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

    Neuronpedia

    INDEX
    Explanations

    references to judges and judging processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibase
    -0.15
     âĹĦ
    -0.15
    /fixtures
    -0.15
     iddi
    -0.15
    ergus
    -0.15
    à¹Ĥม
    -0.14
     Tây
    -0.14
    лÑİ
    -0.14
     Stein
    -0.14
    oucher
    -0.14
    POSITIVE LOGITS
     metro
    0.17
    rey
    0.15
    vap
    0.15
    flex
    0.15
    opot
    0.14
    hn
    0.14
     flex
    0.14
    ney
    0.14
     dere
    0.14
    rig
    0.14
    Act Density 0.004%

    No Known Activations