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

    Neuronpedia

    INDEX
    Explanations

    terms related to environmental pollution

    oai_token-act-pair · gpt-3.5-turbo

    references to environmental pollution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tell
    -0.84
    Bone
    -0.80
    ces
    -0.77
    ches
    -0.75
    ker
    -0.71
    Vert
    -0.70
    strap
    -0.69
    llan
    -0.68
    bable
    -0.66
    nee
    -0.66
    POSITIVE LOGITS
     pollution
    1.19
     pollut
    0.99
     polluted
    0.91
     pollutants
    0.85
     emissions
    0.85
    ution
    0.82
    ourgeois
    0.82
     poisoning
    0.80
     dioxide
    0.78
     contamin
    0.78
    Act Density 0.013%

    No Known Activations