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

    Neuronpedia

    INDEX
    Explanations

    references to specific product models and issues associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iali
    -0.20
     Aware
    -0.15
    UNET
    -0.15
    MMC
    -0.15
    .Messaging
    -0.14
     Conway
    -0.14
    ../../../../
    -0.14
    isce
    -0.14
    PrototypeOf
    -0.14
    .Promise
    -0.14
    POSITIVE LOGITS
     wing
    0.17
    wing
    0.17
    cki
    0.16
    ed
    0.15
     ÅĻ
    0.15
    opers
    0.15
    build
    0.14
    rs
    0.14
    erais
    0.14
    ester
    0.14
    Act Density 0.320%

    No Known Activations