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

    Neuronpedia

    INDEX
    Explanations

    prompts asking users to confirm they are not robots by checking a box or performing an action

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢİ
    -0.83
     gravy
    -0.70
    ways
    -0.63
     adj
    -0.59
     adv
    -0.59
     tact
    -0.58
    kaya
    -0.57
    imer
    -0.57
     tert
    -0.55
    itional
    -0.55
    POSITIVE LOGITS
     Invalid
    1.14
     Copy
    0.66
    Invalid
    0.65
     è£ıè
    0.64
    ItemTracker
    0.62
    Submit
    0.62
     Please
    0.61
     Errors
    0.61
    perture
    0.60
     Thumbnails
    0.59
    Act Density 0.012%

    No Known Activations