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

    Neuronpedia

    INDEX
    Explanations

    dates and times written in the format of numbers with periods between them

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidel
    -0.78
     stre
    -0.67
    £ı
    -0.65
     shroud
    -0.64
    idence
    -0.63
    uracy
    -0.63
     comparisons
    -0.62
     deceptive
    -0.62
     trouble
    -0.62
     association
    -0.61
    POSITIVE LOGITS
    000
    1.04
    05
    0.99
    07
    0.97
    06
    0.96
    09
    0.95
    5
    0.94
    500
    0.94
    04
    0.94
    08
    0.91
    00
    0.91
    Act Density 0.122%

    No Known Activations