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

    Neuronpedia

    INDEX
    Explanations

    words related to debates or speculation

    oai_token-act-pair · gpt-3.5-turbo

    words related to debate or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     paycheck
    -0.76
     wallpaper
    -0.64
    icka
    -0.62
     designated
    -0.62
    otti
    -0.61
     stocking
    -0.61
     buffers
    -0.61
     cyan
    -0.61
     piping
    -0.60
     colon
    -0.58
    POSITIVE LOGITS
    fy
    0.89
    andum
    0.88
    ij士
    0.86
    answer
    0.82
    ostic
    0.81
    butt
    0.78
    rum
    0.73
    question
    0.71
    erness
    0.71
     Regarding
    0.70
    Act Density 0.105%

    No Known Activations