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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and phrases related to governance and social institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instead
    -0.19
    instead
    -0.19
     вмеÑģÑĤ
    -0.16
    irates
    -0.16
    irá
    -0.16
    iri
    -0.15
    fid
    -0.15
    åħ¼
    -0.14
    eral
    -0.14
    oreach
    -0.14
    POSITIVE LOGITS
     Ùħباش
    0.19
    /non
    0.16
     anymore
    0.15
    upo
    0.15
    å±Ĭ
    0.15
    ä½Ĩ
    0.14
    nero
    0.14
     alone
    0.14
     altogether
    0.14
    arella
    0.14
    Act Density 0.153%

    No Known Activations