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

    Neuronpedia

    INDEX
    Explanations

    references to specific reports, studies, or influences on social policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ock
    -0.16
    dados
    -0.16
    ırak
    -0.15
    yper
    -0.15
    otr
    -0.15
     ple
    -0.14
    ervo
    -0.14
    terra
    -0.14
    ubl
    -0.14
    acho
    -0.14
    POSITIVE LOGITS
    undry
    0.16
    âh
    0.15
    imdi
    0.14
     mdi
    0.14
    анд
    0.14
    å¹¹
    0.14
    rvine
    0.14
    emale
    0.14
    uzzi
    0.14
    adian
    0.13
    Act Density 0.166%

    No Known Activations