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

    Neuronpedia

    INDEX
    Explanations

    occurrences of first-person pronouns and related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erif
    -0.17
    llib
    -0.16
     now
    -0.16
    èīĩ
    -0.15
     recently
    -0.15
     soon
    -0.15
     lately
    -0.15
    ocoder
    -0.14
    ZN
    -0.14
    à¸Ħว
    -0.14
    POSITIVE LOGITS
    εÏħ
    0.16
     instead
    0.16
    unday
    0.15
    .mj
    0.15
    ake
    0.15
     will
    0.15
    DAY
    0.14
     Instead
    0.14
    .fromRGBO
    0.14
    okus
    0.14
    Act Density 0.090%

    No Known Activations