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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions or calls for action

    oai_token-act-pair · gpt-3.5-turbo

    references to stopping conflicts or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledged
    -0.90
    olate
    -0.82
    lly
    -0.77
    lore
    -0.74
    soDeliveryDate
    -0.73
    ittal
    -0.72
    anan
    -0.70
    replace
    -0.70
    dds
    -0.70
    ldom
    -0.69
    POSITIVE LOGITS
     bleeding
    1.24
     flow
    1.17
     progress
    0.96
     movement
    0.96
     pace
    0.95
     progression
    0.94
     growth
    0.91
     runaway
    0.91
     onslaught
    0.88
     process
    0.87
    Act Density 0.182%

    No Known Activations