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

    Neuronpedia

    INDEX
    Explanations

    dates associated with resignations from positions of power

    oai_token-act-pair · gpt-3.5-turbo

    instances of resignation or departure, often with detailed context such as dates or conditions of resignation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     translates
    -0.68
    ounters
    -0.68
    gas
    -0.68
    amins
    -0.66
    insky
    -0.64
    Dispatch
    -0.62
    sburg
    -0.61
    erial
    -0.61
    ãĥ¼ãĤ¯
    -0.61
    horn
    -0.61
    POSITIVE LOGITS
     disgrace
    1.09
     unsatisf
    0.92
     resignation
    0.87
     dishon
    0.84
     disgust
    0.81
     citing
    0.80
     resign
    0.79
    ruct
    0.77
     protest
    0.75
     disagreement
    0.74
    Act Density 0.200%

    No Known Activations