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

    Neuronpedia

    INDEX
    Explanations

    words related to names, particularly those with "uy" or "roy" in them

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names associated with specific people or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ily
    -0.77
    ivity
    -0.77
    iness
    -0.64
    ieties
    -0.64
    ILY
    -0.63
    iveness
    -0.60
    ially
    -0.59
    essional
    -0.59
     Luther
    -0.59
     tempted
    -0.59
    POSITIVE LOGITS
    gur
    0.83
    vre
    0.80
    ahime
    0.78
    ãĤ¡
    0.78
    utsu
    0.77
    gements
    0.73
    uki
    0.73
    outube
    0.72
    glers
    0.72
    enne
    0.71
    Act Density 0.060%

    No Known Activations