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

    Neuronpedia

    INDEX
    Explanations

    mentions of cigars and specific geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to cigars and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MacDonald
    -0.83
    âķIJâķIJ
    -0.77
    Ü
    -0.74
    UTERS
    -0.71
    Cry
    -0.68
    NBC
    -0.68
    hy
    -0.67
    conom
    -0.65
    IVES
    -0.65
     Livingston
    -0.65
    POSITIVE LOGITS
     cigars
    1.28
     cigar
    1.27
    illo
    0.94
     wrapper
    0.94
    uana
    0.91
     humid
    0.90
    ensis
    0.87
     Nicarag
    0.85
    cig
    0.84
     Cig
    0.84
    Act Density 0.019%

    No Known Activations