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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing updates or news

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "updates."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berm
    -0.82
    ãĤ¨ãĥ«
    -0.78
    odor
    -0.76
     Tire
    -0.76
    zh
    -0.75
    EG
    -0.71
    tein
    -0.70
    NAS
    -0.70
    tre
    -0.69
    nered
    -0.69
    POSITIVE LOGITS
     updates
    1.32
     update
    1.12
     notifications
    1.07
     Updates
    1.01
    update
    0.94
     upgrades
    0.89
    parency
    0.88
    dates
    0.88
     updating
    0.87
     Update
    0.86
    Act Density 0.007%

    No Known Activations