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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .easy
    -0.16
    antis
    -0.13
     od
    -0.13
     initialized
    -0.13
    ivable
    -0.13
    folios
    -0.13
     shrink
    -0.13
     sist
    -0.13
     espos
    -0.13
    ãģĶãģĸ
    -0.13
    POSITIVE LOGITS
    upal
    0.14
     Weekend
    0.14
    anged
    0.14
    iga
    0.14
    ero
    0.14
     ns
    0.14
    hou
    0.14
    ειο
    0.13
     Reviews
    0.13
    pane
    0.13
    Act Density 0.200%

    No Known Activations