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

    Neuronpedia

    INDEX
    Explanations

    titles or names followed by a preposition 'of'

    oai_token-act-pair · gpt-3.5-turbo

    titles of creative works, particularly those that include the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athered
    -0.76
    nown
    -0.75
     congratulations
    -0.72
     forefront
    -0.70
     stewards
    -0.70
     "$:/
    -0.69
     sooner
    -0.69
    rouse
    -0.68
     forth
    -0.68
     condemnation
    -0.68
    POSITIVE LOGITS
     Madness
    0.86
     Mind
    0.85
     Mem
    0.85
     Us
    0.82
     Affairs
    0.82
     Them
    0.79
     Illusion
    0.79
     Seasons
    0.79
     Things
    0.79
     Programming
    0.78
    Act Density 0.109%

    No Known Activations