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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human characteristics and attributes such as physical appearance, abilities, and societal roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaz
    -0.68
    ensing
    -0.67
     prosecuting
    -0.65
    oyer
    -0.65
    etting
    -0.64
    AU
    -0.64
    —-
    -0.63
    udo
    -0.62
    TG
    -0.62
    hooting
    -0.60
    POSITIVE LOGITS
     been
    1.26
     undergone
    1.20
    been
    1.13
     gotten
    0.98
     suffered
    0.93
     lived
    0.92
     access
    0.91
     difficulty
    0.90
     Been
    0.90
     gone
    0.89
    Act Density 0.335%

    No Known Activations