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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a strong negative emotional response

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "upset."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     livest
    -0.86
    glas
    -0.86
    istered
    -0.72
    atures
    -0.72
    gart
    -0.71
     liner
    -0.71
    audi
    -0.70
    icrobial
    -0.70
    gravity
    -0.70
    acons
    -0.70
    POSITIVE LOGITS
    dy
    0.91
    der
    0.73
    ingly
    0.73
     upset
    0.72
     uproar
    0.69
    wart
    0.67
     Wasserman
    0.66
    bur
    0.65
     stomach
    0.65
    Brexit
    0.64
    Act Density 0.015%

    No Known Activations