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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verbs related to following or supporting a person

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reach
    -0.68
    Limit
    -0.68
     Carrie
    -0.67
     Siege
    -0.66
     Pastebin
    -0.65
    ornia
    -0.64
    Deal
    -0.63
     Molly
    -0.63
     Sara
    -0.63
    Start
    -0.63
    POSITIVE LOGITS
     redes
    0.79
     tremend
    0.77
    atically
    0.77
     conduc
    0.75
     detractors
    0.75
    atic
    0.74
     personally
    0.72
     enthusi
    0.71
     orally
    0.69
     occas
    0.69
    Act Density 0.070%

    No Known Activations