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

    Neuronpedia

    INDEX
    Explanations

    terms related to smoking and its effects

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

    smokers or smoothers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     채
    -0.36
    Hentet
    -0.35
     γ
    -0.34
     бути
    -0.34
     pick
    -0.34
    fär
    -0.33
     Kund
    -0.32
     drauf
    -0.32
     engaged
    -0.32
     tagged
    -0.32
    POSITIVE LOGITS
    smo
    0.93
     Smo
    0.92
    Smo
    0.89
     smo
    0.74
     Efq
    0.66
     pleaſure
    0.65
     myſelf
    0.64
     smoothed
    0.62
     smog
    0.61
     Monfieur
    0.60
    Act Density 0.008%

    No Known Activations