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

    Neuronpedia

    INDEX
    Explanations

    names or titles related to diplomatic positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ambassador."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aver
    -0.73
    fall
    -0.69
    comes
    -0.69
    avers
    -0.68
    efer
    -0.66
    esville
    -0.66
    stood
    -0.66
    à©
    -0.66
    leys
    -0.64
    icester
    -0.64
    POSITIVE LOGITS
     ambassador
    0.95
     abroad
    0.89
    assador
    0.87
     envoy
    0.86
    eur
    0.75
     Ambassador
    0.75
     reception
    0.75
    assadors
    0.73
     diplomat
    0.72
     ambassadors
    0.71
    Act Density 0.010%

    No Known Activations