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

    Neuronpedia

    INDEX
    Explanations

    phrases related to world-class excellence or recognition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to world-renowned entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ell
    -0.75
    BILITIES
    -0.67
     HI
    -0.67
     Inventory
    -0.66
     simulac
    -0.64
     Salvador
    -0.64
     Burr
    -0.63
     Finch
    -0.63
     charcoal
    -0.62
     Shooter
    -0.62
    POSITIVE LOGITS
    famous
    1.37
    wide
    1.37
    saving
    1.28
    leading
    1.26
    changing
    1.20
    span
    1.15
    class
    1.13
    record
    1.12
    worst
    1.12
    standard
    1.10
    Act Density 0.042%

    No Known Activations