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

    Neuronpedia

    INDEX
    Explanations

    phrases related to quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "so" used to emphasize quantity or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prospect
    -0.62
     roundup
    -0.58
     PAL
    -0.55
     Manual
    -0.55
     graz
    -0.54
     NT
    -0.54
     Receiver
    -0.53
     wiser
    -0.53
     Mehran
    -0.53
     Weekly
    -0.53
    POSITIVE LOGITS
     many
    1.36
     much
    1.20
    apy
    1.11
    oooo
    1.09
    ooo
    1.06
    many
    1.03
    bered
    1.01
    aps
    0.98
    oths
    0.98
    oooooooo
    0.96
    Act Density 0.056%

    No Known Activations