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

    Neuronpedia

    INDEX
    Explanations

    quotations from various individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements attributed to speakers or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -0.71
    Exit
    -0.70
    pee
    -0.70
    hack
    -0.69
    ILA
    -0.68
    colored
    -0.68
    toggle
    -0.67
    ãģ¨
    -0.67
    Newsletter
    -0.66
    ANA
    -0.66
    POSITIVE LOGITS
     apologised
    1.00
     whilst
    0.96
     afterwards
    0.95
     organising
    0.92
     analys
    0.89
     criticised
    0.88
     organisers
    0.88
     emphas
    0.87
     £
    0.86
     humour
    0.85
    Act Density 0.252%

    No Known Activations