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

    Neuronpedia

    INDEX
    Explanations

    terms related to political, historical, and security-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative, social, or political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thia
    -0.74
    Dialogue
    -0.73
    ventus
    -0.73
    ecause
    -0.70
    Ô
    -0.68
    morrow
    -0.68
    hops
    -0.67
     Helpful
    -0.67
    ipedia
    -0.66
    TeX
    -0.66
    POSITIVE LOGITS
     acronym
    0.98
     onslaught
    0.91
     moniker
    0.86
     enclave
    0.85
     duo
    0.84
     tide
    0.83
     saga
    0.83
     ordeal
    0.83
     trio
    0.83
    liest
    0.82
    Act Density 0.477%

    No Known Activations