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

    Neuronpedia

    INDEX
    Explanations

    mentions of smoking-related items like cigars and cigarette related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to cigars and related smoking items or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.80
    Ü
    -0.75
     Livingston
    -0.73
    yll
    -0.69
    MN
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    PASS
    -0.66
     Bicycle
    -0.66
    Cry
    -0.66
    earch
    -0.65
    POSITIVE LOGITS
     cigars
    1.05
     cigar
    0.95
    illo
    0.91
    ensis
    0.89
     wrapper
    0.88
    Wra
    0.84
    ango
    0.84
     Maduro
    0.83
    inals
    0.80
    rito
    0.80
    Act Density 0.021%

    No Known Activations