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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important political figures and their positions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to prime ministers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oteric
    -0.72
    bleacher
    -0.69
    ascade
    -0.66
     Bunker
    -0.66
     tattoos
    -0.65
    oso
    -0.64
    anwhile
    -0.63
    entric
    -0.62
     charcoal
    -0.62
    hovah
    -0.61
    POSITIVE LOGITS
     Minister
    1.27
     ministerial
    1.21
     minister
    1.18
     Ministers
    0.98
     ministers
    0.95
     Secretary
    0.89
     secretary
    0.88
     Cabinet
    0.79
     nominee
    0.79
    isl
    0.74
    Act Density 0.021%

    No Known Activations