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

    Neuronpedia

    INDEX
    Explanations

    references to standards for evaluating performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Toll
    -0.18
    enco
    -0.17
    obus
    -0.15
    AI
    -0.14
    ÛĮÚ©ÛĮ
    -0.14
     Matters
    -0.14
     Them
    -0.13
     Portal
    -0.13
    SE
    -0.13
     Auch
    -0.13
    POSITIVE LOGITS
    209
    0.18
    ItemSelectedListener
    0.17
    /reference
    0.15
    oeff
    0.15
    lace
    0.15
     performances
    0.15
    .KeyChar
    0.15
    ister
    0.15
    ing
    0.14
    fluid
    0.14
    Act Density 0.005%

    No Known Activations