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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to personal belongings or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isode
    -0.16
    io
    -0.15
    pell
    -0.15
    佩
    -0.15
    ering
    -0.14
    est
    -0.14
    estar
    -0.14
    wers
    -0.14
     jej
    -0.14
     sede
    -0.14
    POSITIVE LOGITS
    vala
    0.16
    558
    0.15
    /stretch
    0.14
     yans
    0.14
    ymb
    0.14
     Suff
    0.14
    alyzed
    0.14
    ->{$
    0.14
    ¤ij
    0.13
    ĶåĽŀ
    0.13
    Act Density 0.181%

    No Known Activations