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

    Neuronpedia

    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terminology or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategor
    -0.66
     overlap
    -0.56
     VIEW
    -0.56
    wcs
    -0.55
     reading
    -0.53
    ogen
    -0.52
     silence
    -0.51
     bol
    -0.51
     archived
    -0.50
     objection
    -0.50
    POSITIVE LOGITS
    ensis
    0.77
    sylv
    0.70
    naire
    0.70
    ield
    0.65
    ë
    0.65
    ļé
    0.64
    ruary
    0.63
    espie
    0.63
    reme
    0.62
    illon
    0.61
    Act Density 0.539%

    No Known Activations