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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal terms and government entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chunks
    -0.72
     fert
    -0.65
     warp
    -0.64
     Linear
    -0.62
     fortun
    -0.62
    ModLoader
    -0.61
     Canaan
    -0.60
     adolesc
    -0.60
     Clever
    -0.59
     sacrific
    -0.59
    POSITIVE LOGITS
    ship
    1.06
    iversary
    1.04
    cation
    1.01
    swer
    1.00
    s
    0.96
    utive
    0.94
    tyard
    0.91
    office
    0.90
    ution
    0.89
    of
    0.85
    Act Density 0.243%

    No Known Activations