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

    Neuronpedia

    INDEX
    Explanations

    names or titles related to prominent leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in positions of authority, specifically chairs of committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.75
    uder
    -0.71
    Cooldown
    -0.70
    ENC
    -0.66
    ilar
    -0.65
    اÙĦ
    -0.64
     IMAGES
    -0.64
    Sharp
    -0.63
    Sensor
    -0.62
    XP
    -0.62
    POSITIVE LOGITS
    IAL
    1.04
    ority
    1.01
    doms
    1.01
    pins
    0.94
    woman
    0.90
    person
    0.90
     emer
    0.89
    mans
    0.80
     chair
    0.79
     drawer
    0.79
    Act Density 0.017%

    No Known Activations