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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or authors in the context of academic or professional citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ello
    -0.22
    imal
    -0.18
    ouses
    -0.18
    ackers
    -0.18
    appen
    -0.18
    ellas
    -0.17
    abit
    -0.17
    á»Ĩ
    -0.17
    idden
    -0.17
    ansa
    -0.17
    POSITIVE LOGITS
    ruby
    0.20
    ureau
    0.18
    lady
    0.18
    rk
    0.18
    rone
    0.17
    riv
    0.17
    su
    0.17
    nat
    0.17
    rus
    0.17
    hend
    0.17
    Act Density 0.039%

    No Known Activations