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

    Neuronpedia

    INDEX
    Explanations

    constructions involving possessive forms of 'is' and 'are'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’s
    -0.26
    ’m
    -0.19
    å£°éŁ³
    -0.18
    ’n
    -0.18
    ‘s
    -0.17
    ä¸ĢäºĽ
    -0.17
    大
    -0.16
     latter
    -0.16
    æĥħåĨµ
    -0.16
    ologically
    -0.15
    POSITIVE LOGITS
     been
    0.42
     got
    0.32
     gotta
    0.29
    been
    0.29
     not
    0.29
     Been
    0.29
     BEEN
    0.28
     gonna
    0.27
    /'
    0.24
    got
    0.22
    Act Density 0.293%

    No Known Activations