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

    Neuronpedia

    INDEX
    Explanations

    references to contamination and pollution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contamination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étoient
    -0.60
     étoit
    -0.57
     oración
    -0.55
    เฉ
    -0.55
     avoient
    -0.54
     vôtre
    -0.54
     vœ
    -0.52
     Khusus
    -0.52
     AttributeSet
    -0.52
     purpoſe
    -0.52
    POSITIVE LOGITS
     contamination
    1.93
     Contamination
    1.77
    contamination
    1.77
     contaminate
    1.66
     contamin
    1.64
     contaminated
    1.63
    contaminated
    1.46
     contaminant
    1.43
     Contamin
    1.40
     contaminants
    1.34
    Act Density 0.006%

    No Known Activations