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

    Neuronpedia

    INDEX
    Explanations

    references to alcohol or drunkenness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Flavoring
    -1.47
    adr
    -1.10
    ppa
    -1.07
    ILA
    -1.05
    atro
    -1.02
    venants
    -1.00
    ptive
    -0.97
    ASON
    -0.96
    agnetic
    -0.95
    76561
    -0.95
    POSITIVE LOGITS
    ness
    2.07
    nesses
    1.36
    NESS
    1.26
    ity
    1.22
    ly
    1.01
    ities
    0.95
     nodd
    0.89
    cies
    0.87
    lings
    0.87
     citiz
    0.85
    Act Density 1.191%

    No Known Activations