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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political views and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Radar
    -0.76
    Poké
    -0.73
     Raspberry
    -0.68
     RAID
    -0.67
    raft
    -0.66
     Medline
    -0.66
     NX
    -0.65
     Deadline
    -0.63
     Arri
    -0.62
    iple
    -0.62
    POSITIVE LOGITS
     ideologically
    0.97
     ideological
    0.95
     morally
    0.92
     Democr
    0.91
     democratically
    0.90
     democratic
    0.89
     politically
    0.85
    democratic
    0.85
     neoliberal
    0.85
     elector
    0.82
    Act Density 2.322%

    No Known Activations