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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a specific verb or verb phrase

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to individuals in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.70
     Skydragon
    -0.64
     Leban
    -0.63
    isSpecialOrderable
    -0.62
     Explore
    -0.61
     Experimental
    -0.60
     UCH
    -0.59
    Measure
    -0.59
     Greenwood
    -0.58
    due
    -0.58
    POSITIVE LOGITS
     forgot
    1.17
     ignores
    1.15
     lied
    1.12
     conveniently
    1.06
     ought
    1.04
     implied
    1.03
     sounded
    1.02
     shouldn
    1.01
     didn
    1.01
     cites
    1.01
    Act Density 0.285%

    No Known Activations