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

    Neuronpedia

    INDEX
    Explanations

    words related to indexing, formatting, and technical elements present in text

    oai_token-act-pair · gpt-3.5-turbo

    various symbols, numbers, and structural elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Liberties
    -0.68
    ival
    -0.66
     698
    -0.66
    rek
    -0.65
    468
    -0.62
     elim
    -0.61
    748
    -0.61
     Sloven
    -0.59
    678
    -0.59
    unal
    -0.59
    POSITIVE LOGITS
    111
    0.97
    11
    0.94
    911
    0.86
    211
    0.85
    1111
    0.85
    2011
    0.84
    411
    0.84
     111
    0.83
     11
    0.83
     411
    0.80
    Act Density 0.076%

    No Known Activations