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

    Neuronpedia

    INDEX
    Explanations

    the possessive pronoun 'its'

    oai_token-act-pair · gpt-4-turbo

    phrases related to features or details about different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "its"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AAAA
    -0.81
    eering
    -0.73
     gif
    -0.70
    Show
    -0.70
    Condition
    -0.68
    Gallery
    -0.66
    ãĤ¹ãĥĪ
    -0.65
     Unsure
    -0.65
     Hastings
    -0.65
    ooo
    -0.64
    POSITIVE LOGITS
     own
    1.51
    ELF
    1.07
     respective
    1.05
     predecessor
    0.94
    self
    0.87
     conduc
    0.87
     predecessors
    0.85
     knees
    0.84
     tradem
    0.83
    asca
    0.83
    Act Density 0.123%

    No Known Activations