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

    Neuronpedia

    INDEX
    Explanations

    phrases related to something causing an increase or intensification of a particular situation or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the concept of being 'fueled' or driven by various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perture
    -0.78
    ihad
    -0.76
    roma
    -0.75
    bestos
    -0.71
    achu
    -0.70
    é¾įåĸļ士
    -0.69
    esan
    -0.69
    opers
    -0.68
    atar
    -0.68
    andro
    -0.67
    POSITIVE LOGITS
     fue
    1.12
     fueling
    1.11
     fueled
    0.99
     fuelled
    0.94
    Fuel
    0.84
     fuels
    0.81
    fuel
    0.79
     fuel
    0.78
    ument
    0.77
     Fuel
    0.74
    Act Density 0.015%

    No Known Activations