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

    Neuronpedia

    INDEX
    Explanations

    words related to heating, cooling, and temperature regulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to potential hazards or risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Founding
    -0.76
    vernment
    -0.75
    çīĪ
    -0.75
    ISC
    -0.68
    ocracy
    -0.63
    olitical
    -0.63
     Publication
    -0.62
     Provision
    -0.62
    resents
    -0.61
    galitarian
    -0.61
    POSITIVE LOGITS
     undet
    0.85
     nausea
    0.78
     spikes
    0.75
     untreated
    0.75
     refill
    0.73
     congest
    0.73
     flares
    0.72
     liquids
    0.72
     impair
    0.71
     conserve
    0.70
    Act Density 1.620%

    No Known Activations