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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the complexity, diversity, and scale of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the characteristics and intricacies of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oras
    -0.71
    alus
    -0.62
    inis
    -0.60
    eg
    -0.60
    itionally
    -0.59
    xiety
    -0.59
     newsletters
    -0.56
    EMS
    -0.56
    bye
    -0.55
    idav
    -0.55
    POSITIVE LOGITS
     inherent
    1.06
     of
    1.02
    lessness
    1.01
     afforded
    0.98
     thereof
    0.93
    abl
    0.90
    fulness
    0.86
    iness
    0.81
    ality
    0.81
    lihood
    0.80
    Act Density 0.208%

    No Known Activations