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

    Neuronpedia

    INDEX
    Explanations

    adverbs denoting high degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifying adverbs that express strong emotions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliate
    -0.79
    ibling
    -0.76
    chens
    -0.72
     Receiver
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.70
    ource
    -0.69
    rule
    -0.68
    iture
    -0.66
    former
    -0.66
     Prospect
    -0.66
    POSITIVE LOGITS
     comfortable
    1.01
     uncomfortable
    0.99
     useful
    0.89
     noticeable
    0.89
     interesting
    0.87
     aggressive
    0.86
     awkward
    0.85
     competent
    0.83
     helpful
    0.83
     productive
    0.83
    Act Density 0.172%

    No Known Activations