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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and industry-specific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrat
    -0.17
    urma
    -0.15
    loat
    -0.15
    onaut
    -0.15
    VML
    -0.14
    ynet
    -0.14
    abwe
    -0.14
    strate
    -0.14
    illance
    -0.14
    elah
    -0.14
    POSITIVE LOGITS
    instead
    0.16
    iores
    0.15
     techniques
    0.14
     technique
    0.14
    aux
    0.14
    odium
    0.14
    óc
    0.14
    .setInt
    0.13
     Bav
    0.13
     principles
    0.13
    Act Density 0.399%

    No Known Activations