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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    key geographical and political terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    initions
    -0.77
    iage
    -0.70
    insula
    -0.70
    ortment
    -0.68
    robe
    -0.64
    enery
    -0.64
    lihood
    -0.62
     constitution
    -0.61
    etsk
    -0.61
    rity
    -0.61
    POSITIVE LOGITS
    isible
    0.92
    arily
    0.88
    worthy
    0.83
    vable
    0.82
     incarn
    0.81
    eligible
    0.80
    actly
    0.79
    centric
    0.79
    ishly
    0.79
    ivable
    0.79
    Act Density 0.444%

    No Known Activations