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

    Neuronpedia

    INDEX
    Explanations

    references to testing and evaluation processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uros
    -0.20
    anst
    -0.16
    cheid
    -0.15
    .intellij
    -0.15
    uhn
    -0.15
     Andersen
    -0.14
    ective
    -0.14
     FactoryBot
    -0.14
    annis
    -0.14
    argar
    -0.14
    POSITIVE LOGITS
     cos
    0.17
    fare
    0.17
     COS
    0.16
     Provid
    0.16
     Superv
    0.15
    /Area
    0.15
    481
    0.15
    kos
    0.14
    oux
    0.14
     gar
    0.14
    Act Density 0.337%

    No Known Activations