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

    Neuronpedia

    INDEX
    Explanations

    words related to political positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to the role of president or candidacy for president

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     presentations
    -0.64
     pestic
    -0.61
    ighed
    -0.60
     Scores
    -0.57
    ensen
    -0.57
     Hoff
    -0.57
     informants
    -0.56
    Kings
    -0.55
     LOT
    -0.55
     Groups
    -0.55
    POSITIVE LOGITS
     someday
    1.04
    alty
    0.85
    orship
    0.81
    ature
    0.80
    ially
    0.78
    aroo
    0.77
    ial
    0.76
    election
    0.75
    ón
    0.74
    onse
    0.74
    Act Density 0.116%

    No Known Activations