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

    Neuronpedia

    INDEX
    Explanations

    words related to specific topics or themes, such as medical, political, or environmental issues

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruary
    -0.93
    ellen
    -0.88
    irlf
    -0.79
    matched
    -0.79
    ilded
    -0.78
    pload
    -0.78
    earchers
    -0.77
    arest
    -0.77
    nai
    -0.77
    ramids
    -0.77
    POSITIVE LOGITS
     activities
    1.15
     activity
    1.06
     pursuits
    1.05
     incidents
    1.02
     disasters
    0.98
     endeavors
    0.98
     fatalities
    0.95
     inquiries
    0.95
     developments
    0.94
     controversies
    0.94
    Act Density 0.046%

    No Known Activations