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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or limitation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating limitation or exclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.66
    device
    -0.62
    etheless
    -0.62
    multipl
    -0.60
    robat
    -0.60
    atin
    -0.60
    odus
    -0.59
     Dru
    -0.59
    successfully
    -0.59
    ashington
    -0.58
    POSITIVE LOGITS
     marginally
    0.83
     spor
    0.82
     ONE
    0.78
     limited
    0.72
     fraction
    0.71
     insofar
    0.70
    ifiable
    0.70
    iffe
    0.70
     finite
    0.69
     ones
    0.67
    Act Density 0.187%

    No Known Activations