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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulation, standards, or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooth
    -0.19
    igne
    -0.18
    วย
    -0.16
    asa
    -0.15
    less
    -0.15
    ovnÄĽ
    -0.15
    erty
    -0.15
    zia
    -0.14
    zy
    -0.14
    èį·
    -0.14
    POSITIVE LOGITS
    $$$$
    0.15
    ´Ģ
    0.15
    иÑĪ
    0.15
    خت
    0.15
    apper
    0.14
    axon
    0.14
    atu
    0.14
    RAD
    0.13
    hdr
    0.13
    LL
    0.13
    Act Density 0.041%

    No Known Activations