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

    Neuronpedia

    INDEX
    Explanations

    references to secrecy and the act of uncovering information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çŃĭ
    -0.15
    ovich
    -0.15
    AZY
    -0.15
    ENAME
    -0.14
     hum
    -0.14
    isky
    -0.14
    edin
    -0.14
    ader
    -0.14
    ollo
    -0.14
    riba
    -0.14
    POSITIVE LOGITS
    wid
    0.15
     MST
    0.15
    .camel
    0.14
    AppBundle
    0.14
    LayoutConstraint
    0.14
    bler
    0.14
    .owl
    0.14
    -online
    0.13
    ukes
    0.13
    Leaks
    0.13
    Act Density 0.157%

    No Known Activations