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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative and distressing situations, including war, disaster, failure, danger, hunger, persecution, defeat, loneliness, starvation, and injury

    oai_token-act-pair · gpt-3.5-turbo

    topics related to conflict and crisis situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TOTAL
    -0.73
    abase
    -0.65
    ocket
    -0.60
     Logo
    -0.59
     encyclopedia
    -0.58
     referen
    -0.58
     calendar
    -0.57
     Judicial
    -0.57
    ITNESS
    -0.56
    riber
    -0.56
    POSITIVE LOGITS
    flies
    0.85
    making
    0.77
    ridden
    0.74
    adas
    0.74
     sickness
    0.74
    lessly
    0.73
    fully
    0.72
    ously
    0.72
    seeking
    0.71
    fulness
    0.70
    Act Density 0.358%

    No Known Activations