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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leadership roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating leadership or positions of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subp
    -0.67
     mell
    -0.67
    ickr
    -0.63
    200000
    -0.63
    icity
    -0.62
     delta
    -0.62
    psey
    -0.61
    aneously
    -0.60
    XP
    -0.60
     suscept
    -0.60
    POSITIVE LOGITS
    quarter
    1.16
    lining
    1.11
    canon
    1.06
    hun
    1.01
    gear
    1.01
    liner
    1.00
    scar
    0.96
    hunter
    0.95
    strong
    0.92
    pin
    0.91
    Act Density 0.024%

    No Known Activations