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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, likely in a news or sports context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain a variety of suffixes or endings, indicating a focus on morphological variations of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     capit
    -0.70
     ($)
    -0.70
    cape
    -0.62
    Downloadha
    -0.58
    thodox
    -0.58
    nexus
    -0.57
    maxwell
    -0.56
     vulner
    -0.55
     reckoning
    -0.55
    Ô
    -0.55
    POSITIVE LOGITS
    essor
    0.79
    uve
    0.74
    ardo
    0.73
    estern
    0.71
    ornia
    0.70
    ixt
    0.70
     Ramos
    0.69
    rama
    0.69
     Phelps
    0.69
    ario
    0.67
    Act Density 0.300%

    No Known Activations