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

    Neuronpedia

    INDEX
    Explanations

    numbers and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and price-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amac
    -0.50
     predec
    -0.46
     comr
    -0.45
    ensibly
    -0.44
     behav
    -0.43
     ensued
    -0.42
    hester
    -0.41
     homegrown
    -0.41
     acron
    -0.41
    arya
    -0.41
    POSITIVE LOGITS
     crore
    0.53
    minimum
    0.52
    00
    0.51
    576
    0.51
     apiece
    0.50
     increments
    0.50
    cycles
    0.49
    GHz
    0.49
    50
    0.48
    mk
    0.48
    Act Density 0.530%

    No Known Activations