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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or ownership

    oai_token-act-pair · gpt-3.5-turbo

    the possessive form of "their" in relation to personal experiences or responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Unsure
    -0.89
    bender
    -0.87
    vine
    -0.85
    epad
    -0.82
    ozy
    -0.74
    cation
    -0.73
    rower
    -0.71
    APTER
    -0.70
    cedented
    -0.69
     Swordsman
    -0.69
    POSITIVE LOGITS
     respective
    1.72
     own
    1.60
    selves
    1.48
     counterparts
    1.46
     selves
    1.43
     spouses
    1.37
     careers
    1.37
     bodies
    1.34
     husbands
    1.34
     necks
    1.33
    Act Density 0.233%

    No Known Activations