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

    Neuronpedia

    INDEX
    Explanations

    questions beginning with "What"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uga
    -0.15
    umer
    -0.14
    zet
    -0.14
    /includes
    -0.14
    ils
    -0.14
    cesso
    -0.14
     haf
    -0.14
     Mun
    -0.13
    unes
    -0.13
    panies
    -0.13
    POSITIVE LOGITS
    razier
    0.18
    nick
    0.16
    CAA
    0.15
    æį·
    0.14
    ieri
    0.14
    ätz
    0.14
    ubu
    0.14
    ollo
    0.13
    mere
    0.13
    RetVal
    0.13
    Act Density 0.042%

    No Known Activations