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

    Neuronpedia

    INDEX
    Explanations

    possessive forms or contractions indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -0.26
     a
    -0.21
     an
    -0.19
     these
    -0.18
     those
    -0.18
     some
    -0.18
     something
    -0.17
    人åĵ¡
    -0.17
     this
    -0.17
     what
    -0.17
    POSITIVE LOGITS
     own
    0.52
     newest
    0.41
     latest
    0.38
     biggest
    0.34
    own
    0.33
     largest
    0.32
     entire
    0.30
    '
    0.29
     Own
    0.29
     youngest
    0.29
    Act Density 0.350%

    No Known Activations