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

    Neuronpedia

    INDEX
    Explanations

    phrases specifically related to possessive forms or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.21
    a
    -0.20
    s
    -0.19
    i
    -0.19
    er
    -0.18
    à¸Ļ
    -0.17
    å£°éŁ³
    -0.17
    -so
    -0.16
    ’t
    -0.16
    m
    -0.16
    POSITIVE LOGITS
    /'
    0.20
    ever
    0.16
    eting
    0.16
    ÂĢÂĻ
    0.16
    ÑĥлÑı
    0.14
    /*č↵
    0.14
    pees
    0.14
    ÑįÑĤомÑĥ
    0.14
    /*/
    0.14
    емон
    0.14
    Act Density 0.043%

    No Known Activations