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

    Neuronpedia

    INDEX
    Explanations

    aspects related to film production

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.80
     disadvant
    -0.78
     loopholes
    -0.76
     pretext
    -0.76
     comprom
    -0.75
     cumbers
    -0.72
     rhy
    -0.71
     contrace
    -0.71
     constitu
    -0.71
    arios
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.17
    ATH
    0.99
    Ļ
    0.92
    éĩ
    0.91
    SHIP
    0.91
    女
    0.90
    ×Ķ
    0.88
    İ
    0.88
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.87
    士
    0.86
    Act Density 0.491%

    No Known Activations