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

    Neuronpedia

    INDEX
    Explanations

    terms related to access and accessibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ationToken
    -0.17
    AVE
    -0.15
     Affero
    -0.15
    اÛĮت
    -0.15
    ongan
    -0.15
    -footer
    -0.14
    rena
    -0.14
    ole
    -0.14
    COME
    -0.14
    ong
    -0.14
    POSITIVE LOGITS
    ibly
    0.28
    ibilities
    0.20
    ions
    0.20
    orial
    0.19
    yonel
    0.19
    ibilit
    0.18
    ibility
    0.18
    IBLE
    0.18
    ories
    0.17
    ability
    0.17
    Act Density 0.049%

    No Known Activations