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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and events involving people or entities

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms associated with conflict and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Specifically
    -0.59
    DonaldTrump
    -0.59
     CFR
    -0.58
     Cosponsors
    -0.56
     regimes
    -0.54
     Accessed
    -0.53
     expansions
    -0.51
    "},
    -0.50
     differentiated
    -0.50
     DOD
    -0.50
    POSITIVE LOGITS
    chan
    0.58
    anus
    0.56
     guiActiveUn
    0.56
    cam
    0.55
    quit
    0.55
    uph
    0.55
    aran
    0.55
     "$:/
    0.55
    aram
    0.53
    reet
    0.53
    Act Density 1.344%

    No Known Activations