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

    Neuronpedia

    INDEX
    Explanations

    names or titles preceded by a title such as Dr. or Ambassador

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of individuals and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iations
    -0.83
    querque
    -0.77
     stocking
    -0.77
    ragon
    -0.76
    alogue
    -0.74
    dayName
    -0.72
    obyl
    -0.70
    romeda
    -0.69
    atu
    -0.67
    NUM
    -0.67
    POSITIVE LOGITS
     Ji
    1.12
    iour
    0.79
     Suk
    0.76
    gio
    0.74
    nee
    0.74
    ð
    0.72
     Sang
    0.70
    inka
    0.69
    Ws
    0.69
     Fey
    0.69
    Act Density 0.018%

    No Known Activations