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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    elements related to social issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.85
     initially
    -0.84
     Initially
    -0.81
     Factors
    -0.78
    Initially
    -0.75
    pects
    -0.74
    ynchron
    -0.73
    earchers
    -0.73
    Adapt
    -0.71
     Originally
    -0.71
    POSITIVE LOGITS
     whining
    1.05
     goddamn
    1.05
     bulldo
    1.04
     thugs
    1.04
     idiots
    1.02
     defund
    1.00
     bureaucrats
    0.99
     fucking
    0.99
     lobbyists
    0.98
     torches
    0.97
    Act Density 0.844%

    No Known Activations