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

    Neuronpedia

    INDEX
    Explanations

    phone numbers in different formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and contact information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    defense
    -0.88
     victimized
    -0.88
     honoring
    -0.87
    colored
    -0.86
    Defense
    -0.85
     totaling
    -0.85
     neighborhoods
    -0.84
     Anaheim
    -0.81
    imize
    -0.80
     savior
    -0.79
    POSITIVE LOGITS
     recognise
    1.46
     organise
    1.43
     realise
    1.41
     recognised
    1.38
     enqu
    1.38
     organising
    1.38
     £
    1.38
     organisation
    1.37
     programme
    1.33
     emphas
    1.33
    Act Density 1.321%

    No Known Activations