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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.64
    ologies
    -0.64
    abre
    -0.63
    isse
    -0.62
    iden
    -0.61
    mares
    -0.60
    ively
    -0.60
    inent
    -0.59
    pill
    -0.56
    oxide
    -0.56
    POSITIVE LOGITS
    vernment
    1.10
    iants
    0.95
    glers
    0.86
    roups
    0.85
    raphic
    0.80
    hetto
    0.80
    irlfriend
    0.79
    reens
    0.77
    ourmet
    0.76
    reetings
    0.76
    Act Density 0.179%

    No Known Activations