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

    Neuronpedia

    INDEX
    Explanations

    references to news articles and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    herits
    -0.07
    ãĥ³ãĥĢ
    -0.06
    FunctionFlags
    -0.06
    apolis
    -0.06
     instead
    -0.06
    ninger
    -0.06
    ỳ
    -0.06
    etheless
    -0.06
    unction
    -0.05
    UNC
    -0.05
    POSITIVE LOGITS
    _TC
    0.07
    ovit
    0.07
    umba
    0.07
    anja
    0.07
    erah
    0.07
    chu
    0.07
    cea
    0.07
    wor
    0.06
    asil
    0.06
    uba
    0.06
    Act Density 0.011%

    No Known Activations