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

    Neuronpedia

    INDEX
    Explanations

    terms related to policy discussions and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to analysis and discussion of policies and regulations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ISBN
    -0.69
    cised
    -0.64
     expired
    -0.64
     deserted
    -0.61
    netflix
    -0.59
     FML
    -0.59
    rompt
    -0.57
     rusty
    -0.57
    ewitness
    -0.57
    bestos
    -0.57
    POSITIVE LOGITS
     purposes
    0.98
     endeavors
    0.94
    .</
    0.74
    .[
    0.72
     calculations
    0.68
     succeeding
    0.68
    eering
    0.67
     overall
    0.67
    ogenesis
    0.66
    .]
    0.65
    Act Density 0.629%

    No Known Activations