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

    Neuronpedia

    INDEX
    Explanations

    the word "latest" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the latest updates or news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phy
    -0.85
    shared
    -0.85
    alias
    -0.82
    later
    -0.82
    umenthal
    -0.70
    wright
    -0.70
    lain
    -0.70
    knife
    -0.68
    lique
    -0.68
    ipal
    -0.68
    POSITIVE LOGITS
     developments
    1.15
     updates
    1.01
     edition
    0.95
     versions
    0.95
     editions
    0.94
     version
    0.92
     trends
    0.91
     arrivals
    0.91
     incarnation
    0.89
     news
    0.87
    Act Density 0.063%

    No Known Activations