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

    Neuronpedia

    INDEX
    Explanations

    references to smoking and smokers

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

    smokers and smoky

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odziel
    -0.41
    thalene
    -0.40
     new
    -0.40
     valueForKey
    -0.40
     kapit
    -0.40
     pendants
    -0.40
     fiber
    -0.40
    iddharth
    -0.39
    forKey
    -0.39
     Tal
    -0.39
    POSITIVE LOGITS
     Smo
    2.13
     smo
    1.97
    Smo
    1.96
    smo
    1.90
     smog
    1.25
     smoker
    1.20
     Smoky
    1.18
     Smokey
    1.12
     SMO
    1.10
     Smoke
    1.08
    Act Density 0.007%

    No Known Activations