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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community events and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.32
    sic
    -0.28
     destro
    -0.27
    代
    -0.27
     prest
    -0.26
    anwhile
    -0.25
    theless
    -0.24
     territ
    -0.23
     referen
    -0.23
     disadvant
    -0.23
    POSITIVE LOGITS
     âĢº
    0.30
     Belfast
    0.23
    )--
    0.22
     ..........
    0.22
     Orioles
    0.22
     Corbyn
    0.22
     Xiaomi
    0.21
     Baltimore
    0.21
    taboola
    0.20
    Arcade
    0.20
    Act Density 12.069%

    No Known Activations