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

    Neuronpedia

    INDEX
    Explanations

    references to various scientific professions and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ameda
    -0.17
    erez
    -0.16
    ukan
    -0.16
    loh
    -0.15
    uet
    -0.15
    318
    -0.15
    ÅĤaw
    -0.15
    hest
    -0.15
    anine
    -0.15
    RAY
    -0.14
    POSITIVE LOGITS
    /engine
    0.23
    urally
    0.23
    ically
    0.23
    MBED
    0.19
    ural
    0.19
    otle
    0.18
    /math
    0.17
    /sc
    0.17
    /stat
    0.17
    -client
    0.16
    Act Density 0.116%

    No Known Activations