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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority figures in a workplace setting

    oai_token-act-pair · gpt-3.5-turbo

    references to supervisory roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.79
    rams
    -0.78
    bed
    -0.76
    çīĪ
    -0.74
    glers
    -0.71
    rums
    -0.71
    aciously
    -0.71
    oliath
    -0.70
    elin
    -0.70
    auntlets
    -0.70
    POSITIVE LOGITS
     supervisor
    1.01
     Supervisor
    0.86
     supervisors
    0.83
    NBC
    0.75
     Sergeant
    0.73
     ANGEL
    0.70
    intendent
    0.69
     overseeing
    0.68
    terday
    0.68
    plin
    0.68
    Act Density 0.017%

    No Known Activations