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

    Neuronpedia

    INDEX
    Explanations

    terms related to the evaluation and calibration of models and protocols in research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wheel
    -0.14
    zdy
    -0.14
    spir
    -0.14
    ami
    -0.13
    astery
    -0.13
    ayne
    -0.13
     Lowest
    -0.13
    å©·
    -0.13
     Beste
    -0.13
     unset
    -0.13
    POSITIVE LOGITS
    oppel
    0.17
    atee
    0.15
    olic
    0.15
    elder
    0.15
    erras
    0.14
    βολ
    0.14
    olate
    0.14
    èĪį
    0.14
    .setTimeout
    0.14
     getMenu
    0.13
    Act Density 0.267%

    No Known Activations