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

    Neuronpedia

    INDEX
    Explanations

    any instance of the word "else"

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning alternatives or additional possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mehran
    -0.68
     Abstract
    -0.62
    gers
    -0.61
    forestation
    -0.61
    tein
    -0.61
    acity
    -0.60
     Encyclopedia
    -0.60
    Upload
    -0.59
    ge
    -0.59
    ousands
    -0.58
    POSITIVE LOGITS
    worldly
    1.31
     besides
    1.00
     entirely
    0.81
    where
    0.75
    mia
    0.71
    cooked
    0.67
    ptive
    0.66
     nearby
    0.66
    .}
    0.65
     includ
    0.65
    Act Density 0.037%

    No Known Activations