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

    Neuronpedia

    INDEX
    Explanations

    words related to contamination and cleaning up contaminated areas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contamination and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.85
    pir
    -0.77
    SEC
    -0.76
    reme
    -0.73
    arb
    -0.73
    hour
    -0.73
    df
    -0.72
    otos
    -0.71
    htar
    -0.69
    uchin
    -0.68
    POSITIVE LOGITS
     contamination
    1.21
     contamin
    1.18
     contaminated
    1.13
     contam
    1.01
     contaminants
    0.98
    obyl
    0.87
     spills
    0.84
     stains
    0.75
     fou
    0.75
     groundwater
    0.75
    Act Density 0.017%

    No Known Activations