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

    Neuronpedia

    INDEX
    Explanations

    terms related to environmental accidents, specifically spills

    oai_token-act-pair · gpt-3.5-turbo

    mentions of environmental spills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tarian
    -0.91
    tarians
    -0.86
    */(
    -0.76
    eering
    -0.75
    HCR
    -0.74
    ically
    -0.72
    iterranean
    -0.71
    olkien
    -0.69
    ican
    -0.68
    ellen
    -0.67
    POSITIVE LOGITS
     spills
    0.96
     spill
    0.93
     spilled
    0.92
    OVER
    0.79
    ards
    0.77
     spilling
    0.77
     litres
    0.75
    sheets
    0.75
    waters
    0.74
    over
    0.74
    Act Density 0.029%

    No Known Activations