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

    Neuronpedia

    INDEX
    Explanations

    references to chairpersons or positions of leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.09
    ſelves
    -1.08
     itſelf
    -1.07
     myſelf
    -1.05
    ſelf
    -0.98
     Majefty
    -0.97
     purpoſe
    -0.95
     ſever
    -0.95
     themſelves
    -0.95
    wiſe
    -0.94
    POSITIVE LOGITS
     Chairman
    0.91
     chairman
    0.83
     chair
    0.80
    Chairman
    0.79
     Chair
    0.79
    CHAIR
    0.73
    chair
    0.73
    Chair
    0.72
    al
    0.67
    力
    0.66
    Act Density 0.119%

    No Known Activations