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

    Neuronpedia

    INDEX
    Explanations

    keywords related to societal issues and concerns

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghazi
    -0.66
    verse
    -0.60
    iverse
    -0.59
    ufact
    -0.58
    selage
    -0.57
    POS
    -0.57
    ÙĪ
    -0.57
     Fidel
    -0.56
    ãĥ¥
    -0.55
    ISSION
    -0.55
    POSITIVE LOGITS
     consists
    0.85
     tends
    0.83
     dictates
    0.82
     isn
    0.80
     is
    0.79
     encompasses
    0.79
     comprises
    0.77
     improves
    0.77
     dominates
    0.77
     refers
    0.76
    Act Density 0.376%

    No Known Activations