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

    Neuronpedia

    INDEX
    Explanations

    political entities, ideological terms, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political affiliations and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.77
    onet
    -0.75
    maxwell
    -0.65
    entanyl
    -0.64
    cellence
    -0.62
    icut
    -0.62
    puter
    -0.60
    endum
    -0.60
    ntil
    -0.58
    amping
    -0.57
    POSITIVE LOGITS
     deems
    1.33
     considers
    0.97
     deem
    0.97
     forgot
    0.91
     undertook
    0.90
     describes
    0.89
     owes
    0.89
     wants
    0.87
     uses
    0.86
     sorely
    0.86
    Act Density 0.244%

    No Known Activations