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

    Neuronpedia

    INDEX
    Explanations

    phrases related to speeding up or facilitating processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of expediting processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤº
    -0.66
    dash
    -0.66
    maker
    -0.65
    ktop
    -0.64
     Imran
    -0.64
     Maker
    -0.64
    plate
    -0.64
    cloth
    -0.62
     Pixie
    -0.61
    blank
    -0.61
    POSITIVE LOGITS
    itions
    1.35
    ited
    1.25
    ition
    1.23
    itive
    1.19
    iting
    1.12
    itional
    1.10
    itors
    1.07
    iency
    1.06
    itionally
    1.03
    itives
    1.02
    Act Density 0.045%

    No Known Activations