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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nik
    -0.15
    buat
    -0.14
    uru
    -0.13
     íĭ
    -0.13
    ekl
    -0.13
    each
    -0.13
    ubre
    -0.13
    flip
    -0.13
     visc
    -0.13
    RelativeTo
    -0.13
    POSITIVE LOGITS
     ours
    0.25
     particular
    0.25
     version
    0.24
     theirs
    0.23
     situation
    0.23
     own
    0.21
     hers
    0.21
    -version
    0.21
     PARTICULAR
    0.20
    -Version
    0.20
    Act Density 0.120%

    No Known Activations