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

    Neuronpedia

    INDEX
    Explanations

    the words and entities starting with special characters or unusual symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character 'Ļ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rhy
    -0.77
    awaru
    -0.76
     comprom
    -0.73
    okin
    -0.71
     promoters
    -0.70
    raviolet
    -0.70
     gist
    -0.70
     imitation
    -0.68
     loopholes
    -0.68
    hematic
    -0.66
    POSITIVE LOGITS
    Ļ
    0.99
    ħ
    0.97
    İ
    0.94
    士
    0.90
    女
    0.89
    ×Ķ
    0.87
    ı
    0.87
    ï¸ı
    0.87
    Ľ
    0.85
    ĺ
    0.84
    Act Density 0.484%

    No Known Activations