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

    Neuronpedia

    INDEX
    Explanations

    terms related to commenting or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.16
    upos
    -0.15
     Duffy
    -0.15
    egov
    -0.14
     Weiner
    -0.14
    ÏĢο
    -0.14
    rok
    -0.14
    ker
    -0.14
    ordo
    -0.14
    vr
    -0.14
    POSITIVE LOGITS
    ators
    0.20
    luv
    0.17
    aries
    0.17
    arendra
    0.16
    aires
    0.16
    ãĤ¹ãĥ¬
    0.16
    .nano
    0.16
    ghan
    0.15
    -reply
    0.15
    ary
    0.15
    Act Density 0.016%

    No Known Activations