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

    Neuronpedia

    INDEX
    Explanations

    mentions of the White House

    oai_token-act-pair · gpt-3.5-turbo

    references to the White House

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.86
    isine
    -0.81
    ãĤ¨ãĥ«
    -0.80
    Ô
    -0.75
    rossover
    -0.71
    ãĤ½
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    dylib
    -0.68
    amia
    -0.68
    Redd
    -0.68
    POSITIVE LOGITS
     reacted
    1.08
     responded
    1.01
     intervened
    1.00
     opted
    1.00
     froze
    0.93
     withdrew
    0.93
     acknowledges
    0.91
     undertook
    0.89
     countered
    0.88
     declined
    0.87
    Act Density 0.432%

    No Known Activations