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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rs
    -0.15
    ams
    -0.15
     Manning
    -0.15
     gent
    -0.15
    inc
    -0.15
     unserialize
    -0.14
     Straw
    -0.14
    ue
    -0.14
    oust
    -0.14
     SIL
    -0.14
    POSITIVE LOGITS
    éli
    0.16
     jadx
    0.16
    .SDK
    0.15
    본
    0.15
    ¯ÃĤ
    0.15
    igidBody
    0.15
    .XR
    0.14
     DISCLAIM
    0.14
    lanma
    0.14
    azeera
    0.14
    Act Density 0.060%

    No Known Activations