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

    Neuronpedia

    INDEX
    Explanations

    references to statistics and opinions about Americans

    oai_token-act-pair · gpt-3.5-turbo

    references to the American population

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    operation
    -0.74
    ival
    -0.71
    selection
    -0.69
    wrapper
    -0.67
    fecture
    -0.66
    ough
    -0.66
    NB
    -0.64
    Initialized
    -0.63
    ÃŁ
    -0.63
    yz
    -0.62
    POSITIVE LOGITS
    ICAN
    0.80
     Idol
    0.76
     who
    0.74
     Citizens
    0.72
     Airlines
    0.71
    ornings
    0.71
     citizens
    0.68
     born
    0.68
    ervatives
    0.68
     Psychiatric
    0.68
    Act Density 0.034%

    No Known Activations