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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific numerical sequences (e.g., "3rd and short")

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.79
    ONSORED
    -0.70
    achine
    -0.70
    exempt
    -0.68
    bo
    -0.66
    stals
    -0.66
    GD
    -0.65
    edIn
    -0.64
    ubi
    -0.62
    casts
    -0.62
    POSITIVE LOGITS
     foremost
    0.99
     mids
    0.75
    rogen
    0.73
     parcel
    0.68
     limb
    0.67
     consequently
    0.67
    rogens
    0.67
     balcony
    0.66
     shoulders
    0.64
     vice
    0.64
    Act Density 0.212%

    No Known Activations