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

    Neuronpedia

    INDEX
    Explanations

    references to political events or conventions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lasses
    -0.84
    =#
    -0.68
    tera
    -0.68
    protein
    -0.65
    paragraph
    -0.65
    riv
    -0.65
    cam
    -0.63
    depend
    -0.62
    river
    -0.62
    Ha
    -0.62
    POSITIVE LOGITS
    eers
    1.08
     delegates
    1.06
     convened
    0.93
     attendees
    0.91
    goers
    0.90
    eering
    0.87
     convention
    0.84
     hall
    0.83
     Convention
    0.83
     speeches
    0.83
    Act Density 0.019%

    No Known Activations