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

    Neuronpedia

    INDEX
    Explanations

    terms related to authoritative texts or doctrines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "canon" and canonical references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undai
    -0.69
    RANT
    -0.68
    Frameworks
    -0.67
    -+
    -0.66
     Pupp
    -0.65
    wx
    -0.63
    Beaut
    -0.62
    ungle
    -0.60
    inx
    -0.60
    pants
    -0.60
    POSITIVE LOGITS
    icals
    1.26
    icity
    1.13
    ical
    1.10
    ically
    1.03
    icles
    1.02
    ervative
    0.90
    esan
    0.88
    icle
    0.87
    canon
    0.86
    ization
    0.85
    Act Density 0.034%

    No Known Activations