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

    Neuronpedia

    INDEX
    Explanations

    sentences emphasizing a high degree of something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensis
    -0.75
    olor
    -0.73
    osal
    -0.71
    onis
    -0.71
    igi
    -0.68
    ourses
    -0.66
    sburgh
    -0.66
    adelphia
    -0.65
    amel
    -0.64
    iture
    -0.63
    POSITIVE LOGITS
     important
    0.93
     much
    0.92
     nice
    0.90
     informative
    0.89
     difficult
    0.89
     rare
    0.89
     similar
    0.88
     interesting
    0.88
     unlikely
    0.88
     exciting
    0.86
    Act Density 0.305%

    No Known Activations