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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checking in, updates, and confirmations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of checking back for updates or follow-ups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.74
    EStreamFrame
    -0.69
    terness
    -0.62
    姫
    -0.61
     Thur
    -0.61
    ©¶æ¥µ
    -0.60
    ranged
    -0.60
    «ĺ
    -0.59
    NetMessage
    -0.58
    virtual
    -0.58
    POSITIVE LOGITS
     sidelines
    0.79
     balances
    0.77
    balance
    0.68
     inbox
    0.68
    tips
    0.64
     positives
    0.64
     crossings
    0.64
     flats
    0.63
     periphery
    0.62
     borders
    0.62
    Act Density 0.125%

    No Known Activations