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

    Neuronpedia

    INDEX
    Explanations

    adjectives and adverbs related to quantity and degree

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    utics
    -0.95
    amia
    -0.82
    attery
    -0.80
    Ear
    -0.80
    apons
    -0.79
    ilaterally
    -0.78
    itored
    -0.77
    ushima
    -0.76
    ensis
    -0.75
    their
    -0.74
    POSITIVE LOGITS
     implication
    1.15
     assumption
    1.14
     question
    1.12
     downside
    1.02
     answer
    1.00
     takeaway
    0.99
     caveat
    0.98
     rationale
    0.97
     majority
    0.97
     impetus
    0.96
    Act Density 0.343%

    No Known Activations