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

    Neuronpedia

    INDEX
    Explanations

    instances of the apostrophe character used in possessive forms or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    a
    -0.18
    i
    -0.17
    à¸Ļ
    -0.17
    ا
    -0.16
    ity
    -0.16
    m
    -0.16
    er
    -0.15
    y
    -0.15
    icity
    -0.15
    en
    -0.15
    POSITIVE LOGITS
    ibraltar
    0.18
     themselves
    0.16
    /*č↵
    0.16
    /'
    0.16
    uber
    0.15
    Å¡k
    0.15
    ches
    0.14
    eting
    0.14
    ÑįÑĤомÑĥ
    0.14
    bsites
    0.14
    Act Density 0.044%

    No Known Activations