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

    Neuronpedia

    INDEX
    Explanations

    phrases involving possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    possessive phrases indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flix
    -0.78
    event
    -0.76
     Controls
    -0.74
    Quantity
    -0.73
    cks
    -0.72
    bender
    -0.71
    oak
    -0.71
     Skydragon
    -0.71
    xxx
    -0.69
    lehem
    -0.69
    POSITIVE LOGITS
     own
    1.23
     newest
    0.97
     namesake
    0.90
     initials
    0.87
     maiden
    0.87
    ELF
    0.87
     eldest
    0.84
     current
    0.84
     successor
    0.83
     inability
    0.83
    Act Density 0.117%

    No Known Activations