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

    Neuronpedia

    INDEX
    Explanations

    words related to fundamental concepts or central aspects of a topic

    oai_token-act-pair · gpt-3.5-turbo

    references to fundamental principles or essential elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Laksh
    -0.69
    ilon
    -0.67
    channelAvailability
    -0.66
    OTOS
    -0.66
     tempered
    -0.66
    levard
    -0.64
    hops
    -0.62
    pload
    -0.61
     annexed
    -0.61
    DERR
    -0.61
    POSITIVE LOGITS
     tenets
    1.14
    lig
    1.09
     compet
    1.07
    opsis
    1.02
     principles
    0.99
     beliefs
    0.91
     premise
    0.89
     belief
    0.85
     values
    0.84
     competence
    0.83
    Act Density 0.035%

    No Known Activations