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

    Neuronpedia

    INDEX
    Explanations

    keywords related to structure and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reflex
    -0.16
    kowski
    -0.16
    lane
    -0.15
    obs
    -0.15
    zzo
    -0.15
     propTypes
    -0.14
    oste
    -0.14
    omy
    -0.14
    adr
    -0.14
    ec
    -0.14
    POSITIVE LOGITS
    ocu
    0.16
    ntity
    0.16
    adesh
    0.16
    eneg
    0.16
    akis
    0.15
    Spy
    0.14
    MES
    0.14
    sass
    0.14
    ikki
    0.14
    lein
    0.14
    Act Density 0.001%

    No Known Activations