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

    Neuronpedia

    INDEX
    Explanations

    the phrase "full-blown."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to exaggeration or something being over the top

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.77
    sie
    -0.76
    ept
    -0.75
    ierre
    -0.75
    orb
    -0.72
    xy
    -0.69
    les
    -0.69
    resses
    -0.68
    idas
    -0.67
    aspers
    -0.67
    POSITIVE LOGITS
    blown
    1.20
    fledged
    0.87
     blown
    0.83
    advertising
    0.82
     Away
    0.74
    assetsadobe
    0.71
     tongues
    0.69
    ULTS
    0.69
    OUT
    0.69
    CLASSIFIED
    0.66
    Act Density 0.017%

    No Known Activations