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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments and complex character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inati
    -0.16
    еви
    -0.15
     \''
    -0.15
    Friends
    -0.15
     desar
    -0.15
    707
    -0.15
    281
    -0.15
    illus
    -0.15
    /******/
    -0.14
    PELL
    -0.13
    POSITIVE LOGITS
     Officer
    0.20
     Det
    0.17
     Franc
    0.17
     upt
    0.16
     Principal
    0.16
     Doc
    0.16
     reception
    0.16
     Gem
    0.16
     Agent
    0.15
     Coach
    0.15
    Act Density 0.119%

    No Known Activations