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

    Neuronpedia

    INDEX
    Explanations

    instances of possessiveness and personal ownership

    oai_token-act-pair · gpt-3.5-turbo

    expressions of ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.62
     occasional
    -0.62
    eatures
    -0.57
     gradual
    -0.53
     bulky
    -0.53
     intermittent
    -0.52
     vast
    -0.52
     ubiquitous
    -0.52
     ellipt
    -0.51
     inconsist
    -0.51
    POSITIVE LOGITS
    _.
    1.11
    .#
    1.07
    .
    1.03
    *.
    1.03
    .?
    0.99
    .*
    0.95
    ãĢĤ
    0.95
    .:
    0.95
    .</
    0.94
    .''
    0.92
    Act Density 1.188%

    No Known Activations