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 their use in relation to different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lement
    -0.78
    thood
    -0.74
    bender
    -0.73
    cook
    -0.73
    eers
    -0.71
    inctions
    -0.68
    ontent
    -0.68
    upon
    -0.67
    unct
    -0.67
    encers
    -0.65
    POSITIVE LOGITS
     behalf
    1.36
     periphery
    1.28
     own
    1.26
     doorstep
    1.21
     heels
    1.19
     shoulders
    1.18
     knees
    1.17
     occasions
    0.99
     footing
    0.97
     pedest
    0.97
    Act Density 0.089%

    No Known Activations