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

    Neuronpedia

    INDEX
    Explanations

    conversational elements related to acceptance and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.15
     Moor
    -0.14
    audi
    -0.14
    ubi
    -0.13
     ineligible
    -0.13
    IBE
    -0.13
    UMP
    -0.13
    -lnd
    -0.13
    ŀ
    -0.13
    913
    -0.13
    POSITIVE LOGITS
     setBackgroundColor
    0.15
     Jay
    0.14
    eton
    0.14
    rupa
    0.14
     Cater
    0.14
    lier
    0.13
     Eug
    0.13
    lig
    0.13
     rek
    0.13
     Conway
    0.13
    Act Density 0.205%

    No Known Activations