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

    Neuronpedia

    INDEX
    Explanations

    capital letters at the beginning of a word or abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    single-letter or short acronyms and their significance in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pony
    -0.72
     FIRST
    -0.67
    ãĢı
    -0.65
     SUPER
    -0.64
     Hobbit
    -0.64
    Ħ¢
    -0.63
     PATH
    -0.63
     Incarnation
    -0.63
     LEGO
    -0.63
     WAY
    -0.62
    POSITIVE LOGITS
    ocally
    1.29
    ately
    1.20
    sequently
    1.20
    ifully
    1.18
    rarily
    1.18
    ogether
    1.17
    pecially
    1.16
    itionally
    1.16
    cially
    1.13
    beit
    1.13
    Act Density 0.257%

    No Known Activations