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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of recording or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utom
    -0.19
    imoto
    -0.17
    pt
    -0.17
    ux
    -0.16
    wel
    -0.16
    fw
    -0.15
     UObject
    -0.15
    endor
    -0.15
    uta
    -0.15
     bread
    -0.14
    POSITIVE LOGITS
    -breaking
    0.29
    keeping
    0.28
    breaking
    0.23
    ings
    0.20
    atorio
    0.18
     hete
    0.18
    RTC
    0.17
    -setting
    0.17
    arsers
    0.16
    keeper
    0.16
    Act Density 0.039%

    No Known Activations