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

    Neuronpedia

    INDEX
    Explanations

    unusual unicode characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the vowel 'i'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.91
     compr
    -0.87
     subsequ
    -0.84
     confir
    -0.83
     srf
    -0.83
     traged
    -0.82
     misunder
    -0.82
    theless
    -0.82
     condem
    -0.81
     undercover
    -0.81
    POSITIVE LOGITS
    cup
    0.99
    æµ
    0.94
    į
    0.94
    ı
    0.93
    ÙĪ
    0.93
    ł
    0.92
    ä¼
    0.92
    âĶģ
    0.88
    Ùħ
    0.85
    IJ
    0.85
    Act Density 0.002%

    No Known Activations