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

    Neuronpedia

    INDEX
    Explanations

    the symbol 'Ŀ'

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that represent a significant concept or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tricked
    -0.85
     revived
    -0.85
     camoufl
    -0.83
     salv
    -0.82
     resemblance
    -0.82
     imperson
    -0.81
     resurrected
    -0.79
     untouched
    -0.77
     dreamed
    -0.76
     flavour
    -0.76
    POSITIVE LOGITS
    ï¸ı
    1.23
     Additionally
    1.22
    However
    1.19
     Unfortunately
    1.18
    Additionally
    1.17
    Therefore
    1.17
     Furthermore
    1.13
     However
    1.10
     Therefore
    1.10
     Similarly
    1.09
    Act Density 0.145%

    No Known Activations