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

    Neuronpedia

    INDEX
    Explanations

    titles or positions of leadership within organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⁂
    -0.67
     Tomlinson
    -0.67
    slidesToShow
    -0.67
    ♬
    -0.65
     OnDestroy
    -0.65
     Alcott
    -0.63
    zyż
    -0.62
    Wirtschaft
    -0.62
     Occupations
    -0.62
    ikkert
    -0.61
    POSITIVE LOGITS
     head
    3.30
     Head
    3.16
    Head
    2.97
     HEAD
    2.90
    head
    2.70
    HEAD
    2.49
     heads
    2.48
     Heads
    2.25
    heads
    2.06
    Heads
    1.99
    Act Density 0.043%

    No Known Activations