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

    Neuronpedia

    INDEX
    Explanations

    references to government entities and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozem
    -0.16
    roup
    -0.16
    curity
    -0.16
    odb
    -0.15
    abler
    -0.14
    RITE
    -0.14
    lus
    -0.14
    033
    -0.14
    .community
    -0.14
    ington
    -0.14
    POSITIVE LOGITS
    wide
    0.21
    frey
    0.18
    al
    0.18
    /local
    0.17
    /state
    0.17
    ally
    0.17
    /public
    0.17
     shutdown
    0.15
    -wide
    0.15
    -owned
    0.15
    Act Density 0.040%

    No Known Activations