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

    Neuronpedia

    INDEX
    Explanations

    technical specifications and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ening
    -0.17
    ongs
    -0.17
    ymes
    -0.16
     Leer
    -0.16
    oles
    -0.16
    uctor
    -0.15
    ented
    -0.15
    rette
    -0.15
    beits
    -0.14
    STITUTE
    -0.14
    POSITIVE LOGITS
    imen
    0.34
    ulative
    0.28
    imens
    0.27
    iale
    0.26
    IFIC
    0.24
     spec
    0.22
    (spec
    0.22
    ail
    0.22
    ifications
    0.21
    ified
    0.21
    Act Density 0.007%

    No Known Activations