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

    Neuronpedia

    INDEX
    Explanations

    words related to causation or correlation

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to political, environmental, and health issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    netflix
    -0.67
    egal
    -0.61
    pires
    -0.58
    perse
    -0.57
     Seb
    -0.56
     Cruise
    -0.54
     Gunn
    -0.54
     Guys
    -0.54
     lasted
    -0.53
     Flam
    -0.53
    POSITIVE LOGITS
     pree
    0.72
     constituents
    0.69
     conception
    0.67
     deity
    0.66
     philosophies
    0.66
     criminality
    0.66
    establishment
    0.65
     existing
    0.65
     purposes
    0.64
     objectives
    0.64
    Act Density 0.787%

    No Known Activations