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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expedited or accelerated processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expediency and processes that are expedited

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.87
    corn
    -0.72
    pour
    -0.69
    Fram
    -0.65
     Leaf
    -0.65
     Rove
    -0.63
    LD
    -0.62
     Soda
    -0.62
     Koch
    -0.62
     Dome
    -0.62
    POSITIVE LOGITS
     exped
    1.45
    itions
    0.97
    iency
    0.90
    uations
    0.87
    ient
    0.87
     dilig
    0.86
    itous
    0.86
    ited
    0.85
    aily
    0.85
    itious
    0.84
    Act Density 0.007%

    No Known Activations