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

    Neuronpedia

    INDEX
    Explanations

    instances of possessive pronouns and expressions of uncertainty or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    682
    -0.15
     Gil
    -0.15
    ance
    -0.14
    rieb
    -0.14
    steen
    -0.14
    幸
    -0.14
    unga
    -0.14
    BuilderFactory
    -0.14
    izo
    -0.13
    oyo
    -0.13
    POSITIVE LOGITS
     Recorder
    0.16
    ëıħ
    0.15
    nova
    0.15
    ify
    0.15
    etas
    0.15
    thew
    0.14
    elize
    0.14
    iese
    0.14
    ypress
    0.14
    etest
    0.14
    Act Density 0.049%

    No Known Activations