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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronouns "I" and "I'm" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouce
    -0.15
    anness
    -0.14
    roperties
    -0.14
    ieren
    -0.14
    lege
    -0.14
    úng
    -0.13
    longleftrightarrow
    -0.13
    isure
    -0.13
     TORT
    -0.13
    _png
    -0.13
    POSITIVE LOGITS
    face
    0.20
     recently
    0.20
     have
    0.18
    18
    0.18
     facing
    0.18
     hava
    0.17
     face
    0.17
    éĿ¢
    0.17
     faced
    0.17
     develop
    0.16
    Act Density 0.048%

    No Known Activations