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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns related to politicians or governmental figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals involved in political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.84
    ghai
    -0.80
    ndum
    -0.77
    ighth
    -0.76
    apore
    -0.74
    ographed
    -0.73
    opsis
    -0.72
    ocol
    -0.71
    chnology
    -0.71
    agra
    -0.71
    POSITIVE LOGITS
     Gibbs
    1.02
    sonian
    0.83
    hops
    0.81
    sein
    0.72
    layer
    0.70
    LIN
    0.70
    sim
    0.68
    step
    0.68
    ford
    0.65
    lins
    0.65
    Act Density 0.009%

    No Known Activations