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

    Neuronpedia

    INDEX
    Explanations

    terms related to public figures and their statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to political remarks or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Located
    -0.76
    houses
    -0.74
     ILCS
    -0.71
     [];
    -0.70
    Exper
    -0.70
     Printing
    -0.68
    geries
    -0.67
     Archdemon
    -0.67
     Agric
    -0.66
    )/
    -0.66
    POSITIVE LOGITS
     remarks
    0.97
     praise
    0.95
     upbeat
    0.94
     scathing
    0.94
     clarify
    0.92
     reiterate
    0.90
     categ
    0.89
    lique
    0.88
     sarcast
    0.88
     clarification
    0.87
    Act Density 0.513%

    No Known Activations