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

    Neuronpedia

    INDEX
    Explanations

    references to politics, particularly related to significant figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramework
    -0.16
    uhn
    -0.14
    arehouse
    -0.14
     Guerr
    -0.14
    OLF
    -0.13
    ubu
    -0.13
     Aware
    -0.13
    sak
    -0.13
    claimer
    -0.13
    allo
    -0.13
    POSITIVE LOGITS
    659
    0.16
    agi
    0.16
    062
    0.15
     spell
    0.15
     lessons
    0.14
    803
    0.14
    320
    0.14
    ("")]↵
    0.14
    .extract
    0.14
     beyond
    0.14
    Act Density 0.309%

    No Known Activations