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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news headlines or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and discussions, particularly those involving interviews and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     artif
    -0.80
     ak
    -0.77
    Lear
    -0.74
     blat
    -0.72
     assum
    -0.69
     appre
    -0.64
    eday
    -0.63
     nav
    -0.63
     metab
    -0.63
    edIn
    -0.62
    POSITIVE LOGITS
    isconsin
    0.84
    igious
    0.74
     Republican
    0.74
    aughs
    0.72
    olin
    0.71
    lees
    0.71
    ptive
    0.69
    uania
    0.68
    ributes
    0.68
    Lago
    0.68
    Act Density 0.065%

    No Known Activations