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

    Neuronpedia

    INDEX
    Explanations

    names with a common pattern, likely related to a specific person or topic

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "iy" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mint
    -0.78
    IBLE
    -0.77
    âĹ¼
    -0.75
    olkien
    -0.68
    inates
    -0.66
    ufact
    -0.66
    Else
    -0.65
    ãĥ¼ãĥ«
    -0.64
    wcs
    -0.64
     Hurricanes
    -0.64
    POSITIVE LOGITS
    yah
    1.23
    azaki
    0.94
    yy
    0.94
    adh
    0.92
    ielding
    0.91
    oko
    0.90
    ya
    0.89
    atana
    0.89
    ota
    0.89
    oji
    0.88
    Act Density 0.025%

    No Known Activations