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

    Neuronpedia

    INDEX
    Explanations

    references to contrasting perspectives or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥªãĤ«
    -0.16
    ible
    -0.16
    fty
    -0.16
    edly
    -0.16
    ryn
    -0.15
    ray
    -0.15
    enko
    -0.15
    koli
    -0.15
    sgi
    -0.15
    linkplain
    -0.14
    POSITIVE LOGITS
     side
    0.34
    world
    0.29
     Side
    0.26
     extreme
    0.25
    hand
    0.24
    Side
    0.24
    -side
    0.23
     lado
    0.23
    ness
    0.23
     half
    0.23
    Act Density 0.056%

    No Known Activations