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

    Neuronpedia

    INDEX
    Explanations

    mentions of notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and the corresponding subjects they relate to

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.79
    ages
    -0.75
    daq
    -0.74
    ————
    -0.73
    hari
    -0.73
     Rowling
    -0.73
    ATURES
    -0.71
    aunder
    -0.70
    Copyright
    -0.68
    >]
    -0.67
    POSITIVE LOGITS
     successor
    1.30
     predecessor
    1.28
     predecessors
    1.19
     cabinet
    1.15
     Cabinet
    1.11
     successors
    1.09
     administration
    1.09
     aides
    1.08
     ministers
    1.08
     Majesty
    1.06
    Act Density 0.166%

    No Known Activations