sworth
    1.08
    sung
    0.97
    umes
    0.93
    borough
    0.91
    worth
    0.89
    ume
    0.89
    nesses
    0.88
    endor
    0.87
    iness
    0.86
    ages
    0.85
    Act Density 0.018%

    No Known Activations