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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "are"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the properties, functions, or characteristics of various subjects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.77
    FTWARE
    -0.75
    LOG
    -0.71
    CCC
    -0.68
    iates
    -0.66
    INTON
    -0.65
     Ago
    -0.65
    00007
    -0.64
    2020
    -0.64
    ipop
    -0.63
    POSITIVE LOGITS
    senal
    1.05
     typically
    1.04
     inherently
    1.03
     rarely
    1.02
     prolifer
    1.02
     notoriously
    1.01
     everywhere
    1.01
     generally
    1.00
     usually
    0.99
     often
    0.98
    Act Density 0.278%

    No Known Activations