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

    Neuronpedia

    INDEX
    Explanations

    instances where an event or action has not occurred or a decision has not been made yet

    oai_token-act-pair · gpt-3.5-turbo

    the word "yet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rities
    -0.70
    stories
    -0.66
    Sequ
    -0.62
    performance
    -0.61
     Fortress
    -0.58
    current
    -0.58
    ï
    -0.57
    packs
    -0.57
    Reporting
    -0.57
    warts
    -0.56
    POSITIVE LOGITS
    heric
    0.68
    jee
    0.68
     surpassed
    0.67
     definitively
    0.66
    ë
    0.65
     succumb
    0.65
     TBD
    0.65
     succumbed
    0.64
    uden
    0.64
    icia
    0.64
    Act Density 0.014%

    No Known Activations