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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ongoing action or states of existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oops
    -0.63
     Kills
    -0.62
     Declaration
    -0.62
     Apart
    -0.60
    ace
    -0.59
    /+
    -0.58
     uproar
    -0.55
    Else
    -0.55
     Extension
    -0.55
     clicks
    -0.54
    POSITIVE LOGITS
     been
    1.49
     gotten
    1.34
    been
    1.31
     undergone
    1.16
     tended
    1.15
     taken
    1.13
     relied
    1.12
     struggled
    1.11
     Been
    1.10
     benefited
    1.09
    Act Density 0.285%

    No Known Activations