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

    Neuronpedia

    INDEX
    Explanations

    terms related to expediting or speeding up processes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with efficiency and expedited processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.93
    corn
    -0.79
    pour
    -0.78
    Fram
    -0.71
    REE
    -0.66
    wine
    -0.65
    REL
    -0.64
     Soda
    -0.63
    Ùİ
    -0.62
     Dome
    -0.62
    POSITIVE LOGITS
     exped
    1.27
    itions
    1.04
    iency
    0.96
    ited
    0.96
    itious
    0.87
    ient
    0.87
    itous
    0.87
    anced
    0.87
    iencies
    0.85
     forwarding
    0.84
    Act Density 0.007%

    No Known Activations