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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases indicating ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orks
    -0.94
    clips
    -0.77
    osi
    -0.73
    ourses
    -0.70
    BBC
    -0.66
     Figures
    -0.65
    PLA
    -0.65
    icates
    -0.65
    #$#$
    -0.63
    ptives
    -0.61
    POSITIVE LOGITS
     fault
    1.24
     favorite
    1.22
     downfall
    1.17
     favourite
    1.15
     undo
    1.05
     own
    1.04
     savior
    1.02
     biggest
    1.02
     cue
    1.00
     Achilles
    1.00
    Act Density 0.121%

    No Known Activations