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

    Neuronpedia

    INDEX
    Explanations

    references to the city "Ottawa"

    oai_token-act-pair · gpt-3.5-turbo

    references to types of data or information sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    draft
    -0.74
    igree
    -0.72
    brow
    -0.69
    dress
    -0.69
    stroke
    -0.69
    s
    -0.67
    sed
    -0.67
     directions
    -0.66
    sheet
    -0.66
    itchie
    -0.65
    POSITIVE LOGITS
    ota
    1.21
    OTA
    0.89
    iba
    0.82
    oba
    0.78
     Luxem
    0.78
    wana
    0.78
    anu
    0.78
    ague
    0.77
    rolet
    0.77
    une
    0.77
    Act Density 0.006%

    No Known Activations