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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those related to a specific context or event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pride
    -0.67
     Sussex
    -0.66
     Curse
    -0.61
     swamp
    -0.59
     Indians
    -0.58
     dividend
    -0.57
     slack
    -0.56
     Naruto
    -0.56
     graffiti
    -0.55
     tyre
    -0.55
    POSITIVE LOGITS
    mann
    1.79
    strom
    1.58
    feld
    1.54
    lund
    1.49
    gren
    1.46
    berg
    1.46
    meyer
    1.43
    quist
    1.42
    baum
    1.41
    stein
    1.38
    Act Density 0.102%

    No Known Activations