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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun 'he' and its variations in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Millennium
    -0.74
     Mandatory
    -0.74
    upp
    -0.68
    classic
    -0.67
    iciency
    -0.64
    earch
    -0.64
    akedown
    -0.64
    necessary
    -0.63
    veyard
    -0.62
    ormal
    -0.62
    POSITIVE LOGITS
    'd
    1.17
     remembers
    1.11
     admits
    1.11
     knew
    1.10
     volunteered
    1.07
     awoke
    1.03
     thinks
    1.02
     wondered
    1.01
     prefers
    1.00
     knows
    1.00
    Act Density 0.310%

    No Known Activations