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

    Neuronpedia

    INDEX
    Explanations

    instances of the contraction "I've"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igated
    -0.15
    uraa
    -0.15
    å£°éŁ³
    -0.15
    gue
    -0.14
    úÄįast
    -0.14
    DMI
    -0.14
    oper
    -0.13
    znik
    -0.13
    Msp
    -0.13
    icals
    -0.13
    POSITIVE LOGITS
    ä¹Ī
    0.14
    atown
    0.14
     Hosp
    0.14
    γÏīγ
    0.14
    lei
    0.14
     Fat
    0.13
    emek
    0.13
    à¸Ńà¸ĩ
    0.13
    urv
    0.13
    ļĮ
    0.12
    Act Density 0.038%

    No Known Activations