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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raison
    -0.15
    owied
    -0.15
    ernals
    -0.15
    arness
    -0.14
    ERGY
    -0.14
     bắt
    -0.14
    iê
    -0.14
    baru
    -0.14
    .statistics
    -0.14
    درس
    -0.14
    POSITIVE LOGITS
     behalf
    0.50
     occasions
    0.26
     occasion
    0.26
     basis
    0.24
     heels
    0.22
    lap
    0.20
     radar
    0.19
     doorstep
    0.19
     shoulders
    0.19
     dime
    0.19
    Act Density 0.040%

    No Known Activations