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

    Neuronpedia

    INDEX
    Explanations

    references to "parametric" concepts or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mented
    -0.17
    istrat
    -0.16
    ép
    -0.15
    iste
    -0.14
    ieri
    -0.14
    riages
    -0.14
    haf
    -0.14
    ê°IJ
    -0.14
    IVA
    -0.14
    isci
    -0.14
    POSITIVE LOGITS
    etric
    0.31
    ilitary
    0.26
    agnetic
    0.25
    ater
    0.25
    ters
    0.23
    aters
    0.22
    etr
    0.21
    para
    0.21
    etrize
    0.20
    edics
    0.19
    Act Density 0.011%

    No Known Activations