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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’s
    -0.23
    ä¸ĢäºĽ
    -0.18
     latter
    -0.18
    æĥħåĨµ
    -0.17
    ‘s
    -0.17
    ’m
    -0.16
    å£°éŁ³
    -0.16
    ’n
    -0.15
    大
    -0.15
    ously
    -0.15
    POSITIVE LOGITS
     been
    0.40
     got
    0.33
     gotta
    0.29
     Been
    0.28
    been
    0.28
     BEEN
    0.27
     gonna
    0.26
     not
    0.25
    got
    0.23
    Got
    0.22
    Act Density 0.321%

    No Known Activations