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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to sizes and quantities

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     besides
    -0.78
     Became
    -0.76
    ãĥ»
    -0.73
    iband
    -0.72
    ea
    -0.71
     alongside
    -0.70
     alone
    -0.68
     followed
    -0.67
     namely
    -0.66
     furthermore
    -0.66
    POSITIVE LOGITS
     usual
    1.35
     rest
    1.22
     proverbial
    1.12
     slightest
    1.10
     previous
    1.09
     prevailing
    1.09
     aforementioned
    1.08
     typical
    1.06
     entirety
    1.02
     nearest
    1.00
    Act Density 0.263%

    No Known Activations