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

    Neuronpedia

    INDEX
    Explanations

    specific actions and statements made by political figures

    oai_token-act-pair · gpt-3.5-turbo

    statements related to political announcements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahi
    -0.73
    ICES
    -0.70
    usercontent
    -0.66
    IENT
    -0.66
    AGES
    -0.63
    ENE
    -0.62
    selves
    -0.62
    MpServer
    -0.62
     CLIENT
    -0.61
     selves
    -0.60
    POSITIVE LOGITS
     pard
    1.02
     veto
    0.93
     aides
    0.82
     pardon
    0.80
     Mattis
    0.80
     Pence
    0.78
     vetoed
    0.76
     presidential
    0.76
    ij士
    0.74
     himself
    0.74
    Act Density 0.867%

    No Known Activations