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

    Neuronpedia

    INDEX
    Explanations

    questions that begin with "how" or "why"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orn
    -0.14
    ola
    -0.14
    roe
    -0.14
    504
    -0.14
    idious
    -0.14
    orum
    -0.13
    nio
    -0.13
    OLA
    -0.13
    uzz
    -0.13
    abble
    -0.13
    POSITIVE LOGITS
     ever
    0.17
    ever
    0.15
    Machine
    0.14
    Ever
    0.14
    alsy
    0.14
     MACHINE
    0.14
    anza
    0.14
    -ever
    0.14
    IAS
    0.14
    oba
    0.14
    Act Density 0.095%

    No Known Activations