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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating record achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kes
    -0.16
    ç²¾
    -0.15
    ZA
    -0.14
     purpos
    -0.14
    pu
    -0.14
    åī²
    -0.14
     ought
    -0.14
     Jones
    -0.14
    bau
    -0.14
     should
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.18
    itler
    0.16
    ably
    0.14
    gow
    0.14
    levels
    0.13
    ely
    0.13
    LAN
    0.13
    _simps
    0.13
    ilateral
    0.13
    chio
    0.13
    Act Density 0.016%

    No Known Activations