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

    Neuronpedia

    INDEX
    Explanations

    instances of the apostrophe used in possessive or contracted forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.17
    нг
    -0.16
    er
    -0.16
    en
    -0.16
    ses
    -0.15
    ity
    -0.14
    rone
    -0.14
    o
    -0.14
    aad
    -0.14
    ر
    -0.14
    POSITIVE LOGITS
     themselves
    0.17
    ibraltar
    0.15
    ÑģÑı
    0.14
    ever
    0.14
    Âĺ
    0.13
    ollower
    0.13
    بÙĪاسطة
    0.13
    /*č↵
    0.13
    ches
    0.13
    /student
    0.13
    Act Density 0.034%

    No Known Activations