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

    Neuronpedia

    INDEX
    Explanations

    publications and their corresponding dates in the format: Day, Month Date, Year

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Published" indicating publication dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.90
    pt
    -0.80
    umatic
    -0.80
    ixel
    -0.77
    gger
    -0.76
    adows
    -0.76
    aps
    -0.75
    ander
    -0.75
    ø
    -0.75
    ift
    -0.74
    POSITIVE LOGITS
    Published
    1.19
     behavi
    0.88
    âĸ¬
    0.87
    lishing
    0.86
    ãĤ´
    0.86
    Ô
    0.84
     Published
    0.81
    âĸ¬âĸ¬
    0.81
    lisher
    0.80
    NESS
    0.80
    Act Density 0.010%

    No Known Activations