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

    Neuronpedia

    INDEX
    Explanations

    government-related acronyms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislation, acronyms, and regulatory bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.88
    ord
    -0.86
    atom
    -0.84
    gaard
    -0.81
    angel
    -0.79
    roman
    -0.77
    iary
    -0.77
    eson
    -0.75
    atz
    -0.75
    ices
    -0.75
    POSITIVE LOGITS
    ISM
    1.27
    TY
    1.17
    ILY
    1.13
    NING
    1.11
    ANC
    1.11
    IST
    1.11
    BOOK
    1.11
    ISE
    1.11
    MY
    1.10
    ANCE
    1.10
    Act Density 0.134%

    No Known Activations