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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging the reader to stay updated on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging vigilance or attention to important information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.77
    NetMessage
    -0.72
     tom
    -0.72
    Interstitial
    -0.68
    MpServer
    -0.67
    displayText
    -0.67
    Sov
    -0.64
     Mehran
    -0.64
    odied
    -0.62
    ody
    -0.62
    POSITIVE LOGITS
    ership
    0.85
     tabs
    0.84
    ers
    0.83
     scrolling
    0.82
     Calm
    0.80
    overs
    0.79
    s
    0.78
    watch
    0.73
    ressing
    0.72
    agh
    0.72
    Act Density 0.022%

    No Known Activations