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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "By" followed by associated categorical phrases or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efeller
    -0.16
     Blow
    -0.15
    aison
    -0.14
    æŁ±
    -0.14
    ahat
    -0.13
    plx
    -0.13
     depress
    -0.13
    à¥įयत
    -0.13
    åĨ
    -0.13
    leton
    -0.13
    POSITIVE LOGITS
    еÑİ
    0.17
    _substr
    0.16
    IMIT
    0.15
    ogne
    0.14
    (savedInstanceState
    0.14
    alley
    0.14
    дÑĢеÑģ
    0.13
    ICI
    0.13
    ÏĦεί
    0.13
    imos
    0.13
    Act Density 0.004%

    No Known Activations