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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veau
    -0.17
     hend
    -0.14
    ursive
    -0.14
    usch
    -0.13
     Beste
    -0.13
    pleted
    -0.13
    oon
    -0.13
    .cz
    -0.13
    aily
    -0.13
    оÑĢе
    -0.12
    POSITIVE LOGITS
    heimer
    0.17
    volt
    0.15
    ÃŃÅĻ
    0.15
    redo
    0.14
    memberof
    0.14
    grunt
    0.14
    isci
    0.14
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.14
    PostBack
    0.14
    βο
    0.14
    Act Density 0.051%

    No Known Activations