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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morse
    -0.17
    mit
    -0.16
    n
    -0.14
    CMP
    -0.14
    verb
    -0.14
     &
    -0.14
    avers
    -0.14
    INU
    -0.14
     event
    -0.14
    quarter
    -0.13
    POSITIVE LOGITS
    ripp
    0.15
    .stamp
    0.15
    roker
    0.15
    serter
    0.15
    hti
    0.15
    onian
    0.15
    htdocs
    0.15
    OptionsMenu
    0.15
    ilon
    0.15
    udur
    0.14
    Act Density 0.743%

    No Known Activations