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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    sequences involving backticks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     division
    -0.76
     dividing
    -0.67
     Burnett
    -0.66
    terday
    -0.65
     Lancaster
    -0.64
     Mamm
    -0.63
    ampton
    -0.63
     Liver
    -0.61
     Farn
    -0.61
     Starship
    -0.61
    POSITIVE LOGITS
    taboola
    1.03
     `
    1.00
    mons
    0.77
    wcsstore
    0.75
    uggets
    0.75
    endi
    0.74
    TY
    0.74
    POSE
    0.74
    desktop
    0.74
    seq
    0.72
    Act Density 0.006%

    No Known Activations