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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to roles and actions taken by individuals or groups in authority or decision-making positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fax
    -0.64
    Quote
    -0.63
    statement
    -0.60
     Compass
    -0.57
    pic
    -0.56
    laughs
    -0.56
     diary
    -0.56
    Cub
    -0.56
    plate
    -0.56
     Sakuya
    -0.56
    POSITIVE LOGITS
     themselves
    1.27
     respectively
    1.13
    selves
    1.05
     collectively
    1.04
     specialize
    0.86
     converge
    0.81
     jointly
    0.80
     populate
    0.77
     individually
    0.75
     constitute
    0.74
    Act Density 0.687%

    No Known Activations