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

    Neuronpedia

    INDEX
    Explanations

    politicians, political figures, and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent political figures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.69
    ãĥ¯
    -0.64
    Oracle
    -0.63
    thens
    -0.63
    tml
    -0.62
    pires
    -0.61
     Mehran
    -0.60
    Berry
    -0.59
    asury
    -0.57
    uers
    -0.56
    POSITIVE LOGITS
     being
    0.94
    's
    0.93
     behaving
    0.86
     dying
    0.86
     needing
    0.85
     involvement
    0.84
     disappearing
    0.83
     losing
    0.82
     versus
    0.82
     influencing
    0.80
    Act Density 0.794%

    No Known Activations